A H YBRID C RITICAL P ATH M ETHODOLOGY – ABCP (A S B UILT C RITICAL P ATH ); ITS I MPLEMENTATION AND A NALYSIS WITH ACO FOR M EDICAL I MAGE E DGE D ETECTION
The edge detection in an image has become an imminent process, with the edge of an image containing the
important information related to a particular image such as the pixel intensity value, m
inimal path
deciding factors, etc. This requires a specific methodology to guide in the detection of the edges, assign a
Critical Path with a minimal path set and their respective energy partitions. The basis for this approach is
the Optimized Ant Colony A
lgorithm [2], guiding through the various optimized structure in the edge
detection of an image. Here we have considered the scenario with respect to a Medical Image, as the
information contained in the obtained medical image is of high value and requires
a redundant loss in
information pertaining to the medical image obtained through various modalities. A proper plan with a
minimal set as Critical Path, analysis with respect to the Power partitions or the Energy partitions with the
minimal set, computation
of the total time taken by the algorithm to detect an edge and retrieve the data
with respect to the edge of a medical image, cumulatively considering the cliques, trade
-
offs in the intensity
and the number of iterations required to detect an edge in an
image, with or without the presence of
suitable noise factors in the image are the necessary aspects being addressed in this paper. This paper
includes an efficient hybrid approach to address the edge detection within an image and the consideration
of vari
ous other factors, including the Shortest path out of the all the paths being produced during the
traversing of the ants within a medical image, evaluation of the time duration empirically produced by the
ants in traversing the entire image. We also constr
uct a hybrid mechanism called ABCP (As Built Critical
Path) factor to show the deviation produced by the algorithm in covering the entire medical image, for the
metrics such as the shortest paths, computation time stamps obtained eventually and the planne
d
schedules.
This document proposes a method for improving medical image registration using mutual information. It aims to address limitations in standard mutual information-based registration when there are local intensity variations. The method incorporates spatial and geometric information by computing mutual information in regions identified by the Harris corner detection operator. These regions have large spatial variations that provide geometric information. The method is tested on synthetic and clinical data, showing improved registration accuracy. It is implemented on a GPU for increased parallel processing efficiency, providing a 4-46% speed improvement over standard registration methods.
This document presents a novel edge detection algorithm proposed for mammographic images. It begins with an abstract summarizing the paper's focus on edge detection in mammograms and comparison to other common edge detection methods. It then provides background on edge detection and medical image analysis, describing common gradient and derivative-based edge detection methods. The main body introduces a new two-phase edge detection process called Binary Homogeneity Enhancement Algorithm (BHEA) that homogenizes the mammogram and detects edges by traversing the image horizontally and vertically. Results from the new method are then compared to other common edge detection filters.
Medical Image segmentation using Image Mining conceptsEditor IJMTER
Image differencing is usually done by subtracting the low-level skin texture like strength
in images that are already associated. This paper extracts high-level skin texture in order to find out
an efficient image differencing method for the analysis of Brain Tumor. On the other hand, this
produces sets of skin texture that are both spatial. We demonstrate a technique that avoids arbitrary
spatial constraints and is robust in the presence of sound, outliers, and imaging artifact, while
outperforming even profitable products in the analysis of Brain Tumor images. First, the landmark
are establish, and then the top entrant are sorted into a end set. Second, the top sets of the two
descriptions are then differenced through a cluster judgment. The symmetry of the human body is
utilized to increase the accuracy of the finding. We imitate this technique in an effort to understand
and ultimately capture the judgment of the radiologist. The image differencing with clustered
contrast process determines the being there of Brain Tumor. Using the most favorable features
extracted from normal and tumor regions of MRI by using arithmetical features, classifiers are used
to categorize and segment the tumor portion in irregular images. Both the difficult and preparation
phase gives the proportion of accuracy on each parameter in neural networks, which gives the idea to
decide the best one to be used in supplementary works. The results showed outperformance of
algorithm when compared with classification accuracy which works as shows potential tool for
classification and requires extension in brain tumor analysis.
Fuzzy k c-means clustering algorithm for medical imageAlexander Decker
This document summarizes and compares several algorithms used for medical image segmentation, including thresholding, classifiers, Markov random field models, artificial neural networks, atlas-guided approaches, deformable models, and clustering analysis methods like k-means and fuzzy c-means. It provides details on the fuzzy c-means and k-means clustering algorithms, including their process and flowcharts. A new fuzzy k-c-means algorithm is proposed that combines fuzzy c-means and k-means clustering to improve segmentation time. The algorithms are tested on MRI brain images and their results are analyzed and compared based on time, iterations, and accuracy.
Image registration is the fundamental task used to
match two or more partially overlapping images taken, for
example, at different times,from different sensors, or from
different viewpoints and stitch these images into one
panoramic image comprising the whole scene. It is
afundamental image processing technique and is very useful
in integrating information from different sensors, finding
changes in images taken at different times, inferring threedimensional
information from stereo images, and recognizing
model-based objects.
This paper overviews the theoretical aspects of an image
registration problem. The purpose of this paper is to present a
survey of image registration techniques. This technique of
image registration aligns two images geometrically. These two
images are reference image and sensed image. The ultimate
purpose of digital image filtering is to support the visual
identification of certain features expressed by characteristic
shapes and patterns. Numerous recipes, algorithms and ready
made programs exist nowadays that predominantly have in
common that users have to set certain parameters.
Particularly if processing is fast and shows results rather
immediately, the choice of parameters may be guided by
making the image ―looking nice‖. However, in practical
situations most users are not in a mood to ―play around‖
with a displayed image, particularly if they are in a stressy
situation as it may encountered in security applications. The
requirements for the application of digital image processing
under such circumstances will be discussed with an example
of automaticfiltering without manual parameter settings that
even entails the advantage of delivering unbiased results
IRJET- Brain Tumour Detection and ART Classification Technique in MR Brai...IRJET Journal
This document describes a proposed method for detecting and classifying brain tumors in MR brain images using robust principal component analysis (RPCA) and quad tree (QT) decomposition for image fusion. The method involves fusing T1 and T2 MRI images using RPCA and QT decomposition. The fused image is then segmented using level set segmentation. Features are extracted from the segmented image using complete local binary pattern (CLBP) and pyramid histogram of oriented gradients (PHOG) approaches. The features are then classified using an adaptive resonance theory (ART) classifier to classify the brain tumor as malignant or benign. The proposed method aims to efficiently fuse multi-modal MRI images for improved brain tumor detection and classification.
This document summarizes a research paper on using bilateral symmetry analysis to detect brain tumors from MRI images. It begins by introducing the problem of brain tumor detection and importance of asymmetry analysis. It then describes the proposed algorithm which involves defining a bilateral symmetry axis between the two brain hemispheres and detecting any regions of asymmetry that could indicate a tumor. The algorithm uses edge detection techniques to find the symmetry axis. Performance is evaluated on sample patient data and results show the method can successfully identify tumor locations and sizes. In conclusion, analyzing bilateral symmetry is an effective approach for automated brain tumor detection from MRI images.
Comparative performance analysis of segmentation techniquesIAEME Publication
This document compares the performance of several image segmentation techniques: global thresholding, adaptive thresholding, region growing, and level set segmentation. It applies these techniques to medical and synthetic images corrupted with noise and evaluates the segmentation results using binary classification metrics like sensitivity, specificity, accuracy, and precision. The results show that level set segmentation best preserves object boundaries, adaptive thresholding captures most image details, and global thresholding has the highest success rate at extracting regions of interest. Overall, the study aims to determine the optimal segmentation method for medical images from CT scans.
This document proposes a method for improving medical image registration using mutual information. It aims to address limitations in standard mutual information-based registration when there are local intensity variations. The method incorporates spatial and geometric information by computing mutual information in regions identified by the Harris corner detection operator. These regions have large spatial variations that provide geometric information. The method is tested on synthetic and clinical data, showing improved registration accuracy. It is implemented on a GPU for increased parallel processing efficiency, providing a 4-46% speed improvement over standard registration methods.
This document presents a novel edge detection algorithm proposed for mammographic images. It begins with an abstract summarizing the paper's focus on edge detection in mammograms and comparison to other common edge detection methods. It then provides background on edge detection and medical image analysis, describing common gradient and derivative-based edge detection methods. The main body introduces a new two-phase edge detection process called Binary Homogeneity Enhancement Algorithm (BHEA) that homogenizes the mammogram and detects edges by traversing the image horizontally and vertically. Results from the new method are then compared to other common edge detection filters.
Medical Image segmentation using Image Mining conceptsEditor IJMTER
Image differencing is usually done by subtracting the low-level skin texture like strength
in images that are already associated. This paper extracts high-level skin texture in order to find out
an efficient image differencing method for the analysis of Brain Tumor. On the other hand, this
produces sets of skin texture that are both spatial. We demonstrate a technique that avoids arbitrary
spatial constraints and is robust in the presence of sound, outliers, and imaging artifact, while
outperforming even profitable products in the analysis of Brain Tumor images. First, the landmark
are establish, and then the top entrant are sorted into a end set. Second, the top sets of the two
descriptions are then differenced through a cluster judgment. The symmetry of the human body is
utilized to increase the accuracy of the finding. We imitate this technique in an effort to understand
and ultimately capture the judgment of the radiologist. The image differencing with clustered
contrast process determines the being there of Brain Tumor. Using the most favorable features
extracted from normal and tumor regions of MRI by using arithmetical features, classifiers are used
to categorize and segment the tumor portion in irregular images. Both the difficult and preparation
phase gives the proportion of accuracy on each parameter in neural networks, which gives the idea to
decide the best one to be used in supplementary works. The results showed outperformance of
algorithm when compared with classification accuracy which works as shows potential tool for
classification and requires extension in brain tumor analysis.
Fuzzy k c-means clustering algorithm for medical imageAlexander Decker
This document summarizes and compares several algorithms used for medical image segmentation, including thresholding, classifiers, Markov random field models, artificial neural networks, atlas-guided approaches, deformable models, and clustering analysis methods like k-means and fuzzy c-means. It provides details on the fuzzy c-means and k-means clustering algorithms, including their process and flowcharts. A new fuzzy k-c-means algorithm is proposed that combines fuzzy c-means and k-means clustering to improve segmentation time. The algorithms are tested on MRI brain images and their results are analyzed and compared based on time, iterations, and accuracy.
Image registration is the fundamental task used to
match two or more partially overlapping images taken, for
example, at different times,from different sensors, or from
different viewpoints and stitch these images into one
panoramic image comprising the whole scene. It is
afundamental image processing technique and is very useful
in integrating information from different sensors, finding
changes in images taken at different times, inferring threedimensional
information from stereo images, and recognizing
model-based objects.
This paper overviews the theoretical aspects of an image
registration problem. The purpose of this paper is to present a
survey of image registration techniques. This technique of
image registration aligns two images geometrically. These two
images are reference image and sensed image. The ultimate
purpose of digital image filtering is to support the visual
identification of certain features expressed by characteristic
shapes and patterns. Numerous recipes, algorithms and ready
made programs exist nowadays that predominantly have in
common that users have to set certain parameters.
Particularly if processing is fast and shows results rather
immediately, the choice of parameters may be guided by
making the image ―looking nice‖. However, in practical
situations most users are not in a mood to ―play around‖
with a displayed image, particularly if they are in a stressy
situation as it may encountered in security applications. The
requirements for the application of digital image processing
under such circumstances will be discussed with an example
of automaticfiltering without manual parameter settings that
even entails the advantage of delivering unbiased results
IRJET- Brain Tumour Detection and ART Classification Technique in MR Brai...IRJET Journal
This document describes a proposed method for detecting and classifying brain tumors in MR brain images using robust principal component analysis (RPCA) and quad tree (QT) decomposition for image fusion. The method involves fusing T1 and T2 MRI images using RPCA and QT decomposition. The fused image is then segmented using level set segmentation. Features are extracted from the segmented image using complete local binary pattern (CLBP) and pyramid histogram of oriented gradients (PHOG) approaches. The features are then classified using an adaptive resonance theory (ART) classifier to classify the brain tumor as malignant or benign. The proposed method aims to efficiently fuse multi-modal MRI images for improved brain tumor detection and classification.
