IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
The Technology Research of Camera Calibration Based On LabVIEWIJRES Journal
Β
The technology of camera calibration is most important part for machine vision detection and
location, the accuracy of calibration directly determines the processing accuracy of machine vision systems. In
this paper, we use LabVIEW and MATLAB to calibrate the internal and external parameters of the camera, at
the same time, we use dot calibration board, the circle edge is detected by Canny operator, then with the method
of circle fitting based on subpixel edge extraction, the information of dots image coordinate is extracted. The
present method reduces the difficulty of camera calibration and shortens the software development cycle, the
most important is that it has a high calibration accuracy, which can meet the actual industrial detection accuracy,
the results of experimental show that the method is feasible.
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.
Image fusion using nsct denoising and target extraction for visual surveillanceeSAT Publishing House
Β
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.
Comparative Analysis of Hand Gesture Recognition TechniquesIJERA Editor
Β
During past few years, human hand gesture for interaction with computing devices has continues to be active area of research. In this paper survey of hand gesture recognition is provided. Hand Gesture Recognition is contained three stages: Pre-processing, Feature Extraction or matching and Classification or recognition. Each stage contains different methods and techniques. In this paper define small description of different methods used for hand gesture recognition in existing system with comparative analysis of all method with its benefits and drawbacks are provided.
Solving the Pose Ambiguity via a Simple Concentric Circle ConstraintDr. Amarjeet Singh
Β
Estimating the pose of objects with circle feature from images is a basic and important question in computer vision
community. This paper is focused on the ambiguity problem in pose estimation of circle feature, and a new method is proposed based
on the concentric circle constraint. The pose of a single circle feature, in general, can be determined from its projection in the image
plane with a pre-calibrated camera. However, there are generally two possible sets of pose parameters. By introducing the concentric
circle constraint, interference from the false solution can be excluded. On the basis of element at infinity in projective geometry and
the Euclidean distance invariant, cases that concentric circles are coplanar and non-coplanar are discussed respectively. Experiments
on these two cases are performed to validate the proposed method.
Expert system of single magnetic lens using JESS in Focused Ion Beamijcsa
Β
This work shows expert system of symmetrical single magnetic lens used in focused ion beam optical system. Java expert system shell(JESS) programming is proposed to build the intelligent agent "MOPTION"for getting an optimum magnetic flux density , and calculate the ion optical trajectory. The combination of such rule based engine and SIMION 8.1 has configured the reconstruction process and compiled the data retrieved by the proposed expert system agent to implement the pole-pieces reconstruction for lens design. The pole pieces reconstruction has been resulted in 3D graph , and under the infinite magnification conditions of the optical path, aberration (spherical / chromatic and total) disks diameters have been obtained and got the values (0.03,0.13 and 0.133) micron (ΞΌm) respectively.
This summarizes an article about a method for image segmentation and intensity non-uniformity correction. It proposes defining a local clustering criterion function based on intensities in a neighborhood around each point. This function evaluates how well the intensities are classified based on the image partition. An energy term is defined as the integral of this local clustering criterion over the image domain. Minimizing this energy allows simultaneous segmentation of the image into regions and estimation of a bias field to correct for intensity non-uniformities. The method is applied to MRI and other medical images to produce accurate segmentations in the presence of intensity inhomogeneities.
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
The Technology Research of Camera Calibration Based On LabVIEWIJRES Journal
Β
The technology of camera calibration is most important part for machine vision detection and
location, the accuracy of calibration directly determines the processing accuracy of machine vision systems. In
this paper, we use LabVIEW and MATLAB to calibrate the internal and external parameters of the camera, at
the same time, we use dot calibration board, the circle edge is detected by Canny operator, then with the method
of circle fitting based on subpixel edge extraction, the information of dots image coordinate is extracted. The
present method reduces the difficulty of camera calibration and shortens the software development cycle, the
most important is that it has a high calibration accuracy, which can meet the actual industrial detection accuracy,
the results of experimental show that the method is feasible.
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.
Image fusion using nsct denoising and target extraction for visual surveillanceeSAT Publishing House
Β
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.
Comparative Analysis of Hand Gesture Recognition TechniquesIJERA Editor
Β
During past few years, human hand gesture for interaction with computing devices has continues to be active area of research. In this paper survey of hand gesture recognition is provided. Hand Gesture Recognition is contained three stages: Pre-processing, Feature Extraction or matching and Classification or recognition. Each stage contains different methods and techniques. In this paper define small description of different methods used for hand gesture recognition in existing system with comparative analysis of all method with its benefits and drawbacks are provided.
Solving the Pose Ambiguity via a Simple Concentric Circle ConstraintDr. Amarjeet Singh
Β
Estimating the pose of objects with circle feature from images is a basic and important question in computer vision
community. This paper is focused on the ambiguity problem in pose estimation of circle feature, and a new method is proposed based
on the concentric circle constraint. The pose of a single circle feature, in general, can be determined from its projection in the image
plane with a pre-calibrated camera. However, there are generally two possible sets of pose parameters. By introducing the concentric
circle constraint, interference from the false solution can be excluded. On the basis of element at infinity in projective geometry and
the Euclidean distance invariant, cases that concentric circles are coplanar and non-coplanar are discussed respectively. Experiments
on these two cases are performed to validate the proposed method.