This document summarizes a research paper on using bilateral symmetry analysis to detect brain tumors from MRI images. It begins by introducing the problem of brain tumor detection and importance of asymmetry analysis. It then describes the proposed algorithm which involves defining a bilateral symmetry axis between the two brain hemispheres and detecting any regions of asymmetry that could indicate a tumor. The algorithm uses edge detection techniques to find the symmetry axis. Performance is evaluated on sample patient data and results show the method can successfully identify tumor locations and sizes. In conclusion, analyzing bilateral symmetry is an effective approach for automated brain tumor detection from MRI images.
Comparative performance analysis of segmentation techniquesIAEME Publication
This document compares the performance of several image segmentation techniques: global thresholding, adaptive thresholding, region growing, and level set segmentation. It applies these techniques to medical and synthetic images corrupted with noise and evaluates the segmentation results using binary classification metrics like sensitivity, specificity, accuracy, and precision. The results show that level set segmentation best preserves object boundaries, adaptive thresholding captures most image details, and global thresholding has the highest success rate at extracting regions of interest. Overall, the study aims to determine the optimal segmentation method for medical images from CT scans.
A Novel Multiple-kernel based Fuzzy c-means Algorithm with Spatial Informatio...CSCJournals
Fuzzy c-means (FCM) algorithm has proved its effectiveness for image segmentation. However, still it lacks in getting robustness to noise and outliers, especially in the absence of prior knowledge of the noise. To overcome this problem, a generalized a novel multiple-kernel fuzzy cmeans (FCM) (NMKFCM) methodology with spatial information is introduced as a framework for image-segmentation problem. The algorithm utilizes the spatial neighborhood membership values in the standard kernels are used in the kernel FCM (KFCM) algorithm and modifies the membership weighting of each cluster. The proposed NMKFCM algorithm provides a new flexibility to utilize different pixel information in image-segmentation problem. The proposed algorithm is applied to brain MRI which degraded by Gaussian noise and Salt-Pepper noise. The proposed algorithm performs more robust to noise than other existing image segmentation algorithms from FCM family.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
journal publishing, how to publish research paper, Call For research paper, international journal, publishing a paper, IJERD, journal of science and technology, how to get a research paper published, publishing a paper, publishing of journal, publishing of research paper, reserach and review articles, IJERD Journal, How to publish your research paper, publish research paper, open access engineering journal, Engineering journal, Mathemetics journal, Physics journal, Chemistry journal, Computer Engineering, Computer Science journal, how to submit your paper, peer reviw journal, indexed journal, reserach and review articles, engineering journal, www.ijerd.com, research journals,
yahoo journals, bing journals, International Journal of Engineering Research and Development, google journals, hard copy of journal
Survey on Brain MRI Segmentation TechniquesEditor IJMTER
Image segmentation is aimed at cutting out, a ROI (Region of Interest) from an image. For
medical images, segmentation is done for: studying the anatomical structure, identifying ROI ie tumor
or any other abnormalities, identifying the increase in tissue volume in a region, treatment planning.
Currently there are many different algorithms available for image segmentation. This paper lists and
compares some of them. Each has their own advantages and limitations.
International Journal of Computational Engineering Research(IJCER) ijceronline
This document presents a hybrid methodology for classifying segmented images using both unsupervised and supervised classification techniques. The proposed methodology involves first segmenting the image into spectrally homogeneous regions using region growing segmentation. Then, a clustering algorithm is applied to the segmented regions for initial classification. Selected regions are used as training data for a supervised classification algorithm to further categorize the image. The hybrid approach combines the benefits of unsupervised clustering and supervised classification. The methodology is evaluated on natural and aerial images to compare its performance to existing seeded region growing and texture extraction segmentation methods.
Issues in Image Registration and Image similarity based on mutual informationDarshana Mistry
This is my 2nd Doctorate progresses committee presentation in image registration which is explained how do you find image similarity based on Entropy and mutual information
BFO – AIS: A FRAME WORK FOR MEDICAL IMAGE CLASSIFICATION USING SOFT COMPUTING...ijsc
Medical images provide diagnostic evidence/information about anatomical pathology. The growth in
database is enormous as medical digital image equipment’s like Magnetic Resonance Images (MRI),
Computed Tomography (CT), and Positron Emission Tomography CT (PET-CT) are part of clinical work.
CT images distinguish various tissues according to gray levels to help medical diagnosis. Ct is more
reliable for early tumours and haemorrhages detection as it provides anatomical information to plan radio
therapy. Medical information systems goals are to deliver information to right persons at the right time and
place to improve care process quality and efficiency. This paper proposes an Artificial Immune System
(AIS) classifier and proposed feature selection based on hybrid Bacterial Foraging Optimization (BFO)
with Local Search (LS) for medical image classification.
Lec5: Pre-Processing Medical Images (III) (MRI Intensity Standardization)Ulaş Bağcı
2017 Spring, UCF Medical Image Computing CAVA: Computer Aided Visualization and Analysis • CAD: Computer Aided Diagnosis • Definitions and Terminologies • Coordinate Systems • Pre-Processing Images – Volume of Interest – RegionofInterest – IntensityofInterest – ImageEnhancement • Filtering • Smoothing • Introduction to Medical Image Computing and Toolkits • Image Filtering, Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology
Medical Image Segmentation Based on Level Set MethodIOSR Journals
This document presents a new medical image segmentation technique based on the level set method. The technique uses a combination of thresholding, morphological erosion, and a variational level set method. Thresholding is applied to determine object pixels, followed by optional erosion to remove small fragments. Then a variational level set method is applied on the original image to evaluate the contour and segment objects. The technique is tested on various medical images and provides good segmentation results, though it struggles with complex images containing multiple distinct objects.
Lec8: Medical Image Segmentation (II) (Region Growing/Merging)Ulaş Bağcı
. Region Growing algorithm
• Homogeneity Criteria
• Split/Merge algorithm
• Examples from CT, MRI, PET
• Limitations
Image Filtering, Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology
Comparison of Feature selection methods for diagnosis of cervical cancer usin...IJERA Editor
Even though a great attention has been given on the cervical cancer diagnosis, it is a tuff task to observe the
pap smear slide through microscope. Image Processing and Machine learning techniques helps the pathologist
to take proper decision. In this paper, we presented the diagnosis method using cervical cell image which is
obtained by Pap smear test. Image segmentation performed by multi-thresholding method and texture and shape
features are extracted related to cervical cancer. Feature selection is achieved using Mutual Information(MI),
Sequential Forward Search (SFS), Sequential Floating Forward Search (SFFS) and Random Subset Feature
Selection(RSFS) methods.
Lec14: Evaluation Framework for Medical Image SegmentationUlaş Bağcı
How to evaluate accuracy of image segmentation?
– Gold standard ~ surrogate of truths
– Qualitative • Visual
• Inter-andintra-observeragreementrates – Quantitative
• Volumetricmeasurements(regression) • Regionoverlaps
• Shapebasedmeasurements
• Theoreticalcomparisons
• STAPLE,Uncertaintyguidance,andevaluationw/otruths
Clustering – K-means – FCM (fuzzyc-means) – SMC (simple membership based clustering) – AP(affinity propagation) – FLAB(fuzzy locally adaptive Bayesian) – Spectral Clustering Methods ShapeModeling – M-reps – Active Shape Models (ASM) – Oriented Active Shape Models (OASM) – Application in anatomy recognition and segmentation – Comparison of ASM and OASM ActiveContour(Snake) • LevelSet • Applications Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology Fuzzy Connectivity (FC) – Affinity functions • Absolute FC • Relative FC (and Iterative Relative FC) • Successful example applications of FC in medical imaging • Segmentation of Airway and Airway Walls using RFC based method Energy functional – Data and Smoothness terms • GraphCut – Min cut – Max Flow • ApplicationsinRadiologyImages
Morphological and wavelet transform techniques were applied to enhance mammographic phantom images containing microcalcifications, nodules, and fibrils. Four observers evaluated the original and enhanced images using receiver operating characteristic analysis and subjective rating scales. While some techniques improved detection of certain structures over original images based on ROC curve analysis, subjective ratings indicated original images had better contrast, sharpness, and quality. Overall, the enhancement methods did not consistently increase detection performance. Future work should focus on improving enhancement algorithms to more effectively enhance image quality and visualization without altering structure morphology.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
This document provides an overview of medical image segmentation techniques. It discusses fundamental medical image processing steps such as image capture, enhancement, segmentation, and feature extraction. Various segmentation methods are reviewed, including thresholding, region-based, edge detection, and hybrid techniques. The document emphasizes the need for developing robust segmentation methods that can recognize malignant growths early to improve cancer treatment outcomes.
Mri brain image retrieval using multi support vector machine classifiersrilaxmi524
This document discusses content-based image retrieval (CBIR) for medical images. It proposes using multiple query images instead of a single query image to improve retrieval accuracy. The system works by preprocessing queries, extracting features like texture from the queries, optimizing the features, using classifiers like SVM to categorize images, and then using KNN to retrieve similar images from the database based on feature matching. It claims this approach improves on existing CBIR systems that rely on annotations and have difficulties bridging the semantic gap between low-level features and high-level meanings.
Lec13: Clustering Based Medical Image Segmentation MethodsUlaş Bağcı
Clustering – K-means
– FCM (fuzzyc-means)
– SMC (simple membership based clustering) – AP(affinity propagation)
– FLAB(fuzzy locally adaptive Bayesian)
– Spectral Clustering Methods
ShapeModeling – M-reps – Active Shape Models (ASM) – Oriented Active Shape Models (OASM) – Application in anatomy recognition and segmentation – Comparison of ASM and OASM ActiveContour(Snake) • LevelSet • Applications Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology Fuzzy Connectivity (FC) – Affinity functions • Absolute FC • Relative FC (and Iterative Relative FC) • Successful example applications of FC in medical imaging • Segmentation of Airway and Airway Walls using RFC based method Energy functional – Data and Smoothness terms • GraphCut – Min cut – Max Flow • ApplicationsinRadiologyImages
Lec6: Pre-Processing for Nuclear Medicine ImagesUlaş Bağcı
2017 Spring, UCF Medical Image Computing
1. The use of PET/SPECT, PET/CT and MRI/PET Images
2. What to measure from Nuclear Medicine Images?
3. Denoising Nuclear MedicineI mages
4. PartialVolumeCorrection
ImageEnhancement • Filtering • Smoothing • Introduction to Medical Image Computing and Toolkits • Image Filtering, Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology
Mammogram image segmentation using rough clusteringeSAT Journals
This document discusses using rough clustering algorithms for mammogram image segmentation. It proposes using Rough K-Means clustering on Haralick texture features extracted from mammogram images. The Rough K-Means algorithm is compared to traditional K-Means and Fuzzy C-Means using metrics like mean square error and root mean square error. Preliminary results found that Rough K-Means produced better segmentation results than the other methods. The document provides background on rough set theory, image segmentation, feature extraction, and different clustering algorithms that can be used.
This document summarizes a research paper on segmenting and classifying brain tumors in MRI images using cellular automata and neural networks. The researchers first use co-occurrence matrices and run length features to automatically select seed points in abnormal tumor regions. A cellular automata algorithm then performs seeded segmentation on the images to detect and highlight the tumor region. Finally, the images are classified into normal, benign, or malignant categories using texture features and a radial basis function neural network. The neural network approach provides fast and accurate tumor classification compared to other methods. In summary, this paper presents an automatic method for segmenting and classifying brain tumors in MRI images based on cellular automata for segmentation and neural networks for classification.
This document discusses using ant colony optimization (ACO) for image edge detection. It begins with an introduction to how real ants find food sources by laying pheromone trails. It then presents the ACO edge detection model, which uses artificial ants to construct a pheromone matrix representing edge information. The ants move between adjacent pixels probabilistically based on pheromone levels and image features. After construction, the pheromone matrix is updated and used to classify pixels as edges or non-edges. Experimental results are presented but not described.
The document discusses ant colony optimization (ACO) algorithms. It introduces ACO as a probabilistic metaheuristic technique inspired by the behavior of ants seeking paths between their colony and food sources. It outlines the ACO metaheuristic and describes key ACO algorithms like Ant System, Ant Colony System, and MAX-MIN Ant System. The document also covers applications of ACO, advantages like inherent parallelism and efficient solutions to problems like the traveling salesman problem, and disadvantages like difficulty analyzing ACO theoretically.
A Novel Multiple-kernel based Fuzzy c-means Algorithm with Spatial Informatio...CSCJournals
Fuzzy c-means (FCM) algorithm has proved its effectiveness for image segmentation. However, still it lacks in getting robustness to noise and outliers, especially in the absence of prior knowledge of the noise. To overcome this problem, a generalized a novel multiple-kernel fuzzy cmeans (FCM) (NMKFCM) methodology with spatial information is introduced as a framework for image-segmentation problem. The algorithm utilizes the spatial neighborhood membership values in the standard kernels are used in the kernel FCM (KFCM) algorithm and modifies the membership weighting of each cluster. The proposed NMKFCM algorithm provides a new flexibility to utilize different pixel information in image-segmentation problem. The proposed algorithm is applied to brain MRI which degraded by Gaussian noise and Salt-Pepper noise. The proposed algorithm performs more robust to noise than other existing image segmentation algorithms from FCM family.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
journal publishing, how to publish research paper, Call For research paper, international journal, publishing a paper, IJERD, journal of science and technology, how to get a research paper published, publishing a paper, publishing of journal, publishing of research paper, reserach and review articles, IJERD Journal, How to publish your research paper, publish research paper, open access engineering journal, Engineering journal, Mathemetics journal, Physics journal, Chemistry journal, Computer Engineering, Computer Science journal, how to submit your paper, peer reviw journal, indexed journal, reserach and review articles, engineering journal, www.ijerd.com, research journals,
yahoo journals, bing journals, International Journal of Engineering Research and Development, google journals, hard copy of journal
Survey on Brain MRI Segmentation TechniquesEditor IJMTER
Image segmentation is aimed at cutting out, a ROI (Region of Interest) from an image. For
medical images, segmentation is done for: studying the anatomical structure, identifying ROI ie tumor
or any other abnormalities, identifying the increase in tissue volume in a region, treatment planning.
Currently there are many different algorithms available for image segmentation. This paper lists and
compares some of them. Each has their own advantages and limitations.
International Journal of Computational Engineering Research(IJCER) ijceronline
This document presents a hybrid methodology for classifying segmented images using both unsupervised and supervised classification techniques. The proposed methodology involves first segmenting the image into spectrally homogeneous regions using region growing segmentation. Then, a clustering algorithm is applied to the segmented regions for initial classification. Selected regions are used as training data for a supervised classification algorithm to further categorize the image. The hybrid approach combines the benefits of unsupervised clustering and supervised classification. The methodology is evaluated on natural and aerial images to compare its performance to existing seeded region growing and texture extraction segmentation methods.
Issues in Image Registration and Image similarity based on mutual informationDarshana Mistry
This is my 2nd Doctorate progresses committee presentation in image registration which is explained how do you find image similarity based on Entropy and mutual information
BFO – AIS: A FRAME WORK FOR MEDICAL IMAGE CLASSIFICATION USING SOFT COMPUTING...ijsc
Medical images provide diagnostic evidence/information about anatomical pathology. The growth in
database is enormous as medical digital image equipment’s like Magnetic Resonance Images (MRI),
Computed Tomography (CT), and Positron Emission Tomography CT (PET-CT) are part of clinical work.
CT images distinguish various tissues according to gray levels to help medical diagnosis. Ct is more
reliable for early tumours and haemorrhages detection as it provides anatomical information to plan radio
therapy. Medical information systems goals are to deliver information to right persons at the right time and
place to improve care process quality and efficiency. This paper proposes an Artificial Immune System
(AIS) classifier and proposed feature selection based on hybrid Bacterial Foraging Optimization (BFO)
with Local Search (LS) for medical image classification.
Lec5: Pre-Processing Medical Images (III) (MRI Intensity Standardization)Ulaş Bağcı
2017 Spring, UCF Medical Image Computing CAVA: Computer Aided Visualization and Analysis • CAD: Computer Aided Diagnosis • Definitions and Terminologies • Coordinate Systems • Pre-Processing Images – Volume of Interest – RegionofInterest – IntensityofInterest – ImageEnhancement • Filtering • Smoothing • Introduction to Medical Image Computing and Toolkits • Image Filtering, Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology
Medical Image Segmentation Based on Level Set MethodIOSR Journals
This document presents a new medical image segmentation technique based on the level set method. The technique uses a combination of thresholding, morphological erosion, and a variational level set method. Thresholding is applied to determine object pixels, followed by optional erosion to remove small fragments. Then a variational level set method is applied on the original image to evaluate the contour and segment objects. The technique is tested on various medical images and provides good segmentation results, though it struggles with complex images containing multiple distinct objects.
Lec8: Medical Image Segmentation (II) (Region Growing/Merging)Ulaş Bağcı
. Region Growing algorithm
• Homogeneity Criteria
• Split/Merge algorithm
• Examples from CT, MRI, PET
• Limitations
Image Filtering, Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology
Comparison of Feature selection methods for diagnosis of cervical cancer usin...IJERA Editor
Even though a great attention has been given on the cervical cancer diagnosis, it is a tuff task to observe the
pap smear slide through microscope. Image Processing and Machine learning techniques helps the pathologist
to take proper decision. In this paper, we presented the diagnosis method using cervical cell image which is
obtained by Pap smear test. Image segmentation performed by multi-thresholding method and texture and shape
features are extracted related to cervical cancer. Feature selection is achieved using Mutual Information(MI),
Sequential Forward Search (SFS), Sequential Floating Forward Search (SFFS) and Random Subset Feature
Selection(RSFS) methods.
Lec14: Evaluation Framework for Medical Image SegmentationUlaş Bağcı
How to evaluate accuracy of image segmentation?
– Gold standard ~ surrogate of truths
– Qualitative • Visual
• Inter-andintra-observeragreementrates – Quantitative
• Volumetricmeasurements(regression) • Regionoverlaps
• Shapebasedmeasurements
• Theoreticalcomparisons
• STAPLE,Uncertaintyguidance,andevaluationw/otruths
Clustering – K-means – FCM (fuzzyc-means) – SMC (simple membership based clustering) – AP(affinity propagation) – FLAB(fuzzy locally adaptive Bayesian) – Spectral Clustering Methods ShapeModeling – M-reps – Active Shape Models (ASM) – Oriented Active Shape Models (OASM) – Application in anatomy recognition and segmentation – Comparison of ASM and OASM ActiveContour(Snake) • LevelSet • Applications Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology Fuzzy Connectivity (FC) – Affinity functions • Absolute FC • Relative FC (and Iterative Relative FC) • Successful example applications of FC in medical imaging • Segmentation of Airway and Airway Walls using RFC based method Energy functional – Data and Smoothness terms • GraphCut – Min cut – Max Flow • ApplicationsinRadiologyImages
Morphological and wavelet transform techniques were applied to enhance mammographic phantom images containing microcalcifications, nodules, and fibrils. Four observers evaluated the original and enhanced images using receiver operating characteristic analysis and subjective rating scales. While some techniques improved detection of certain structures over original images based on ROC curve analysis, subjective ratings indicated original images had better contrast, sharpness, and quality. Overall, the enhancement methods did not consistently increase detection performance. Future work should focus on improving enhancement algorithms to more effectively enhance image quality and visualization without altering structure morphology.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
This document provides an overview of medical image segmentation techniques. It discusses fundamental medical image processing steps such as image capture, enhancement, segmentation, and feature extraction. Various segmentation methods are reviewed, including thresholding, region-based, edge detection, and hybrid techniques. The document emphasizes the need for developing robust segmentation methods that can recognize malignant growths early to improve cancer treatment outcomes.
Mri brain image retrieval using multi support vector machine classifiersrilaxmi524
This document discusses content-based image retrieval (CBIR) for medical images. It proposes using multiple query images instead of a single query image to improve retrieval accuracy. The system works by preprocessing queries, extracting features like texture from the queries, optimizing the features, using classifiers like SVM to categorize images, and then using KNN to retrieve similar images from the database based on feature matching. It claims this approach improves on existing CBIR systems that rely on annotations and have difficulties bridging the semantic gap between low-level features and high-level meanings.
Lec13: Clustering Based Medical Image Segmentation MethodsUlaş Bağcı
Clustering – K-means
– FCM (fuzzyc-means)
– SMC (simple membership based clustering) – AP(affinity propagation)
– FLAB(fuzzy locally adaptive Bayesian)
– Spectral Clustering Methods
ShapeModeling – M-reps – Active Shape Models (ASM) – Oriented Active Shape Models (OASM) – Application in anatomy recognition and segmentation – Comparison of ASM and OASM ActiveContour(Snake) • LevelSet • Applications Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology Fuzzy Connectivity (FC) – Affinity functions • Absolute FC • Relative FC (and Iterative Relative FC) • Successful example applications of FC in medical imaging • Segmentation of Airway and Airway Walls using RFC based method Energy functional – Data and Smoothness terms • GraphCut – Min cut – Max Flow • ApplicationsinRadiologyImages
Lec6: Pre-Processing for Nuclear Medicine ImagesUlaş Bağcı
2017 Spring, UCF Medical Image Computing
1. The use of PET/SPECT, PET/CT and MRI/PET Images
2. What to measure from Nuclear Medicine Images?
3. Denoising Nuclear MedicineI mages
4. PartialVolumeCorrection
ImageEnhancement • Filtering • Smoothing • Introduction to Medical Image Computing and Toolkits • Image Filtering, Enhancement, Noise Reduction, and Signal Processing • MedicalImageRegistration • MedicalImageSegmentation • MedicalImageVisualization • Machine Learning in Medical Imaging • Shape Modeling/Analysis of Medical Images Deep Learning in Radiology
Mammogram image segmentation using rough clusteringeSAT Journals
This document discusses using rough clustering algorithms for mammogram image segmentation. It proposes using Rough K-Means clustering on Haralick texture features extracted from mammogram images. The Rough K-Means algorithm is compared to traditional K-Means and Fuzzy C-Means using metrics like mean square error and root mean square error. Preliminary results found that Rough K-Means produced better segmentation results than the other methods. The document provides background on rough set theory, image segmentation, feature extraction, and different clustering algorithms that can be used.
This document summarizes a research paper on segmenting and classifying brain tumors in MRI images using cellular automata and neural networks. The researchers first use co-occurrence matrices and run length features to automatically select seed points in abnormal tumor regions. A cellular automata algorithm then performs seeded segmentation on the images to detect and highlight the tumor region. Finally, the images are classified into normal, benign, or malignant categories using texture features and a radial basis function neural network. The neural network approach provides fast and accurate tumor classification compared to other methods. In summary, this paper presents an automatic method for segmenting and classifying brain tumors in MRI images based on cellular automata for segmentation and neural networks for classification.
This document discusses using ant colony optimization (ACO) for image edge detection. It begins with an introduction to how real ants find food sources by laying pheromone trails. It then presents the ACO edge detection model, which uses artificial ants to construct a pheromone matrix representing edge information. The ants move between adjacent pixels probabilistically based on pheromone levels and image features. After construction, the pheromone matrix is updated and used to classify pixels as edges or non-edges. Experimental results are presented but not described.
The document discusses ant colony optimization (ACO) algorithms. It introduces ACO as a probabilistic metaheuristic technique inspired by the behavior of ants seeking paths between their colony and food sources. It outlines the ACO metaheuristic and describes key ACO algorithms like Ant System, Ant Colony System, and MAX-MIN Ant System. The document also covers applications of ACO, advantages like inherent parallelism and efficient solutions to problems like the traveling salesman problem, and disadvantages like difficulty analyzing ACO theoretically.
Ant colony optimization is a swarm intelligence technique inspired by the behavior of ants. It is used to find optimal paths or solutions to problems. The key aspects are that ants deposit pheromones as they move, influencing the paths other ants take, with shorter paths receiving more pheromones over time. This results in the emergence of the shortest path as the most favorable route. The algorithm is often applied to problems like the traveling salesman problem to find the shortest route between nodes.
Ant colony optimization (ACO) is a heuristic optimization algorithm inspired by the foraging behavior of ants. It is used to find optimal paths in graph problems. The algorithm operates by simulating ants walking around the problem space, depositing and following pheromone trails. Over time, as ants discover short paths, the pheromone density increases on those paths, making them more desirable for future ants. This positive feedback eventually leads all ants to converge on the shortest path. ACO has been applied successfully to problems like the traveling salesman problem.