Expert system of single magnetic lens using JESS in Focused Ion Beamijcsa
Β
This work shows expert system of symmetrical single magnetic lens used in focused ion beam optical system. Java expert system shell(JESS) programming is proposed to build the intelligent agent "MOPTION"for getting an optimum magnetic flux density , and calculate the ion optical trajectory. The combination of such rule based engine and SIMION 8.1 has configured the reconstruction process and compiled the data retrieved by the proposed expert system agent to implement the pole-pieces reconstruction for lens design. The pole pieces reconstruction has been resulted in 3D graph , and under the infinite magnification conditions of the optical path, aberration (spherical / chromatic and total) disks diameters have been obtained and got the values (0.03,0.13 and 0.133) micron (ΞΌm) respectively.
This summarizes an article about a method for image segmentation and intensity non-uniformity correction. It proposes defining a local clustering criterion function based on intensities in a neighborhood around each point. This function evaluates how well the intensities are classified based on the image partition. An energy term is defined as the integral of this local clustering criterion over the image domain. Minimizing this energy allows simultaneous segmentation of the image into regions and estimation of a bias field to correct for intensity non-uniformities. The method is applied to MRI and other medical images to produce accurate segmentations in the presence of intensity inhomogeneities.
This document provides an overview of machine vision applications including content-based image retrieval and face recognition. It discusses how content-based image retrieval systems work by extracting image features, calculating distances between images, and returning similar images from a database based on a query image. Examples of content-based image retrieval systems and the features they use are described. The document also covers face detection and recognition techniques, including the use of eigenfaces which represent faces as locations in a lower-dimensional space.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
Β
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
Dynamic texture based traffic vehicle monitoring systemeSAT Journals
Β
Abstract Dynamic Textures are function of both space and time which exhibit spatio-temporal stationary property. They have spatially repetitive patterns which vary with time. In this paper, importance of phase spectrum in the signals is utilized and a novel method for vehicle monitoring is proposed with the help of Fourier analysis, synthesis and image processing. Methods like Doppler radar or GPS navigation are used commonly for tracking. The proposed image based approach has an added advantage that the clear image of the object (vehicle) can be used for future reference like proof of incidence, identification of owner and registration number. Keywords-Fourier Transform, dynamic texture, phase spectrum
Local Phase Oriented Structure Tensor To Segment Texture Images With Intensit...CSCJournals
Β
This paper proposed the active contour based texture image segmentation scheme using the linear structure tensor and tensor oriented steerable Quadrature filter. Linear Structure tensor (LST) is a popular method for the unsupervised texture image segmentation where LST contains only horizontal and vertical orientation information but lake in other orientation information and also in the image intensity information on which active contour is dependent. Therefore in this paper, LST is modified by adding intensity information from tensor oriented structure tensor to enhance the orientation information. In the proposed model, these phases oriented features are utilized as an external force in the region based active contour model (ACM) to segment the texture images having intensity inhomogeneity and noisy images. To validate the results of the proposed model, quantitative analysis is also shown in terms of accuracy using a Berkeley image database.
This paper presents an FPGA-based algorithm for moving object detection from video for traffic surveillance. The algorithm uses background subtraction, edge detection and shadow detection techniques. Background subtraction involves selective and non-selective updating to improve sensitivity. Edge detection helps find object boundaries while shadow detection removes falsely detected pixels from shadows. The algorithm is implemented using VHDL on a Spartan-6 FPGA board. Experimental results show the algorithm can accurately detect moving vehicles in different lighting conditions with low power consumption, making it suitable for traffic monitoring applications.
Object extraction using edge, motion and saliency information from videoseSAT Journals
Β
Abstract Object detection is a process of finding the instances of object of a certain class which is useful in analysis of video or image. There are number of algorithms have been developed so far for object detection. Object detection has got significant role in variety of areas of computer vision like video surveillance, image retrieval`. In this paper presented an efficient algorithm for moving object extraction using edge, motion and saliency information from videos. Out methodology includes 4 stages: Frame generation, Pre-processing, Foreground generation and integration of cues. Foreground generation includes edge detection using sobel edge detection algorithm, motion detection using pixel-based absolute difference algorithm and motion saliency detection. Conditional Random Field (CRF) is applied for integration of cues and thus we get better spatial information of segmented object. Keywords: Object detection, Saliency information, Sobel edge detection, CRF.
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.
Model User Calibration Free Remote Gaze Estimation SystemKalle
Β
Gaze estimation systems use calibration procedures that require active subject participation to estimate the point-of-gaze accurately. In these procedures, subjects are required to fixate on a specific point or points in space at specific time instances. This
paper describes a gaze estimation system that does not use calibration procedures that require active user participation. The
system estimates the optical axes of both eyes using images from a stereo pair of video cameras without a personal calibration procedure. To estimate the point-of-gaze, which lies along the visual axis, the angles between the optical and visual axes are estimated by a novel automatic procedure that minimizes the distance between the intersections of the visual axes of the left and right eyes with the surface of a display while subjects look naturally at the display (e.g., watching a video clip). Experiments
with four subjects demonstrate that the RMS error of this point-of-gaze estimation system is 1.3ΒΊ.
This document provides an overview of image processing techniques for traffic applications. It discusses automatic lane finding using color-based and texture-based segmentation as well as feature-driven approaches. Object detection methods like thresholding, edge detection using Canny operator, and background differencing are also covered. Additionally, the document proposes an emergency vehicle detection system using red beacon detection and frequency analysis to override normal traffic light patterns when an emergency vehicle is detected.