The document discusses ant colony optimization (ACO), which is a metaheuristic algorithm inspired by the behavior of real ant colonies. It describes how real ants deposit pheromone trails to communicate indirectly and find the shortest path between their colony and food sources. The algorithm works by "artificial ants" probabilistically building solutions to optimization problems and adjusting pheromone levels based on solution quality, similar to how real ants reinforce shorter paths. It provides examples of how ACO has been applied to problems like the traveling salesman problem and discusses some extensions to the basic ACO algorithm.
Similar to A H YBRID C RITICAL P ATH M ETHODOLOGY – ABCP (A S B UILT C RITICAL P ATH ); ITS I MPLEMENTATION AND A NALYSIS WITH ACO FOR M EDICAL I MAGE E DGE D ETECTION
A MORPHOLOGICAL MULTIPHASE ACTIVE CONTOUR FOR VASCULAR SEGMENTATIONijbbjournal
This paper presents a morphological active contour ideal for vascular segmentation in biomedical images.
The unenhanced images of vessels and background are successfully segmented using a two-step
morphological active contour based upon Chan and Vese’s Active Contour without Edges. Using dilation
and erosion as an approximation of curve evolution, the contour provides an efficient, simple, and robust
alternative to solving partial differential equations used by traditional level-set Active Contour models. The
proposed method is demonstrated with segmented data set images and compared to results garnered from
multiphase Active Contour without Edges, morphological watershed, and Fuzzy C-means segmentations.
IRJET- Proposed System for Animal Recognition using Image ProcessingIRJET Journal
The document proposes an animal recognition system using image processing. It would use PCA algorithms and eigenfaces methods to identify animals from images captured by existing cameras in nature reserves. This would allow authorities to be alerted of the presence of dangerous animals so people in the reserves can live without fear of attack. The system would analyze images to extract features, calculate covariances and eigenvectors to identify animals based on training data from five classes of animals. If implemented, it could automate animal detection compared to relying on human monitoring of video feeds.
A NEW APPROACH OF BRAIN TUMOR SEGMENTATION USING FAST CONVERGENCE LEVEL SETijbesjournal
Segmentation of region of interest has a critical task in image processing applications. The accuracy of Segmentation is based on processing methodology and limiting value used. In this paper, an enhanced approach of region segmentation using level set (LS) method is proposed, which is achieved by using cross over point in the valley point as a new dynamic stopping criterion in the level set segmentation. The proposed method has been tested with developed database of MR Images. From the test results, it is found that proposed method improves the convergence performance such as complexity in terms of number of iterations, delay and resource overhead as compared to conventional level set based segmentation
approach.
This document discusses using Fourier transforms to measure image similarity. It proposes a metric that uses both the real and complex components of the Fourier transform to compute a similarity ranking between two images. The metric calculates the intersection of the covariance matrix of the Fourier transform magnitude and phase spectra of the two images. The approach is shown to be advantageous for images with varying degrees of lighting. It summarizes existing methods for image comparison and feature extraction, and discusses implementing the proposed similarity metric using OpenCV. Sample results are given comparing the new Fourier-based method to existing histogram comparison techniques.
Comparative analysis of multimodal medical image fusion using pca and wavelet...IJLT EMAS
nowadays, there are a lot of medical images and their
numbers are increasing day by day. These medical images are
stored in large database. To minimize the redundancy and
optimize the storage capacity of images, medical image fusion is
used. The main aim of medical image fusion is to combine
complementary information from multiple imaging modalities
(Eg: CT, MRI, PET etc.) of the same scene. After performing
image fusion, the resultant image is more informative and
suitable for patient diagnosis. There are some fusion techniques
which are described in this paper to obtain fused image. This
paper presents two approaches to image fusion, namely Spatial
Fusion and Transform Fusion. This paper describes Techniques
such as Principal Component Analysis which is spatial domain
technique and Discrete Wavelet Transform, Stationary Wavelet
Transform which are Transform domain techniques.
Performance metrics are implemented to evaluate the
performance of image fusion algorithm. An experimental result
shows that image fusion method based on Stationary Wavelet
Transform is better than Principal Component Analysis and
Discrete Wavelet Transform.
The document proposes a new feature descriptor called Local Bit-Plane Wavelet Pattern (LBWP) to improve content-based retrieval of biomedical images like CT and MRI scans. LBWP encodes relationships between pixel intensities in different bit planes and applies a wavelet function, capturing more fine-grained image details than prior methods. Evaluation on a dataset from The Cancer Imaging Archive showed LBWP outperformed existing approaches like Local Wavelet Pattern with higher average retrieval precision, rate, and F-score.
This document summarizes a research article that proposes using a Bayesian classifier to aid in level set segmentation for early detection of diabetic retinopathy. Level set segmentation is used to segment retinal images and detect small blood clots. A Bayesian classifier is applied to help propagate the level set contour and classify pixels as normal blood vessels or abnormal blood clots. The method was tested on retinal images and showed it could detect small clots of 0.02mm, indicating it may help detect early proliferation stages. Results demonstrated it outperformed other methods in detecting minute clots for early stage proliferation detection.
IRJET- Retinal Fundus Image Segmentation using Watershed AlgorithmIRJET Journal
This document presents a method for segmenting retinal fundus images using the watershed algorithm to detect the optic disk and identify potential eye cancer. It involves pre-processing the fundus image, enhancing it with histogram equalization, applying Sobel edge detection to capture edges, segmenting the image using watershed segmentation based on gradient magnitude, and applying circular Hough transform to approximate the optic disk boundary with a circle. The method then analyzes the optic disk area and size to detect potential cancer, displaying the results to the user. It aims to develop an automated system to assist in early detection of eye diseases from fundus images.
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...IRJET Journal
This document summarizes a research paper that proposes a method for detecting brain tumors by fusing CT and MRI images using stationary wavelet transform and a probabilistic neural network classifier. The proposed method involves preprocessing the CT and MRI images using median filtering for noise removal. It then applies stationary wavelet transform to the images to extract features before segmenting the tumor region using k-means clustering. Finally, the probabilistic neural network classifier determines if the tumor is benign or malignant based on the fused image features. The paper reviews other existing fusion and classification methods and argues that the proposed stationary wavelet transform and probabilistic neural network approach provides better detection of brain tumors.
V. Karthikeyan proposes a novel histogram-based image registration technique. The method segments images using multiple histogram thresholds to extract objects. Extracted objects are characterized by attributes like area, axis ratio, and fractal dimension. Objects between images are matched to estimate rotation and translation. The technique was tested on pairs of images with different rotations and translations and achieved sub-pixel accuracy in registration. The method outperformed other techniques like SIFT for remote sensing images. Future work could optimize the segmentation and apply the technique to multispectral images.
BFO – AIS: A Framework for Medical Image Classification Using Soft Computing ...ijsc
Medical images provide diagnostic evidence/information about anatomical pathology. The growth in database is enormous as medical digital image equipment’s like Magnetic Resonance Images (MRI), Computed Tomography (CT), and Positron Emission Tomography CT (PET-CT) are part of clinical work. CT images distinguish various tissues according to gray levels to help medical diagnosis. Ct is more reliable for early tumours and haemorrhages detection as it provides anatomical information to plan radio therapy. Medical information systems goals are to deliver information to right persons at the right time and place to improve care process quality and efficiency. This paper proposes an Artificial Immune System (AIS) classifier and proposed feature selection based on hybrid Bacterial Foraging Optimization (BFO) with Local Search (LS) for medical image classification.
Analysis of contrast concentration for radiological images using cbir frameworkIAEME Publication
This document summarizes a research paper that proposes a framework for analyzing contrast concentration in radiological images using content-based image retrieval (CBIR). The framework uses adaptive complex independent component analysis and a reference region method to calculate intravascular contrast concentration, which is then corrected using pharmacokinetic modeling. CBIR is then used to incorporate the results into an MRI image database for similarity matching and image retrieval. The goal is to more precisely identify contrast agents in prostate cancer diagnosis to help physicians determine the correct treatment.
Analysis of Efficient Wavelet Based Volumetric Image CompressionCSCJournals
Recently, the wavelet transform has emerged as a cutting edge technology, within the field of image compression research. Telemedicine, among other things, involves storage and transmission of medical images, popularly known as teleradiology. Due to constraints on bandwidth and storage capacity, a medical image may be needed to be compressed before transmission/storage. This paper is focused on selecting the most appropriate wavelet transform for a given type of medical image compression. In this paper we have analysed the behaviour of different type of wavelet transforms with different type of medical images and identified the most appropriate wavelet transform that can perform optimum compression for a given type of medical image. To analyze the performance of the wavelet transform with the medical images at constant PSNR, we calculated SSIM and their respective percentage compression.
Image Retrieval using Graph based Visual SaliencyIRJET Journal
This document discusses image retrieval using graph-based visual saliency. It begins with an abstract that describes saliency detection methods and graph-based visual saliency (GBVS), which forms activation maps from image features and normalizes them to highlight salient parts. The purpose is to evaluate GBVS using statistical metrics like precision and recall, and to use genetic algorithms to improve its performance. It then provides background on saliency, different saliency approaches, what graph-based visual saliency is, its advantages and applications. Finally, it reviews several related works on visual saliency models.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
The document presents a new approach called Linear Curvature Empirical Coding (LCEC) for image retrieval. LCEC aims to improve upon existing curvature-based coding approaches by linearly representing the curvature scale space plot and then applying empirical coding to select descriptive shape features. The linear representation considers variations across all smoothing factors rather than discarding information below a threshold. Empirical coding is used to select features based on variation density rather than just magnitudes. The results show LCEC performs better than previous methods for image retrieval.
Empirical Coding for Curvature Based Linear Representation in Image Retrieval...iosrjce
The document presents a new approach called Linear Curvature Empirical Coding (LCEC) for image retrieval. LCEC aims to improve upon existing curvature-based coding approaches by linearly representing the curvature scale space plot and then applying empirical coding to select descriptive shape features. The linear representation considers variations across all smoothing factors rather than discarding information below a threshold. Empirical coding is used to select features based on variation density rather than just magnitude. The results show LCEC performs better than previous methods for image retrieval.
IRJET- Blood Vessel Segmentation & Analysis in Retinal Images using Image Pro...IRJET Journal
This document discusses a proposed method for segmenting and analyzing blood vessels in retinal images using image processing techniques. It begins with an abstract that outlines segmenting retinal images to extract blood vessels in order to analyze features like thickness and width that can help in diagnosing diseases. It then provides more details on the proposed method which includes steps like image segmentation, vessel enhancement filtering using techniques like median filtering, morphological reconstruction filtering, and using a K-nearest neighbors algorithm for classification. The key steps and techniques are illustrated through a flowchart and example results of applying the method to a retinal image.
Contour evolution method for precise boundary delineation of medical imagesTELKOMNIKA JOURNAL
Image segmentation is an important precursor to boundary delineation of medical images. One of the major challenges in applying automatic image segmentation in medical images is the imperfection in the imaging process which can result in inconsistent contrast and brightness levels, and low image sharpness and vanishing boundaries. Although recent advances in deep learning produce vast improvements in the quality of image segmentation, the accuracy of segmentation around object boundaries still requires improvement. We developed a new approach to contour evolution that is more intuitive but shares some common principles with the active contour model method. The method uses two concepts, namely the boundary grid and sparse boundary representation, as an implicit and explicit representation of the boundary points. We tested our method using lumbar spine MRI images of 515 patients. The experiment results show that our method performs up to 10.2 times faster and more flexible than the geodesic active contours method. Using BF-score contour-based metric, we show that our method improves the boundary accuracy from 74% to 84% as opposed to 63% by the latter method.
Classification of Osteoporosis using Fractal Texture FeaturesIJMTST Journal
In our proposed method an automatic Osteoporosis classification system is developed. The input of the system is Lumbar spine digital radiograph, which is subjected to pre-processing which includes conversion of grayscale image to binary image and enhancement using Contrast Limited Adaptive Histogram Equalization technique(CLAHE). Further Fractal Texture features(SFTA) are extracted, then the image is classified as Osteoporosis, Osteopenia and Normal using a Probabilistic Neural Network(PNN). A total of 158 images have been used, out of which 86 images are used for training the network and 32 images for testing and 40 images for validation. The network is evaluated using a confusion matrix and evaluation parameters like Sensitivity, Specificity, precision and Accuracy are computed fractal feature extraction techniques.
Similar to A H YBRID C RITICAL P ATH M ETHODOLOGY – ABCP (A S B UILT C RITICAL P ATH ); ITS I MPLEMENTATION AND A NALYSIS WITH ACO FOR M EDICAL I MAGE E DGE D ETECTION (20)
THE USE OF VIRTUAL PRIVATE NETWORK IN THE CONTEXT OF “BRING YOUR OWN DEVICE” ...ijcsitcejournal
Using a Virtual Private Network (VPN) for remote work provides an added layer of security by encrypting
the internet connection. It helps protect sensitive data and prevents unauthorized access. With a VPN,
employees can securely access company resources and files from anywhere in the world. This allows for
greater flexibility in work arrangements and enables employees to collaborate seamlessly. Implementing a
VPN as a remote workplace solution can lead to cost savings for businesses. It eliminates the need for
physical office space and reduces expenses associated with commuting and travel.
While VPNs offer numerous benefits for remote work, it is crucial for organizations to implement proper
security measures and educate employees on best practices to realize this technology's full potential. This
article explores the change in the use of VPNs during and after the Covid-19 pandemic era. A short
literature review precedes the opinion of the information security community about the usage and role of
VPNs in efficiently securing information and information systems.
PANDEMIC INFORMATION DISSEMINATION WEB APPLICATION: A MANUAL DESIGN FOR EVERYONEijcsitcejournal
The aim of this research is to generate a web application from an inedited methodology with a series of
instructions indicating the coding in a flow diagram. The primary purpose of this methodology is to aid
non-profits in disseminating information regarding the COVID-19 pandemic, so that users can share vital
and up-to-date information. This is a functional design, and a series of screenshots demonstrating its
behaviour is presented below. This unique design arose from the necessity to create a web application for
an information dissemination platform; it also addresses an audience that does not have programming
knowledge. This document uses the scientific method in its writing. The authors understand that there is a
similar design in the bibliography; therefore, the differences between the designs are described herein; it
is very important to point out that this proposal can be taken as an alternative to the design of any web
application.
Library Information Retrieval (IR) System of University of Cyprus (UCY)ijcsitcejournal
Building an effective Information Retieval (IR) System for such a complex sector like a library, is indeed a challenging task. Creating this kind of applications, one must be aware of basic IR methodologies and structures used, as well as the User’s Experience requirements. Combining different technologies for creating different kinds of applications has been one of the major problems in software reuse. However, in recent years, many frameworks that offer a complete suite for developing cross-platform applications have been developed. In this paper, we present a combination of breakthrough technologies and frameworks for developing a Python based RestAPI, an Administrator’s side desktop application and a cross-platform application powered by Ionic, Angular, HTML and CSS, as the main IR tool of UCY’s library.
In this paper, a fruit image data set is used to compare the efficiency and accuracy of two widely used Convolutional Neural Network, namely the ResNet and the DenseNet, for the recognition of 50 different kinds of fruits. In the experiment, the structure of ResNet-34 and DenseNet_BC-121 (with bottleneck layer) are used. The mathematic principle, experiment detail and the experiment result will be explained through comparison.
NETCDL : THE NETWORK CERTIFICATION DESCRIPTION LANGUAGEijcsitcejournal
Modern IP networks are complex entities that require constant maintenance and care. Similarly, constructing a new network comes with a high amount of upfront cost, planning, and risk. Unlike the disciplines of software and hardware engineering, networking and IT professionals lack an expressive and useful certification language that they can use to verify that their work is correct. When installing and maintaining networks without a standard for describing their behavior, teams find themselves prone to making configuration mistakes. These mistakes can have real monetary and operational efficiency costs for organizations that maintain large networks.In this research, the Network Certification Description Language (NETCDL) is proposed as an easily human readable and writeable language that is used to describe network components and their desired behavior. The complexity of the grammar is shown to rank in the top 5 out of 31 traditional computer language grammars, as measured by metrics suite. The language is also shown to be able to express the majority of common use cases in network troubleshooting. A workflow involving a certifier tool is proposed that uses NETCDL to verify network correctness, and a reference certifier design is presented to guide and standardize future implementations.
PREDICTIVE MODEL FOR LIKELIHOOD OF DETECTING CHRONIC KIDNEY FAILURE AND DISEA...ijcsitcejournal
Fuzzy logic is highly appropriate and valid basis for developing knowledge-based systems in medicine for different tasks and it has been known to produce highly accurate results. Examples of such tasks include syndrome differentiation, likelihood survival for sickle cell anaemia among paediatric patients, diagnosis and optimal selection of medical treatments and real time monitoring of patients. For this paper, a Fuzzy logic-based system is untaken used to provide a comprehensive simulation of a prediction model for determining the likelihood of detecting Chronic Kidney failure/diseases in humans. The Fuzzy-based system uses a 4-tuple record comprising of the following test taken: Blood Urea Test, Urea Clearance Test, Creatinine Clearance test and Estimated Glomerular Filtrate
ate(eGFR).Understanding of the test was elicited from a private hospital in Ibadan through the help of an experienced and qualified nurse which also follows same test according to National Kidney Foundation. This knowledge was then used in the developing the simulated and rule-base prediction model using MATLAB software. The paper also follows the 3 major stages of Fuzzy logic. The results of fuzzification of variables, inference, model testing and defuzzification of variables was also presented. This in turn simplifies the complication involved in detecting Chronic Kidney failure/disease using Fuzzy logic based model.
NEURO-FUZZY APPROACH FOR DIAGNOSING AND CONTROL OF TUBERCULOSISijcsitcejournal
Tuberculosis is the second leading cause of death from an infectious disease worldwide, after the human
immunodeficiency virus. The main aim of this research work is to develop a Neuro-Fuzzy system for diagnosing tuberculosis. The system is structured with to accept symptoms with the help of three domain Medical expertise as inputs that are used to automatically generate rules that are injected in to the knowledge based where the system would use to make decisions and draw a conclusion. MATLAB 7.0 is used to implement this experiment using fuzzy logic and Neural Network toolbox. In this experiment linguistic variables are evaluated using Gaussian membership function. This system will offer potential assistance to medical practitioners and healthcare sector in making prompt decision during the diagnosis of tuberculosis. In this work basic emblematic approach using Neuro-fuzzy methodology is presented that describes a technique to forecast the existence of mycobacterium and provides support platform to researchers in the related field.
A STUDY ON OPTICAL CHARACTER RECOGNITION TECHNIQUESijcsitcejournal
Optical Character Recognition (OCR) is the process which enables a system to without human intervention
identifies the scripts or alphabets written into the users’ verbal communication. Optical Character
identification has grown to be individual of the mainly flourishing applications of knowledge in the field of
pattern detection and artificial intelligence. In our survey we study on the various OCR techniques. In this
paper we resolve and examine the hypothetical and numerical models of Optical Character Identification.
The Optical character identification or classification (OCR) and Magnetic Character Recognition (MCR)
techniques are generally utilized for the recognition of patterns or alphabets. In general the alphabets are
in the variety of pixel pictures and it could be either handwritten or stamped, of any series, shape or
direction etc. Alternatively in MCR the alphabets are stamped with magnetic ink and the studying machine
categorize the alphabet on the basis of the exclusive magnetic field that is shaped by every alphabet. Both
MCR and OCR discover utilization in banking and different trade appliances. Earlier exploration going on
Optical Character detection or recognition has shown that the In Handwritten text there is no limitation
lying on the script technique. Hand written correspondence is complicated to be familiar through due to
diverse human handwriting style, disparity in angle, size and shape of calligraphy. An assortment of
approaches of Optical Character Identification is discussed here all along through their achievement.
The International Journal of Computational Science, Information Technology an...ijcsitcejournal
The International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) is an open access peer-reviewed journal that publishes articles on computational science, mathematical modeling, information technology, computer science, control and automation engineering. The goal of the journal is to bring together researchers from academia and industry in these fields and establish new collaborations. The journal focuses on technical and practical aspects of scientific computing, modeling and simulation, information technology, computer science, networks, communication engineering, control theory and automation.
SEARCH OF INFORMATION BASED CONTENT IN SEMI-STRUCTURED DOCUMENTS USING INTERF...ijcsitcejournal
This paper proposes a semi-structured information retrieval model based on a new method for calculation
of similarity. We have developed CASISS (Calculation of Similarity of Semi-Structured documents)
method to quantify how two given texts are similar. This new method identifies elements of semi-structured
documents using elements descriptors. Each semi-structured document is pre-processed before the
extraction of a set of descriptors for each element, which characterize the contents of elements.It can be
used to increase the accuracy of the information retrieval process by taking into account not only the
presence of query terms in the given document but also the topology (position continuity) of these terms.
ON INCREASING OF DENSITY OF ELEMENTS IN A MULTIVIBRATOR ON BIPOLAR TRANSISTORSijcsitcejournal
In this paper we consider an approach to increase density of elements of a multivibrator on bipolar transistors.
The considered approach based on manufacturing a heterostructure with necessity configuration,
doping by diffusion or ion implantation of required areas to manufacture the required type of conductivity
(p or n) in the areas and optimization of annealing of dopant and/or radiation defects to manufacture more
compact distributions of concentrations of dopants. We also introduce an analytical approach to prognosis
technological process.
DESIGN OF FAST TRANSIENT RESPONSE, LOW DROPOUT REGULATOR WITH ENHANCED STEADY...ijcsitcejournal
Design and implementation of control systems for power supplies require the use of efficient techniques that
provide simple and practical solutions in order to fulfill the performance requirements at an acceptable cost.
Application of manual methods of system identification in determining optimal values of controller settings is
quite time-consuming, expensive and, sometimes, may be impossible to practically carry out. This paper
describes an analytical method for the design of a control system for a fast transient response, low dropout
(LDO) linear regulated power supply on the basis of PID compensation. The controller parameters are
obtained from analytical model of the regulator circuit. Test results showed good dynamic characteristics
with adequate margin of stability. This study shows that PID parameter values sufficiently close to optimum
can easily be obtained from analytical study of the regulator system. The applied method of determining
controller settings greatly reduces design time and cost.
OPTIMIZATION OF MANUFACTURING OF LOGICAL ELEMENTS "AND" MANUFACTURED BY USING...ijcsitcejournal
In this paper we introduce an approach to decrease dimensions of logical elements "AND" based on fieldeffect
heterotransistors. Framework the approach one shall consider a heterostructure with specific structure.
Several specific areas of the het
CHAOS CONTROL VIA ADAPTIVE INTERVAL TYPE-2 FUZZY NONSINGULAR TERMINAL SLIDING...ijcsitcejournal
In this paper, a novel robust adaptive type-2 fuzzy nonsingular sliding mode controller is proposed to
stabilize the unstable periodic orbits of uncertain perturbed chaotic system with internal parameter
uncertainties and external disturbances. This letter is assumed to have an affine form with unknown
mathematical model, the type-2 fuzzy system is used to overcome this constraint. A global nonsingular
terminal sliding mode manifold is proposed to eliminate the singularity problem associated with normal
terminal sliding mode control. The proposed control law can drive system tracking error to converge to
zero in finite time. The adaptive type-2 fuzzy system used to model the unknown dynamic of system is
adjusted on-line by adaptation law deduced from the stability analysis in Lyapunov sense. Simulation
results show the good tracking performances, and the efficiently of the proposed approach.
On optimization ofON OPTIMIZATION OF DOPING OF A HETEROSTRUCTURE DURING MANUF...ijcsitcejournal
We introduce an approach of manufacturing of a p-i-n-heterodiodes. The approach based on using a δ-
doped heterostructure, doping by diffusion or ion implantation of several areas of the heterostructure. After
the doping the dopant and/or radiation defects have been annealed. We introduce an approach to optimize
annealing of the dopant and/or radiation defects. We determine several conditions to manufacture more
compact p-i-n-heterodiodes
A N APPROACH TO MODEL OPTIMIZATION OF MA N- UFACTURING OF EMI T TER - COUPLE...ijcsitcejournal
In this paper we consider an approach to optimiz
e
manufacturing elements of emitter
-
coupled logic. The
optimization
leads
to decreas
ing
dimensions of these elements.