Segmentation and Classification of MRI Brain TumorIRJET Journal
Β
This document presents a study comparing two techniques for detecting brain tumors in MRI images: level set segmentation and K-means segmentation. Features are extracted from the segmented tumors using discrete wavelet transform and gray level co-occurrence matrix. The features are then classified as benign or malignant using a support vector machine. The level set method and K-means method are evaluated based on accuracy, sensitivity, and specificity on a dataset of 41 MRI brain images. The level set method achieved slightly higher accuracy of 94.12% compared to the K-means method.
Palmprint verification using lagrangian decomposition and invariant interestDakshina Kisku
Β
This document summarizes a research paper on palmprint verification using Lagrangian decomposition and invariant interest points. The paper proposes a system that extracts the region of interest from palm images, uses SIFT to extract invariant features, and performs matching using a Lagrangian graph technique. It tests the system on two databases, achieving recognition rates of 97.1% and 95.8% with low false acceptance and rejection rates. The paper concludes the proposed system is effective and robust for palmprint authentication.
Wavelet Transform based Medical Image Fusion With different fusion methodsIJERA Editor
Β
This paper proposes wavelet transform based image fusion algorithm, after studying the principles and characteristics of the discrete wavelet transform. Medical image fusion used to derive useful information from multimodality medical images. The idea is to improve the image content by fusing images like computer tomography (CT) and magnetic resonance imaging (MRI) images, so as to provide more information to the doctor and clinical treatment planning system. This paper based on the wavelet transformation to fused the medical images. The wavelet based fusion algorithms used on medical images CT and MRI, This involve the fusion with MIN , MAX, MEAN method. Also the result is obtained. With more available multimodality medical images in clinical applications, the idea of combining images from different modalities become very important and medical image fusion has emerged as a new promising research field
Obstacle detection for autonomous systems using stereoscopic images and bacte...IJECEIAES
Β
This paper presents a low cost strategy for real-time estimation of the position of ob- stacles in an unknown environment for autonomous robots. The strategy was intended for use in autonomous service robots, which navigate in unknown and dynamic indoor environments. In addition to human interaction, these environments are characterized by a design created for the human being, which is why our developments seek morphological and functional similarity equivalent to the human model. We use a pair of cameras on our robot to achieve a stereoscopic vision of the environment, and we analyze this information to determine the distance to obstacles using an algorithm that mimics bacterial behavior. The algorithm was evaluated on our robotic platform demonstrating high performance in the location of obstacles and real-time operation.
A NOVEL IMAGE SEGMENTATION ENHANCEMENT TECHNIQUE BASED ON ACTIVE CONTOUR AND...acijjournal
Β
This document summarizes a novel image segmentation technique based on active contours and topological alignments. The technique aims to improve boundary detection by incorporating the advantages of both active contours and topological alignments. It presents a two-step algorithm: 1) Initial segmentation is performed using topological alignments to improve cell tracking results. 2) The output is transformed into the input for an active contour model, which evolves toward cell boundaries for analysis of cell mobility. Tests on 70 grayscale cell images showed the technique achieved better segmentation and boundary detection compared to active contours alone, including for low contrast images and cases of under/over-segmentation.
Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...ijsrd.com
Β
The gradual visual field loss and there is a characteristic type of damage to the retinal nerve fiber layer associated with the progression of the disease glaucoma. Texture features within images are actively pursued for accurate and efficient glaucoma classification. Energy distribution over wavelet subband is applied to find these important texture features. In this paper, we investigate the discriminatory potential of wavelet features obtained from the Daubechies (db3), symlets (sym3), and biorthogonal (bio3.3, bio3.5, and bio3.7) wavelet filters. We propose a novel technique to extract energy signatures obtained using 2-D discrete wavelet transform, and subject these signatures to different feature ranking and feature selection strategies. Here my project aims at the use of Probabilistic Neural Network (PNN), Fuzzy C-means (FCM) and K-means helps for the detection of glaucoma disease. For this, fuzzy c-means clustering algorithm and k-means algorithm is used. Fuzzy c-means results faster and reliably good clustering when compare to k-means.
Hierarchical Vertebral Body Segmentation Using Graph Cuts and Statistical Sha...IJTET Journal
Β
Abstractβ Bone Mineral Density (BMD) estimations and fracture investigation of the spine bones are retrained to the vertebral bodies (VBs).A contemporary shape and appearance based method is proposed to segment VBs in clinical Computed Tomography (CT) images without any user arbitration. The proposed approach depends on both image appearance and shape information. Shape knowledge is aggregated from a set of training shapes. Then shape variations are estimated using statistical shape model which approximates the shape variations of the vertebral bodies and its background in the variability region. To segment a VB, the graph cut method used to detect the VB region automatically. Detected contours are aligned and mean shape model is created. The spatial interaction between the neighboring pixels is identified. The statistical shape model is used to produce the deformable shape model and all instances of the shape lies with the current estimate of the mean shape.
Gait Based Person Recognition Using Partial Least Squares Selection Scheme ijcisjournal
Β
The document summarizes a research paper on gait-based person recognition using partial least squares selection. It presents an Arbitrary View Transformation Model (AVTM) that uses gait energy images and partial least squares (PLS) feature selection to improve gait recognition accuracy under varying viewing angles, clothing, and other conditions. The proposed AVTM PLS method is evaluated on the CASIA gait database and shown to achieve higher recognition rates compared to other existing methods, especially when there are changes in viewing angle, clothing, or whether the person is carrying something. Tables of results demonstrate the proposed method outperforms alternatives across different test conditions and ranges of gallery and probe viewing angles.