Framework this pa
per we consider man
u-
facturing
these
elements of emitter
-
coupled logic
framework
a heterostructure with required configur
a
tion
.
After grown the heterostructure
the
required areas
have been doped
by diffusion or ion implant
a
tion
.
It is
attracted an interest
optimization of annealing of dopant and/or radiation defects
to decrease dimensions
of the considered elements
.
We co
n
sider
an approach
to make the optimization.
The modeling part based
on modified method of functional corrections, which
gives us possibili
ty to analyzed manufacturing the
elements of emitter
-
coupled logic
without crosslinking of solutions on interfaces between layers of heter
o-
stru
c
ture
A N E XQUISITE A PPROACH FOR I MAGE C OMPRESSION T ECHNIQUE USING L OSS...ijcsitcejournal
The imminent evolution in the field of medical imaging, telehealth and teleradiology services has been on a
significant rise with a dire need for a proficient structure for the compression of a DICOM (Digital
Imaging and Communications
in Medicine) standard medical image obtained through various modalities,
with clinical relevance and digitized clinical data, and various other diagnostic phenomena and the
progressive transmission of such a medical image over varying bandwidths. The data
loss redundancy
during the process of compression is to be maintained below the alarming level, meaning it is to be under
scanner without the loss of data/information. In this paper we present an efficient time bound algorithm
that utilizes a process flow
wherein multiple ROI sectors as well as the Non
-
ROI sector of the DICOM
image are considered in the algorithmic machine and the compression is done based upon a hybrid
compression algorithm by LZW & SPIHT encoder & decoder machines. The paper provides a m
agnitude of
the overall compression ratio involved in thus compressing the DICOM standard image. It also provides a
brief description about the PSNR values obtained after suitably compressing the image. We analyze the
various encoder scenarios and have pro
jected a suitable hybrid lossless compression algorithm that helps
in the retrieval of the data/information related to the image.
HCL Notes and Domino License Cost Reduction in the World of DLAUpanagenda
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-and-domino-license-cost-reduction-in-the-world-of-dlau/
The introduction of DLAU and the CCB & CCX licensing model caused quite a stir in the HCL community. As a Notes and Domino customer, you may have faced challenges with unexpected user counts and license costs. You probably have questions on how this new licensing approach works and how to benefit from it. Most importantly, you likely have budget constraints and want to save money where possible. Don’t worry, we can help with all of this!
We’ll show you how to fix common misconfigurations that cause higher-than-expected user counts, and how to identify accounts which you can deactivate to save money. There are also frequent patterns that can cause unnecessary cost, like using a person document instead of a mail-in for shared mailboxes. We’ll provide examples and solutions for those as well. And naturally we’ll explain the new licensing model.
Join HCL Ambassador Marc Thomas in this webinar with a special guest appearance from Franz Walder. It will give you the tools and know-how to stay on top of what is going on with Domino licensing. You will be able lower your cost through an optimized configuration and keep it low going forward.
These topics will be covered
- Reducing license cost by finding and fixing misconfigurations and superfluous accounts
- How do CCB and CCX licenses really work?
- Understanding the DLAU tool and how to best utilize it
- Tips for common problem areas, like team mailboxes, functional/test users, etc
- Practical examples and best practices to implement right away
GraphSummit Singapore | The Future of Agility: Supercharging Digital Transfor...Neo4j
Leonard Jayamohan, Partner & Generative AI Lead, Deloitte
This keynote will reveal how Deloitte leverages Neo4j’s graph power for groundbreaking digital twin solutions, achieving a staggering 100x performance boost. Discover the essential role knowledge graphs play in successful generative AI implementations. Plus, get an exclusive look at an innovative Neo4j + Generative AI solution Deloitte is developing in-house.
Communications Mining Series - Zero to Hero - Session 1DianaGray10
This session provides introduction to UiPath Communication Mining, importance and platform overview. You will acquire a good understand of the phases in Communication Mining as we go over the platform with you. Topics covered:
• Communication Mining Overview
• Why is it important?
• How can it help today’s business and the benefits
• Phases in Communication Mining
• Demo on Platform overview
• Q/A
Maruthi Prithivirajan, Head of ASEAN & IN Solution Architecture, Neo4j
Get an inside look at the latest Neo4j innovations that enable relationship-driven intelligence at scale. Learn more about the newest cloud integrations and product enhancements that make Neo4j an essential choice for developers building apps with interconnected data and generative AI.
GraphRAG for Life Science to increase LLM accuracyTomaz Bratanic
GraphRAG for life science domain, where you retriever information from biomedical knowledge graphs using LLMs to increase the accuracy and performance of generated answers
Programming Foundation Models with DSPy - Meetup SlidesZilliz
Prompting language models is hard, while programming language models is easy. In this talk, I will discuss the state-of-the-art framework DSPy for programming foundation models with its powerful optimizers and runtime constraint system.
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc
How does your privacy program stack up against your peers? What challenges are privacy teams tackling and prioritizing in 2024?
In the fifth annual Global Privacy Benchmarks Survey, we asked over 1,800 global privacy professionals and business executives to share their perspectives on the current state of privacy inside and outside of their organizations. This year’s report focused on emerging areas of importance for privacy and compliance professionals, including considerations and implications of Artificial Intelligence (AI) technologies, building brand trust, and different approaches for achieving higher privacy competence scores.
See how organizational priorities and strategic approaches to data security and privacy are evolving around the globe.
This webinar will review:
- The top 10 privacy insights from the fifth annual Global Privacy Benchmarks Survey
- The top challenges for privacy leaders, practitioners, and organizations in 2024
- Key themes to consider in developing and maintaining your privacy program
Building Production Ready Search Pipelines with Spark and MilvusZilliz
Spark is the widely used ETL tool for processing, indexing and ingesting data to serving stack for search. Milvus is the production-ready open-source vector database. In this talk we will show how to use Spark to process unstructured data to extract vector representations, and push the vectors to Milvus vector database for search serving.
Goodbye Windows 11: Make Way for Nitrux Linux 3.5.0!SOFTTECHHUB
As the digital landscape continually evolves, operating systems play a critical role in shaping user experiences and productivity. The launch of Nitrux Linux 3.5.0 marks a significant milestone, offering a robust alternative to traditional systems such as Windows 11. This article delves into the essence of Nitrux Linux 3.5.0, exploring its unique features, advantages, and how it stands as a compelling choice for both casual users and tech enthusiasts.
Dr. Sean Tan, Head of Data Science, Changi Airport Group
Discover how Changi Airport Group (CAG) leverages graph technologies and generative AI to revolutionize their search capabilities. This session delves into the unique search needs of CAG’s diverse passengers and customers, showcasing how graph data structures enhance the accuracy and relevance of AI-generated search results, mitigating the risk of “hallucinations” and improving the overall customer journey.
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024Neo4j
Neha Bajwa, Vice President of Product Marketing, Neo4j
Join us as we explore breakthrough innovations enabled by interconnected data and AI. Discover firsthand how organizations use relationships in data to uncover contextual insights and solve our most pressing challenges – from optimizing supply chains, detecting fraud, and improving customer experiences to accelerating drug discoveries.
Infrastructure Challenges in Scaling RAG with Custom AI modelsZilliz
Building Retrieval-Augmented Generation (RAG) systems with open-source and custom AI models is a complex task. This talk explores the challenges in productionizing RAG systems, including retrieval performance, response synthesis, and evaluation. We’ll discuss how to leverage open-source models like text embeddings, language models, and custom fine-tuned models to enhance RAG performance. Additionally, we’ll cover how BentoML can help orchestrate and scale these AI components efficiently, ensuring seamless deployment and management of RAG systems in the cloud.
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfMalak Abu Hammad
Discover how MongoDB Atlas and vector search technology can revolutionize your application's search capabilities. This comprehensive presentation covers:
* What is Vector Search?
* Importance and benefits of vector search
* Practical use cases across various industries
* Step-by-step implementation guide
* Live demos with code snippets
* Enhancing LLM capabilities with vector search
* Best practices and optimization strategies
Perfect for developers, AI enthusiasts, and tech leaders. Learn how to leverage MongoDB Atlas to deliver highly relevant, context-aware search results, transforming your data retrieval process. Stay ahead in tech innovation and maximize the potential of your applications.
#MongoDB #VectorSearch #AI #SemanticSearch #TechInnovation #DataScience #LLM #MachineLearning #SearchTechnology
Driving Business Innovation: Latest Generative AI Advancements & Success StorySafe Software
Are you ready to revolutionize how you handle data? Join us for a webinar where we’ll bring you up to speed with the latest advancements in Generative AI technology and discover how leveraging FME with tools from giants like Google Gemini, Amazon, and Microsoft OpenAI can supercharge your workflow efficiency.
During the hour, we’ll take you through:
Guest Speaker Segment with Hannah Barrington: Dive into the world of dynamic real estate marketing with Hannah, the Marketing Manager at Workspace Group. Hear firsthand how their team generates engaging descriptions for thousands of office units by integrating diverse data sources—from PDF floorplans to web pages—using FME transformers, like OpenAIVisionConnector and AnthropicVisionConnector. This use case will show you how GenAI can streamline content creation for marketing across the board.
Ollama Use Case: Learn how Scenario Specialist Dmitri Bagh has utilized Ollama within FME to input data, create custom models, and enhance security protocols. This segment will include demos to illustrate the full capabilities of FME in AI-driven processes.
Custom AI Models: Discover how to leverage FME to build personalized AI models using your data. Whether it’s populating a model with local data for added security or integrating public AI tools, find out how FME facilitates a versatile and secure approach to AI.
We’ll wrap up with a live Q&A session where you can engage with our experts on your specific use cases, and learn more about optimizing your data workflows with AI.
This webinar is ideal for professionals seeking to harness the power of AI within their data management systems while ensuring high levels of customization and security. Whether you're a novice or an expert, gain actionable insights and strategies to elevate your data processes. Join us to see how FME and AI can revolutionize how you work with data!
Threats to mobile devices are more prevalent and increasing in scope and complexity. Users of mobile devices desire to take full advantage of the features
available on those devices, but many of the features provide convenience and capability but sacrifice security. This best practices guide outlines steps the users can take to better protect personal devices and information.
Best 20 SEO Techniques To Improve Website Visibility In SERPPixlogix Infotech
Boost your website's visibility with proven SEO techniques! Our latest blog dives into essential strategies to enhance your online presence, increase traffic, and rank higher on search engines. From keyword optimization to quality content creation, learn how to make your site stand out in the crowded digital landscape. Discover actionable tips and expert insights to elevate your SEO game.
Best 20 SEO Techniques To Improve Website Visibility In SERP
A H YBRID C RITICAL P ATH M ETHODOLOGY – ABCP (A S B UILT C RITICAL P ATH ); ITS I MPLEMENTATION AND A NALYSIS WITH ACO FOR M EDICAL I MAGE E DGE D ETECTION
1. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
27
A HYBRID CRITICAL PATH METHODOLOGY –
ABCP
(AS BUILT CRITICAL PATH); ITS IMPLEMENTATION
AND ANALYSIS WITH ACO FOR MEDICAL IMAGE
EDGE DETECTION
Chetan S1
, H.S Sheshadri2
, V. Lokesha3
1
Research Scholar, Jain University, Assistant Professor, Department of Electronics and
Communication Engineering, Dr. Ambedkar Institute of Technology, INDIA
2
Professor & Dean (Research), Department of Electronics and Communication
Engineering, PES College of Engineering, INDIA
3
Associate Professor, Department of Mathematics, Vijayanagara Sri Krishnadevaraya
University, INDIA
ABSTRACT
The edge detection in an image has become an imminent process, with the edge of an image containing the
important information related to a particular image such as the pixel intensity value, minimal path
deciding factors, etc. This requires a specific methodology to guide in the detection of the edges, assign a
Critical Path with a minimal path set and their respective energy partitions. The basis for this approach is
the Optimized Ant Colony Algorithm [2], guiding through the various optimized structure in the edge
detection of an image. Here we have considered the scenario with respect to a Medical Image, as the
information contained in the obtained medical image is of high value and requires a redundant loss in
information pertaining to the medical image obtained through various modalities. A proper plan with a
minimal set as Critical Path, analysis with respect to the Power partitions or the Energy partitions with the
minimal set, computation of the total time taken by the algorithm to detect an edge and retrieve the data
with respect to the edge of a medical image, cumulatively considering the cliques, trade-offs in the intensity
and the number of iterations required to detect an edge in an image, with or without the presence of
suitable noise factors in the image are the necessary aspects being addressed in this paper. This paper
includes an efficient hybrid approach to address the edge detection within an image and the consideration
of various other factors, including the Shortest path out of the all the paths being produced during the
traversing of the ants within a medical image, evaluation of the time duration empirically produced by the
ants in traversing the entire image. We also construct a hybrid mechanism called ABCP (As Built Critical
Path) factor to show the deviation produced by the algorithm in covering the entire medical image, for the
metrics such as the shortest paths, computation time stamps obtained eventually and the planned
schedules.