This document presents a method for tracking moving objects in video sequences using affine flow parameters combined with illumination insensitive template matching. The method extracts affine flow parameters from frames to model local object motion using affine transformations. It then applies template matching with illumination compensation to track objects across frames while being robust to illumination changes. The method is evaluated on various indoor and outdoor database videos and is shown to effectively track objects without false detections, handling issues like illumination variations, camera motion and dynamic backgrounds better than other methods.
This document summarizes research on analyzing the steady-state performance of a self-excited induction generator using three optimization techniques: genetic algorithms, pattern search, and quasi-Newton methods. It provides background on induction generators and how they can operate as self-excited generators by connecting capacitors to the stator terminals. The document presents the standard steady-state equivalent circuit model and derives nonlinear equations that are solved using the three optimization techniques to determine unknown parameters. The performance of the self-excited induction generator is then evaluated based on the determined parameters.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This document discusses sensorless vector control of induction motors. It presents the dynamic modeling of induction motors using a reference frame transformation. It then describes the principles of vector control using an inverse transformation to control stator currents. A model reference adaptive system is proposed for sensorless speed estimation, where an adaptive model estimates the rotor speed by comparing its output to a reference model. Simulation results show the sensorless control approach can accurately estimate speed with good tracking performance.
This document summarizes a paper that proposes a new approach to feature-based 3D modeling of turned components in AutoCAD. The approach develops algorithms to model features like cylinders, tapers, holes, and grooves based on user-entered dimensions. It then stores feature information and uses it to assess similarity between components. The modeling system supports both feature-based design and recognition without needing separate feature extraction. The paper presents the algorithms for modeling different features and assessing similarity based on common features like cylinders, holes, or grooves.
This document provides an overview of machine vision applications including content-based image retrieval and face recognition. It discusses how content-based image retrieval systems work by extracting image features, calculating distances between images, and returning similar images from a database based on a query image. Examples of content-based image retrieval systems and the features they use are described. The document also covers face detection and recognition techniques, including the use of eigenfaces which represent faces as locations in a lower-dimensional space.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
Β
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
Dynamic texture based traffic vehicle monitoring systemeSAT Journals
Β
Abstract Dynamic Textures are function of both space and time which exhibit spatio-temporal stationary property. They have spatially repetitive patterns which vary with time. In this paper, importance of phase spectrum in the signals is utilized and a novel method for vehicle monitoring is proposed with the help of Fourier analysis, synthesis and image processing. Methods like Doppler radar or GPS navigation are used commonly for tracking. The proposed image based approach has an added advantage that the clear image of the object (vehicle) can be used for future reference like proof of incidence, identification of owner and registration number. Keywords-Fourier Transform, dynamic texture, phase spectrum
Local Phase Oriented Structure Tensor To Segment Texture Images With Intensit...CSCJournals
Β
This paper proposed the active contour based texture image segmentation scheme using the linear structure tensor and tensor oriented steerable Quadrature filter. Linear Structure tensor (LST) is a popular method for the unsupervised texture image segmentation where LST contains only horizontal and vertical orientation information but lake in other orientation information and also in the image intensity information on which active contour is dependent. Therefore in this paper, LST is modified by adding intensity information from tensor oriented structure tensor to enhance the orientation information. In the proposed model, these phases oriented features are utilized as an external force in the region based active contour model (ACM) to segment the texture images having intensity inhomogeneity and noisy images. To validate the results of the proposed model, quantitative analysis is also shown in terms of accuracy using a Berkeley image database.
This paper presents an FPGA-based algorithm for moving object detection from video for traffic surveillance. The algorithm uses background subtraction, edge detection and shadow detection techniques. Background subtraction involves selective and non-selective updating to improve sensitivity. Edge detection helps find object boundaries while shadow detection removes falsely detected pixels from shadows. The algorithm is implemented using VHDL on a Spartan-6 FPGA board. Experimental results show the algorithm can accurately detect moving vehicles in different lighting conditions with low power consumption, making it suitable for traffic monitoring applications.
Object extraction using edge, motion and saliency information from videoseSAT Journals
Β
Abstract Object detection is a process of finding the instances of object of a certain class which is useful in analysis of video or image. There are number of algorithms have been developed so far for object detection. Object detection has got significant role in variety of areas of computer vision like video surveillance, image retrieval`. In this paper presented an efficient algorithm for moving object extraction using edge, motion and saliency information from videos. Out methodology includes 4 stages: Frame generation, Pre-processing, Foreground generation and integration of cues. Foreground generation includes edge detection using sobel edge detection algorithm, motion detection using pixel-based absolute difference algorithm and motion saliency detection. Conditional Random Field (CRF) is applied for integration of cues and thus we get better spatial information of segmented object. Keywords: Object detection, Saliency information, Sobel edge detection, CRF.
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.
Model User Calibration Free Remote Gaze Estimation SystemKalle
Β
Gaze estimation systems use calibration procedures that require active subject participation to estimate the point-of-gaze accurately. In these procedures, subjects are required to fixate on a specific point or points in space at specific time instances. This
paper describes a gaze estimation system that does not use calibration procedures that require active user participation. The
system estimates the optical axes of both eyes using images from a stereo pair of video cameras without a personal calibration procedure. To estimate the point-of-gaze, which lies along the visual axis, the angles between the optical and visual axes are estimated by a novel automatic procedure that minimizes the distance between the intersections of the visual axes of the left and right eyes with the surface of a display while subjects look naturally at the display (e.g., watching a video clip). Experiments
with four subjects demonstrate that the RMS error of this point-of-gaze estimation system is 1.3ΒΊ.
This document provides an overview of image processing techniques for traffic applications. It discusses automatic lane finding using color-based and texture-based segmentation as well as feature-driven approaches. Object detection methods like thresholding, edge detection using Canny operator, and background differencing are also covered. Additionally, the document proposes an emergency vehicle detection system using red beacon detection and frequency analysis to override normal traffic light patterns when an emergency vehicle is detected.
Segmentation and Classification of MRI Brain TumorIRJET Journal
Β
This document presents a study comparing two techniques for detecting brain tumors in MRI images: level set segmentation and K-means segmentation. Features are extracted from the segmented tumors using discrete wavelet transform and gray level co-occurrence matrix. The features are then classified as benign or malignant using a support vector machine. The level set method and K-means method are evaluated based on accuracy, sensitivity, and specificity on a dataset of 41 MRI brain images. The level set method achieved slightly higher accuracy of 94.12% compared to the K-means method.
Palmprint verification using lagrangian decomposition and invariant interestDakshina Kisku
Β
This document summarizes a research paper on palmprint verification using Lagrangian decomposition and invariant interest points. The paper proposes a system that extracts the region of interest from palm images, uses SIFT to extract invariant features, and performs matching using a Lagrangian graph technique. It tests the system on two databases, achieving recognition rates of 97.1% and 95.8% with low false acceptance and rejection rates. The paper concludes the proposed system is effective and robust for palmprint authentication.
Wavelet Transform based Medical Image Fusion With different fusion methodsIJERA Editor
Β
This paper proposes wavelet transform based image fusion algorithm, after studying the principles and characteristics of the discrete wavelet transform. Medical image fusion used to derive useful information from multimodality medical images. The idea is to improve the image content by fusing images like computer tomography (CT) and magnetic resonance imaging (MRI) images, so as to provide more information to the doctor and clinical treatment planning system. This paper based on the wavelet transformation to fused the medical images. The wavelet based fusion algorithms used on medical images CT and MRI, This involve the fusion with MIN , MAX, MEAN method. Also the result is obtained. With more available multimodality medical images in clinical applications, the idea of combining images from different modalities become very important and medical image fusion has emerged as a new promising research field
Obstacle detection for autonomous systems using stereoscopic images and bacte...IJECEIAES
Β
This paper presents a low cost strategy for real-time estimation of the position of ob- stacles in an unknown environment for autonomous robots. The strategy was intended for use in autonomous service robots, which navigate in unknown and dynamic indoor environments. In addition to human interaction, these environments are characterized by a design created for the human being, which is why our developments seek morphological and functional similarity equivalent to the human model. We use a pair of cameras on our robot to achieve a stereoscopic vision of the environment, and we analyze this information to determine the distance to obstacles using an algorithm that mimics bacterial behavior. The algorithm was evaluated on our robotic platform demonstrating high performance in the location of obstacles and real-time operation.
A NOVEL IMAGE SEGMENTATION ENHANCEMENT TECHNIQUE BASED ON ACTIVE CONTOUR AND...acijjournal
Β
This document summarizes a novel image segmentation technique based on active contours and topological alignments. The technique aims to improve boundary detection by incorporating the advantages of both active contours and topological alignments. It presents a two-step algorithm: 1) Initial segmentation is performed using topological alignments to improve cell tracking results. 2) The output is transformed into the input for an active contour model, which evolves toward cell boundaries for analysis of cell mobility. Tests on 70 grayscale cell images showed the technique achieved better segmentation and boundary detection compared to active contours alone, including for low contrast images and cases of under/over-segmentation.
Classification and Segmentation of Glaucomatous Image Using Probabilistic Neu...ijsrd.com
Β
The gradual visual field loss and there is a characteristic type of damage to the retinal nerve fiber layer associated with the progression of the disease glaucoma. Texture features within images are actively pursued for accurate and efficient glaucoma classification. Energy distribution over wavelet subband is applied to find these important texture features. In this paper, we investigate the discriminatory potential of wavelet features obtained from the Daubechies (db3), symlets (sym3), and biorthogonal (bio3.3, bio3.5, and bio3.7) wavelet filters. We propose a novel technique to extract energy signatures obtained using 2-D discrete wavelet transform, and subject these signatures to different feature ranking and feature selection strategies. Here my project aims at the use of Probabilistic Neural Network (PNN), Fuzzy C-means (FCM) and K-means helps for the detection of glaucoma disease. For this, fuzzy c-means clustering algorithm and k-means algorithm is used. Fuzzy c-means results faster and reliably good clustering when compare to k-means.