This paper addresses the meta-heuristic process of ant colony optimization which is self-adaptive and adds
onto the parallelism with the addressing of the hard problem offering many practical ways of subduing the
effect of Critical analysis aspects as such.
KEYWORDS
Critical Path, ABCP (As Built critical Path), Energy and Power Partitions, Edge detection, ACO (Ant
Colony Optimization)
2. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
28
1. INTRODUCTION
The various image processing techniques such as Image Segmentation, Image Enhancement and
Restoration involves many images as inputs to the algorithmic machine and outputs a processed
image or a set of parameters or characteristics pertaining to the image. The information contained
within a medical image is of great importance and any compromise in the same is non-tolerant. A
very low level processing of an image is the Edge Detection of an image. These Edges contain
important information and the data redundancy is expected to be low in this regard. The Edges
within an image shows sudden variations and thus are required to be synthesized for the data
integrity. The extraction of such information is necessary and a requirement for higher extraction
efficiency order is required with higher quality values. Such a varsity of image segmentation is
required in Medical Image segmentation and has got great importance value, being a key part in
the medical applications and development of clinical medicines. There appears to difficulties in
the quantitative analysis, image diagnosis without proper image segmentation or degradation in
the edge detection of the medical image, as this requires proper ROI (Region-Of-Interest)
highlight and a proper segmentation methodology for the detection of the edge in a medical
image. These methodologies wavier as the combinatorial logics with the optimization required at
early stages. Such combinatorial logic synthesis requires algorithms that ease the image
segmentation reducing the complexities, such as intrinsic noise, lower resolution and contrast.
A well established history of such methodologies that provide a source of potentiality in adhering
and resolving the medical image edge detection algorithms have been provided in Ant Colony
Optimization (ACO)[3], Modified Ant Colony Algorithm(MACA)[4],etc. An algorithm inspired
by the natural behavior of the population- based, with pheromone deposition phenomenon, ants
and bees, which deposit pheromone in their path of traversal for their followers to have a
favorable path. These algorithms are inspired by the real ant colonies. These natural habitants try
to find the shortest path between their source and destinations. These paths are rendered by the
pheromone deposition made by the former ants in the path, while the latter choose the shortest
path with a strong pheromone concentration.
In this paper, we have used the same methodology followed by the ants in traversing from source
to destination, and back to their nests all along, based on the pheromone deposition
concentrations, as described in the Ant Colony Optimization algorithm (ACO)[3], with the
shortest path criteria as one of the Critical Path Methodologies metric, along with various factors
such as, computation time, cliques, Energy Partitions and Power factors in describing our hybrid
algorithm. We also have proposed an algorithm that clearly specifies the deviations from the
planned schedules with that of the obtained from the previous works. We also propose a pre-
defined shortest path, ABCP (As Built Critical Path), obtained from the algorithmic schedules
that utilizes the best possible computation time, shortest path/best possible path, better energy
definition & partition, evaporation rate of the pheromone deposition and provides with the details
of the edge of the medical image.
2. IMAGE EDGE DETECTION
A boundary or a contour at which there is a significant change in the physical factors of a medical
image such as normality of the surface, depth of the image, surface color & reflectance,
illumination or the visible surface distances. The changes can also be manifested in the metrics
such as texture, gradient, color, or the intensity values of all the pixels in an image. During
underlying major task of object detection in a medical image, requiring precision segmentation,
3. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
29
with respect to various objects being detected in the image is very much essential. Similarly
during the application development for the production of a low bit rate image requiring the
coding of the edges within an image, with respect to the intensity values in an image, making it a
highly intelligible concept for the edge detection. Definition and the identification of the
boundaries or the contours in a medical image representing significant image details are required
for the edge detection. This substantially defines that the edge of an image is highly constrained
with the application requiring the task of edge detection. These edges were earlier termed as
edgels, the short linear edge segments, which are collectively called as the edges, with the
detection of the same. One such factor for the image edge is the image gradient, with the
derivative having a maximum magnitude, or the 2nd
order derivative bearing the value zero, The
image gradient is monitored by the equation;
The rapid change in the intensity factor points out to the gradient points, with the direction of the
gradient given by;
The shapes of the objects convey high amount of semantic information about the image. The
gradient variation as given and monitored by the above equations is one of the methods of image
edge detection, where in the image considered is represented with an analog factor f(x),
representing a typical 1-dimensional edge within an image. The methodology follows an episodic
procedure in the detection of such edges where there happens to be a zero-crossing in the image
considered. The variation in the intensity of the pixels contained within an image is considered as
an essential factor in one of the methods for the detection of the edges in an image, known as the
Laplacian method. Here the general 2-dimensional localization factor f(x,y) with the intensity
variation is considered suitably for the image edge detection. The formula for the Laplacian of a
function f(x,y) is given by;
The main focus shift with the image edge detection is to convert a 2-dimensional image into a set
of curves, with the extraction of the salient features associated with the scene, proving more
efficient and compact than the pixels.
3. RELATED WORK
The process of processing an image pixel by pixel and the application of these modifications in
the pixel neighbourhood, with the noise removal, enhancing the image contours and the edges,
using a MATLAB interactive, high level graphical user interface eliminating the high level
language for coding defining an architecture of filtering images for edge detection with the help
of Video and Image Processing block-set was defined by Amandeep Kamboj et al.(2012). Edge
Detection in a Medical Image remains to be a key in the medical image research and other
diagnosis applications. The contours in these medical images are obtained through the work
established using the standard GVF Snake model, for the image segmentation. Convergence
4. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
30
speed to an optimized solution, processing the concavity, and the precision with which the
segmentation of the image is being done are some of the metrics that needs to be taken care of
with the adopted GVF Snake algorithm as it deviates from these local optimization factors. With
the crowded degree function adherent to the Ant Colony algorithm was developed by Xiangpu
Gong et al. (2008), which enhanced the overall traversability and the capacity to converge at an
optimal solution. The natural behaviour of the ant species that deposit the pheromone in the path
traversed by thou for foraging with the representation of the pheromone matrix with respect to
each pixel position of the image under consideration, based upon the finite amount of ants
allowed to traverse on an image, whose movements are defined by the variations in the intensity
values of the presenting pixels of the image were provided by Shengli Xie et al.(2008) to
demonstrate the superior behaviour of the proposed algorithm. Alberto Coloroni et al. (2008)
were the first to come up with the algorithm based on the behaviour of the ants and their
simulation known as the Ant Colony System (ACS)[5], for the well-known Travelling
Salesperson Problem (TSP), a combinatorial optimization problem.
In this paper we discuss the methodology revolving around the actual proposed work, wherein a
medical image is subjected to noise removal with the application of various filters, and
approximate it to a set of continuous functions from which the image samples were taken,
allowing for the computation of the edge to a sub-pixel precision. Then we apply the Optimized
Ant Colony algorithm to model the image neighbourhood as a bi-cubic polynomial followed by
equation:
The image thus obtained is subject to Critical Path operators for the computation of shortest path
for within the images obtained from the ACO algorithm vector machine, along with the
deviations pertaining to the computation time for the detection of the edge within the image. Our
hybrid algorithm computes the shortest path with the application of the approximation vectors, at
suitable time intervals with the polynomials and suitably enhances the computation time in
detecting the edge of the image.
4. PROPOSED METHODOLOGY
In this paper we have proposed an efficient approach for the detection of the edge in a medical
image. The medical image considered in our scenario is necessary to be a square image with a
resolution factor of either 128X128, or 256X256, or 512X512. The medical image considered is
normalized and the noise is filtered using a suitable filter such as Gaussian, Laplacian, Fourier or
Sine filters as given by the equations in the ACO algorithm as:
Where in the above equation adjusts the clique shape function in the above equations. The
above equations mentioned determines the function that monitors the pixel of clique’s c given by
the equation;
5. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
31
These equations are proportionally guided in the ACO algorithm which considers the meta-
heuristic features of the foraging behaviour of the ants. The same has been modified with the
application of the structured format of initiating the Asynchronous movement of Real Ants and
the synchronous movement of the Virtual Ants in providing some sort of implicit solutions in
finding the edge of an image. The below given flow depicts the actual process flow involved in
the proposed methodology which is the basis for our work:
Figure 1. Proposed Methodology Workflow
The proposed algorithm takes the input in the form of a .bmp (Bitmap Image format), grayscale
image, into the vector machine. Later the image is approximated to the sub-pixel values using the
image approximation methodology. Thus approximated image is defined and synthesized by the
algorithmic vector machine into an acyclic graph, represented with series of arcs(activities)
defined by the movement of the ants and the events during the pheromone deposition, definition
of the contours and the gradient or the intensity variations obtained from approximating the image
with the application of the Hybrid ACO algorithm, which considers a probability to define the
correct(shortest) path and the elimination of the spurious edge detection within a medical image.
The algorithm also takes into consideration the Daemonic Actions for the foraging behaviour of
the ants and their traversal in an image. Then the structure of the Critical Path is applied to find
the shortest path between the source and destination as specified by the algorithm. We also
calculate the computation time and verify the deviation magnitude with the manually calculated
values. This forms the basis for the proposal of the ABCP (As Built critical Path) and an active
involvement of the active metrics in the calculation the deviation produced in the real terms, as
metrics.
5. IMAGE APPROXIMATION
The image approximation procedure with reference to the scenario presented in our proposed
work accepts the input as an array of sample functions in the form of an image. This is helpful in
6. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
32
the estimation of the continuous functions which represent the image properties, to sub-pixel
precisions followed by the equation considered as;
z = f (x,y)
This function z, is considered to be a continuous image intensity function. During the
reconstruction of the image from all these sub-pixel values, we consider the piecewise analytical
functions, similar to facets. Here we try finding the intensity values of each pixel from the local
neighbourhood pixels. This continuous function is approximated locally at every pixel in the
image.
Figure 2. Co-ordinate System for the approximation of the facet value in the neighbourhood
The edge points that occur at a relative maximum point from the pixel of consideration, in the
first directional derivative of the continuous function are approximated with the image intensity
in the neighbourhood of a pixel. These first order derivative results in the zero crossing for the
second order derivative whose equations are given as:
And the second order derivative in the direction given by,
Where the intensity of the local image was approximated with by the cubic polynomial,
With the angle , the angle of the approximation plane resulting in ,
7. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
33
At some point considering the direction and the line of its intersection being made in the same
direction, and , the continuous function follows the equation,
There exists an edge at the point ( , in the image for some , where is the length of the
side of a pixel. For our case study we have considered a medical image as given in Figure 3,
which is an X-ray of human indicating the fracture. The original considered for this scenario is of
the resolution 128X128, and is grayscale, bitmap image file.
Figure 3. Original Medical Image; X-ray image of the Nose Fracture
The original image is then subjected to the approximation and the approximated values are
plotted on a graph for the analysis. The Figure 4 depicts the plot for the sum of pixel values with
respect to the radius of the curve in the considered image.
For the image considered in the above scenario, the bi-cubic polynomial varies in accordance
with the specific values of the constants as follows:
These constants occur from the pixel values with the neighbourhood pixels, with pixel selection
can be made either in the 8 bit clique mode or the 4 bit clique mode, from which these constant
matrices are constructed.
We can also observe from the below plots that the maximum value of the pixel value is achieved
for a sum of the pixel value of 0.8 in Figure 4 while that in Figure 5 it is 0.4. The approximated
value is inversely proportional to the pixel value, varying with the radius of the image, in terms of
pixels.
8. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
34
Figure 4. Image Approximation Plot with
Figure 5. Image Approximation Plot with
6. ALGORITHM
The hybrid ACO algorithm proposed in this paper depends on the basic structure defined in the
ACO meta-heuristic procedure, which includes the major 3 steps as a part of their schedule
activities:
i. Construction of ant solution
ii. Updating of the pheromone depositions in the form of a matrix
iii. Daemonic Actions/activities
The algorithmic flow clearly specifies the categories and the steps involved in the execution
procedure of the algorithm vector machine, which output specific data values at proper intervals
of time, substantiating the proof for the algorithm implementation,
9. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
35
Figure 6. Algorithmic Flow for the modified ACO Approach
The same is referred in our algorithm vector machine with an addition done in the inclusion of the
Virtual ant concept which works around with the pre-defined set of Critical Path parameters
defined in the algorithm. The major deviations, which occur in the exclusive ACO algorithm that
lead to the definition of the hybrid algorithm, are:
10. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
36
i. Detection of erroneous edges within an image
ii. Delay in the execution and the detection of the edges
iii. Complex path traversal by the ant initialized to traverse within an image.
iv. Proper clique/curve definition
v.
The general steps in this process can be summarized as follows:
i. Parameter setting and its initialization wit reference to both the Real Ant and the Virtual
Ant quality
ii. The initialized metrics are to be stepped over for a cycle of L+n steps, with an
incremental process along with their value updation provided in the form of a matrix
iii. All the Real and the Virtual Ants are allowed to traverse on the considered medical
image, with a suitable concentration of pheromone deposition being done in the
process, to highlight the path from the initialized vector point to the destined point.
iv. Update the pheromone matrix so obtained with the localization machine detecting the
edge in the image.
The ant traversed images after the algorithmic vector machine runs for the required number of
iterations, and a specific approximation values, is as shown in the Figure 7 and Figure 8.
Figure 7 Real and Virtual Ants Traversed Image
with
Figure 8 Real and Virtual Ants Traversed Image
with
The edge detected image is then converted to a matrix format containing the information about
the edges detected by the hybrid algorithm. Here we have considered the fact that, the image be in
a compact connected domain in the plane and x,y , with a path from x to y designated as an
injective function;
, such that
and
11. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
37
12. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
38
Figure 8. Flow representing the detection of Edge Weight index used in the determination of the shortest
path parameter for Critical Path
With this concept of the relational minimal path and the surface of action or the energy, of a
potential function given by,
This potential function defined with respect to a source point Ω, evaluated at the source
point x as defined in,
13. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
39
Figure 9. Shortest Path plot by the algorithm
Table 1. Shortest Path as a Critical Path metric in ABCP and their deviation
Expected Value
for the Shortest
Path
Obtained Result Deviation (%)
0.4 6.1 6.3 20
0.8 7.4 6.9 50
In the above equation P depends on the position of and this value will be strictly positive.
The energy partition is done with respect to the a set of sources defined by the
function as the minimal individual energy, given as,
The source is a medical image; while the partition within this image is done based on the
neighbourhood image pixel values based on their intensity values. The power factor analysis
provides us with the magnitude of the intensity value with respect to the neighbourhood pixels in
the image. As we can in Figure 7 & 8 that the concentration of the pheromone deposition is more
at certain regions, leading to the segregation of large group of ants around that region, resembling
the sharp change in the intensity providing an edge at that particular point. The intensity
variations are provided in the energy partitions with their magnitudes in terms of the pheromone
deposition around the edge in the image.
Table 2 Power Factor Analysis as a Critical Path metric in ABCP and their deviation
Expected Energy
Value
Obtained Result Deviation (%)
0.4 81 93 12
0.8 77 85 8
14. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
40
Figure 10. Power Factor Analysis
7. CONCLUSIONS
The information contained in the edges in an image and detection of these edges are highly
required for various image processing, also in various critical applications such as medical
diagnosis and clinical research. With this importance value, substantial algorithms, structured
operators, etc. have been developed and a lot of research is being done for decades. The algorithm
developed in this work is also a meta-heuristic methodology which addresses the critical metrics
and provides a description and describes their deviation from the pre-defined As Built Critical
Path metrics. This also addresses the most in-evitable NP Hard problems. This paper proposes
usage of traditional Ant Colony Optimized edge detectors with Daemonic actions including both
the Real as well as Virtual Ants, pheromone depositions and distribution matrixes that validates
the shortest path, edge weights, edge weight indices, energy partitions, and power analysis. The
adaptivity provided by this algorithm is that it is trained to accept a variety of inputs dependant on
application. Image size constraint and the grayscale factors along with the reduction is
introduced as a really effective method to noise reduction compared to previous method of image
smoothness. Death escape opportunity is provided randomly for some ants to increase the edge
length. In pheromone update process, a few parameters such as diameter and area of travelled
path are converted into rules and rules are normalized to compute the final update value through
averaging. Results are obtained by modifying certain aspects related with the normalized ACO
algorithm and the Critical Path metrics on the same image and also they are more reliable.
ACKNOWLEDGEMENTS
The authors would like to thank the Management, Panchajanya Vidya Peetha Welfare Trust
(Regd), Dr. C. Nanjundaswamy our beloved Principal, Dr. G V Jayaramaiah our beloved HOD,
Dr. R.Murali, Dr M V Mandi and Dr S Ramesh of Dr. Ambedkar Institute of Technology,
Bengaluru for their assistance, suggestions, insight and valuable discussion over the course of this
research work. The authors also thankful to the Jain University, Bengaluru for providing an
opportunity to pursue this research work.
15. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
41
REFERENCES
[1] Chetan.S, H.Sheshadri, V.Lokesha, “A Descriptive Study on Improvisation of Parallel Ant Colony
Optimization with Implementation of CPM for Genetic Algorithm with Evolution and Fast Tracking
”,Proceedings of the Second International Conference on Emerging Research in Computing,
Information, Communication and Applications, ERCICA 2014, ISBN: 9789351072621.
[2] Raman Maini, Dr. Himanshu Aggarwal, “Study and Comparison of Various Image Edge Detection
Techniques”, International Journal of Image Processing (IJIP), Vol.3, Issue 1, pp.1-12.
[3] Jing Tian, Weiyu Yu, and Shengli Xie, “An Ant Colony Optimization Algorithm for Image Edge
Detection”, IEEE Conference on Evolutionary Computation (CEC), 2008, pp.751-756.
[4] Lei Li, Yuemei Ren, and Xiangpu Gong, “Medical Image Segmentation Based on Modified Ant
Colony Algorithm with GVF Snake Model” International Seminar on Future Biomedical Information
Engineering, 2008, pp. 11-14, IEEE
[5] D.-S. Lu and C.-C. Chen, “Edge detection improvement by ant colony optimization,” Pattern
Recognition Letters, vol. 29, pp. 416–425, Mar.2008.
[6] S. Ouadfel and M. Batouche, “Ant colony system with local search for Markov random field image
segmentation,” in Proc. IEEE Int. Conf. on Image Processing, Barcelona, Spain, Sep. 2003, pp. 133–
136.
[7] D. Martens, M. D. Backer, R. Haesen, J. Vanthienen, M. Snoeck, and B. Baesens, “Classification
with ant colony optimization,” IEEE Trans. on Evolutionary Computation, vol. 11, pp. 651–665, Oct.
2007.
[8] R. Siedlova and J. Pozivil, “Implementation of Ant Colony Algorithms in Matlab”, Department of
Computing and Control Engineering, Czech Republic.
[9] Bonabeau, E., Dorigo, M., & Theraulaz, G. (1999). Swarm Intelligence: From Natural to Artificial
Systems. Oxford University Press.
[10] M. Heath, S. Sarkar, T. Sanocki, and K.W. Bowyer. “A Robust Visual Method for Assessing the
Relative. Performance of Edge Detection Algorithms”. IEEE Trans. Pattern Analysis and Machine
Intelligence, vol. 19, no. 12, pp. 1338-1359, Dec. 1997
[11] E. Argyle. “Techniques for edge detection,” Proc. IEEE, vol. 59, pp. 285-286, 1971
[12] M. Dorigo and L. M. Gambardella, “Ant colony system: A cooperative learning approach to the
travelling salesman problem,” IEEE Trans. On Evolutionary Computation, Vol. 1, pp. 53–66, Apr.
1997.
[13] Alirezae Rezaee, “Extracting Edge of Images with Ant Colony”, Journal of Electrical Engineering,
Vol. 59, No. 1, 2008, pp. 57-59.
[14] Verma, O.P., Hanmandlu, M., Sultania, A.K., 2010. A Novel Fuzzy Ant System for Edge Detection.
2010 IEEE/ACIS 9th International Conference on Computer and Information Science 228–233.
[15] Pablo Andrez Arbeleaz and Laurent D Cohen, “Path Variation and Image Segmentation”, France.
[16] Rupert Paget and Dennis Longstaff, “Extracting the Cliques from a Neighbourhood System”, IEEE
Proceedings, Vision Image and Signal Processing, Vol. 144, No. 3, 1997.
[17] Berthold K P Horn, “Understanding Image Intensities”, Artificail Intelligence Laboratory,
Massachusetts Institute of Technology, Cambridge, USA.
[18] Yuanjing Feng and Zhejin Wang, “Ant Colony Optimization for Image Segmentation
[19] Tao, W.B.; Jin, H. & Liu, L.M. (2007). Object segmentation using ant colony optimization algorithm
and fuzzy entropy. Pattern Recognition Letters 28 788-796.
[20] Hegarat-Mascle, L.; Kallel, S. & Velizy, A. etc. (2007). Ant Colony Optimization for image
regularization based on a nonstationary markov modeling, IEEE Transactions on Image Processing,
16(3): 865-878.
[21] Hsien-Hsun, W.; Jyh-Charn, L. & Chui, C. (2000). A wavelet-frame based image force model for
active contouring algorithms, IEEE T. Image Process. 9, 1983–1988.
[22] Mohammad Towhidul Islam, Parimala Thulasiraman_ and Ruppa K. Thulasiram, “A Parallel Ant
Colony Optimization Algorithm for All-Pair Routing in MANETs”, IEEE Proceedings, 2003.
[23] M. Randall. A Parallel Implementation of Ant Colony Optimization. Parallel and Distributed
Computing, 62:1421–1432, 2002.
16. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE) Vol.2, No.1/2, April 2015
42
AUTHORS
Chetan. S is a PhD Scholar majoring in Electronics Engineering at the Jain University,
Bengaluru. He received the B.E. Degree in Electronics & Communication Engineering from
Visvesvaraya Technological University in 2005 and M.Tech. Degree in VLSI Design &
Embedded System from Visvesvaraya Technological University in 2009. His current
research interests include Image Processing, medical image segmentation and analysis and
digital communication. He is a life member of ISTE, SIE, IAENG, IASCIT and has
participated in various national and international conferences and seminars in India and abroad.
Dr. H.S. Sheshadri obtained his B.E. from University of Mysore during 1979 in E & C
Engg, M.E (Applied Electronics) from Bharathiar University, Coimbatore during 1989 and
PhD from Anna University Madras during 2008.He is serving presently as a Professor and
Dean (Research) in PES College of Engineering, Mandya. His field of interest is
Medical Image processing and embedded systems. He has published 12 papers in
national journals and 21 papers in International journals. Also guiding 6 research
candidates for PhD programme under university of Mysore, Two candidates under VTU,
Belgaum. He is a life member of IE (India), IETE, ISTE, SSI, and has participated in various
national and international conferences and seminars in India and abroad.
Dr. V. Lokesha obtained his PhD from Mysore University, Mysore and is currently Special
Officer and Deputy Registrar in Vijayanagara Sri Krishnadevaraya University, Bellary. He
is presently Chairman of Department of Computer Science and Mathematics. He was
invited in Turkey, France, South Korea, and Iran for International conferences. He is a
reviewer of American Mathematical reviews, USA and several Journal of international
repute. He delivered several series of lectures under the V.T. U EDUSAT - LIVE telecast
lecture series programme. He has published more than 100 research papers in the journals of international
repute. Under his Guidance 8 PhD and 28 MPhil degrees are awarded and working as editorial member of
several international and National Journals.