Hierarchical Vertebral Body Segmentation Using Graph Cuts and Statistical Sha...IJTET Journal
Β
Abstractβ Bone Mineral Density (BMD) estimations and fracture investigation of the spine bones are retrained to the vertebral bodies (VBs).A contemporary shape and appearance based method is proposed to segment VBs in clinical Computed Tomography (CT) images without any user arbitration. The proposed approach depends on both image appearance and shape information. Shape knowledge is aggregated from a set of training shapes. Then shape variations are estimated using statistical shape model which approximates the shape variations of the vertebral bodies and its background in the variability region. To segment a VB, the graph cut method used to detect the VB region automatically. Detected contours are aligned and mean shape model is created. The spatial interaction between the neighboring pixels is identified. The statistical shape model is used to produce the deformable shape model and all instances of the shape lies with the current estimate of the mean shape.
Gait Based Person Recognition Using Partial Least Squares Selection Scheme ijcisjournal
Β
The document summarizes a research paper on gait-based person recognition using partial least squares selection. It presents an Arbitrary View Transformation Model (AVTM) that uses gait energy images and partial least squares (PLS) feature selection to improve gait recognition accuracy under varying viewing angles, clothing, and other conditions. The proposed AVTM PLS method is evaluated on the CASIA gait database and shown to achieve higher recognition rates compared to other existing methods, especially when there are changes in viewing angle, clothing, or whether the person is carrying something. Tables of results demonstrate the proposed method outperforms alternatives across different test conditions and ranges of gallery and probe viewing angles.
This document presents a method for tracking moving objects in video sequences using affine flow parameters combined with illumination insensitive template matching. The method extracts affine flow parameters from frames to model local object motion using affine transformations. It then applies template matching with illumination compensation to track objects across frames while being robust to illumination changes. The method is evaluated on various indoor and outdoor database videos and is shown to effectively track objects without false detections, handling issues like illumination variations, camera motion and dynamic backgrounds better than other methods.
This document summarizes research on analyzing the steady-state performance of a self-excited induction generator using three optimization techniques: genetic algorithms, pattern search, and quasi-Newton methods. It provides background on induction generators and how they can operate as self-excited generators by connecting capacitors to the stator terminals. The document presents the standard steady-state equivalent circuit model and derives nonlinear equations that are solved using the three optimization techniques to determine unknown parameters. The performance of the self-excited induction generator is then evaluated based on the determined parameters.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This document discusses sensorless vector control of induction motors. It presents the dynamic modeling of induction motors using a reference frame transformation. It then describes the principles of vector control using an inverse transformation to control stator currents. A model reference adaptive system is proposed for sensorless speed estimation, where an adaptive model estimates the rotor speed by comparing its output to a reference model. Simulation results show the sensorless control approach can accurately estimate speed with good tracking performance.
This document summarizes a paper that proposes a new approach to feature-based 3D modeling of turned components in AutoCAD. The approach develops algorithms to model features like cylinders, tapers, holes, and grooves based on user-entered dimensions. It then stores feature information and uses it to assess similarity between components. The modeling system supports both feature-based design and recognition without needing separate feature extraction. The paper presents the algorithms for modeling different features and assessing similarity based on common features like cylinders, holes, or grooves.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This document presents a geometric programming model to optimize the production rate of a turning process. It develops a mathematical model to express the production time as a function of cutting parameters like cutting speed and feed rate. The objective is to minimize production time by determining the optimal cutting conditions. Experimental validation of the model shows it provides an efficient way to maximize production rate within operating constraints like maximum speed, feed rate, power requirements and surface roughness. The geometric programming technique offers advantages over other optimization methods for this application.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This document summarizes a study on wall pressure distribution in a suddenly expanded flow for an area ratio of 2.56. Experiments were conducted by attaching an enlarged duct to the exit of an axisymmetric convergent-divergent nozzle. Wall pressure was measured for nozzle pressure ratios of 3-11 and Mach numbers of 1.87, 2.2, and 2.58. Microjets were used as an active control method to study their effect on wall pressure distribution. Results showed that microjets did not adversely affect the oscillatory wall pressure field for most conditions tested. At Mach 2.58 and NPR of 9, microjets significantly increased the reattachment length in the duct. In general, microjets were found
This document evaluates the performance of the AODV and DSR routing protocols for Variable Bit Rate (VBR) multimedia traffic in mobile ad hoc networks. It conducts simulations in NS-2 to analyze four performance metrics: packet received, throughput, routing overhead, and network load. The results show that AODV outperforms DSR for packet received, throughput, and routing overhead. DSR has higher network load than AODV. Therefore, the document concludes that AODV is better suited than DSR for VBR multimedia transmission in mobile ad hoc networks.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This document summarizes a study analyzing the integrated land and watershed development of Dhobai Watershed in Dumka District, Jharkhand, India using GIS and geonomic analysis. The study aims to generate updated thematic information on natural resources to facilitate sustainable land and water management. Methodology included visual and digital interpretation of satellite imagery and topographical maps. Themes mapped included geomorphology, drainage, climate, soils, and land use/land cover. Geomorphological units identified include valleys, hills, and uplands. Drainage is dominated by the Dhobai River. Soils include Entisols, Inceptisols and Alfisols. Land use is primarily single
The document discusses the performance analysis of the MUSIC algorithm for direction of arrival (DOA) estimation using different antenna array configurations. It explores the MUSIC algorithm using a uniform linear array (ULA) and uniform circular array (UCA). Computer simulations were developed to evaluate the DOA performance of MUSIC based on ULA and UCA geometries. The performance obtained with both array configurations is analyzed through simulation results. A new proposed array geometry based on ULA is also presented and its performance is compared with ULA through simulation.
El documento expresa afecto y gratitud hacia un grupo de amigas nombradas. Les dice que las quiere y espera seguir contando con su amistad en el futuro.
This document describes visual servo control of a mobile robot using homography-based image feedback. A camera is mounted on the robot to track features in the environment. Homography is estimated from matched features to relate the current and target camera views. The robot's motion model and a control law are derived to drive the robot from its initial position to the target position defined by the target image. Experimental results are presented to validate the visual servo control approach. The high-level goal is to navigate the robot to the target position using only image feedback from the mounted camera.
The document describes the development of an automatic MATLAB-based tool for measuring beam emittance at the Idaho Accelerator Center. An optical transition radiation screen and camera were installed to capture beam images during a quadrupole scan. MATLAB codes were developed to extract beam sizes from the images, perform a polynomial fit to determine emittance, and control the scan automatically via EPICS and MATLAB Channel Access. The tool was tested by measuring the emittance of the HRRL accelerator, reducing measurement time and error compared to manual methods.
This document proposes a new method for corner detection in images using difference chain coding as a measure of curvature. The method involves extracting a one-pixel thick boundary from the image, chain encoding it to determine slope, smoothing the boundary to remove noise, and calculating difference codes to determine points of high curvature change, which indicate corners. Preliminary results show the method is simple, efficient, and performs comparably to standard corner detection techniques like Harris and Yung.
This document presents a novel method for recognizing two-dimensional QR barcodes using texture feature analysis and neural networks. It first extracts texture features like mean, standard deviation, smoothness, skewness and entropy from divided blocks of barcode images. These features are then used to train a neural network to classify blocks as containing a barcode or not. The trained neural network can then be used to locate barcodes in unknown images by classifying each block. The method is implemented and evaluated using MATLAB on a database of QR code images, showing satisfactory recognition results.
Leader Follower Formation Control of Ground Vehicles Using Dynamic Pixel Coun...ijma
Β
This paper deals with leader-follower formations of non-holonomic mobile robots, introducing a formation
control strategy based on pixel counts using a commercial grade electro optics camera. Localization of the
leader for motions along line of sight as well as the obliquely inclined directions are considered based on
pixel variation of the images by referencing to two arbitrarily designated positions in the image frames.
Based on an established relationship between the displacement of the camera movement along the viewing
direction and the difference in pixel counts between reference points in the images, the range and the angle
estimate between the follower camera and the leader is calculated. The Inverse Perspective Transform is
used to account for non linear relationship between the height of vehicle in a forward facing image and its
distance from the camera. The formulation is validated with experiments.
IRJET- Study on the Feature of Cavitation Bubbles in Hydraulic Valve by using...IRJET Journal
Β
This document presents a study on using a single camera and 6 mirrors to measure the 3D features of cavitation bubbles inside a hydraulic valve. It first discusses previous research on using multiple cameras and a single camera with 4 mirrors. It then proposes a new virtual stereo vision system using a single camera and 6 mirrors to account for the opaque object in the hydraulic valve. The document describes the camera model, lens distortion correction, and calibration of the virtual stereo vision sensor. It also presents an algorithm to extract 3D features and size of cavitation bubbles from video data obtained by the new system. Experiments are conducted to demonstrate the effectiveness of the proposed method.
Enhanced Algorithm for Obstacle Detection and Avoidance Using a Hybrid of Pla...IOSR Journals
Β
This document presents an enhanced algorithm for obstacle detection and avoidance using a hybrid of plane-to-plane homography, image segmentation, corner detection, and edge detection techniques. The algorithm aims to improve upon previous methods by eliminating false positives, reducing unreliable corners and broken edges, providing depth perception without planar assumptions, and requiring less processing power. The key components of the algorithm include plane-to-plane homography, image segmentation, Canny edge detection, Harris corner detection, and the RANSAC sampling method for system analysis. Test results on sample images show the algorithm can accurately detect obstacles based on texture differences while reducing noise from ground plane textures.
Segmentation and recognition of handwritten digit numeral string using a mult...ijfcstjournal
Β
In this paper, the use of Multi-Layer Perceptron (MLP) Neural Network model is proposed for recognizing
unconstrained offline handwritten Numeral strings. The Numeral strings are segmented and isolated
numerals are obtained using a connected component labeling (CCL) algorithm approach. The structural
part of the models has been modeled using a Multilayer Perceptron Neural Network. This paper also
presents a new technique to remove slope and slant from handwritten numeral string and to normalize the
size of text images and classify with supervised learning methods. Experimental results on a database of
102 numeral string patterns written by 3 different people show that a recognition rate of 99.7% is obtained
on independent digits contained in the numeral string of digits includes both the skewed and slant data.
Text Detection and Recognition in Natural ImagesIRJET Journal
Β
1. The document presents a framework for detecting and recognizing text in natural images.
2. The framework includes candidate text generation using MSER extraction and discrete wavelet transform, followed by non-text filtering using occupation ratio and stroke width.
3. A component level classifier then determines relationships between connected components, and an SVM classifier further rejects non-text blocks to output the detected text, which is then recognized using OCR.
Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...IRJET Journal
Β
This document presents research on detecting license plates in foggy conditions using an enhanced OTSU technique. The researchers tested their technique on a large database of license plate images taken under different conditions, including clear and foggy images. They evaluated the technique using various performance parameters such as MSE, PSNR, SSIM, and aspect ratio. When compared to a base technique, the enhanced OTSU technique showed improvements in these parameters of 14.93%, 14.12%, 39.21%, and 40% respectively. The technique aims to better handle hazardous image conditions like foggy weather that existing techniques often struggle with. It uses steps like image denoising, thresholding segmentation, and character extraction to read license plates in low-visibility situations
This document presents a new method for detecting DC voltage faults in switched reluctance motor (SRM) drives. The method uses K-means clustering to analyze torque waveform data and classify faults using support vector machines (SVM). Simulation results show that torque ripple patterns change with different DC voltage levels. The proposed approach clusters the torque data and uses SVM to detect and classify DC voltage faults, which enables intelligent fault identification and diagnosis in SRM drives.
A new gridding technique for high density microarrayAlexander Decker
Β
This document describes a new gridding technique for high density microarray images. [1] The technique uses the intensity projection profile of the most suitable subimage to locate subarrays and individual spots without any user input parameters. [2] It is capable of processing images with irregular spots, varying surface intensity, and over 50% contamination. [3] The key steps are preprocessing the image, then using horizontal and vertical intensity projection profiles of the preprocessed image to estimate global parameters for locating subarrays, and local parameters for locating individual spots within each subarray.
Design of Linear Array Transducer Using Ultrasound Simulation Program Field-IIinventy
Β
This document summarizes a study that used the ultrasound simulation program Field II to model and simulate the pressure field generated by a linear array transducer and its propagation through biological tissue. The study designed a 16-element linear array transducer with Field II and simulated its impulse response. It then propagated the acoustic field through a human kidney tissue and observed the pressure profile and beam pattern at the focal point. The study also compared the impulse response, pressure field, beam pattern and detected images produced by linear arrays with 32 elements versus 64 elements. The results demonstrated Field II's ability to simulate ultrasound transducers and propagate fields through tissue.
This document proposes a method for remote sensing image retrieval using convolutional neural networks with weighted distance and result re-ranking. It has two stages: 1) An offline stage where a pre-trained CNN is fine-tuned on labeled images to extract features for the retrieval dataset. 2) An online stage where the fine-tuned CNN extracts features from a query image and calculates weighted distances to retrieved images, giving more preference to images from similar classes to the query. Experiments on two datasets show the method improves retrieval performance compared to state-of-the-art methods.
Title of Publication : A Custom single purpose fixed point Processor Based System for Map Generation Using Ultrasound Sensors
Publisher:
ICEDSP 09 (IEEE - International Conference on Electronic Design and Signal Processing)
Image segmentation methods for brain mri imageseSAT Journals
Β
This document compares different edge detection methods for brain MRI images and proposes a new active contour (snake) model approach. It first describes traditional gradient-based methods like Sobel, Prewitt and Canny edge detectors, noting their limitations in medical images. It then introduces active contour models, which use energy functions to capture edges of curved objects sharply. An experiment applies different methods to a brain MRI image and compares their outputs visually and using PSNR, finding the active contour method performs best in segmenting the brain region accurately. The document concludes the active contour approach is well-suited for medical image segmentation tasks.
1. The document presents a method for super resolution of text images using ant colony optimization. It involves registering multiple low resolution images, fusing them, performing soft classification to assign pixel values to multiple classes, and using ant colony optimization for super resolution mapping to increase the resolution.
2. Key steps include SURF-based image registration, intensity-based and discrete wavelet transform fusion, decision tree-based soft classification, and ant colony optimization to assign pixel values based on pheromone updating to increase resolution.
3. Test cases on images with angular displacement, blurred text, etc. show that the method increases resolution successfully but can add some noise, though processing is faster than alternatives. Ant colony optimization
Comparison of Different Methods for Fusion of Multimodal Medical ImagesIRJET Journal
Β
This document compares different methods for fusing multimodal medical images, including PCA, DCT, SWT, and DWT. It provides an overview of each method, including formulations, process flow diagrams, algorithms, and advantages/disadvantages. PCA uses eigenvectors to reveal internal data structure and remove redundancy. DCT expresses image blocks as sums of cosine functions. SWT is a translation-invariant modification of DWT that does not decimate coefficients. DWT decomposes images into coarse and detailed frequency subbands using wavelet transforms. The document reviews each method for fusing medical images from different modalities to extract complementary information.
EFFICIENT IMAGE RETRIEVAL USING REGION BASED IMAGE RETRIEVALsipij
Β
1) The document describes an efficient region-based image retrieval system that uses discrete wavelet transform and k-means clustering. It segments images into regions, each characterized by features like size, mean, and covariance.
2) The system pre-processes images by resizing, converting to HSV color space, performing DWT, and using k-means clustering on DWT coefficients to generate regions. It extracts features for each region and stores them in a database.
3) For retrieval, it pre-processes the query image similarly and calculates similarities between the query regions and database regions based on their features, returning similar images.
EFFICIENT IMAGE RETRIEVAL USING REGION BASED IMAGE RETRIEVAL
Β
K25047051
1. S. SwarnaLatha, R.Mahesh / International Journal of Engineering Research and Applications
(IJERA) ISSN: 2248-9622 www.ijera.com
Vol. 2, Issue5, September- October 2012, pp.047-051
Image Processing Based Stator Fault Severity Detection and
Diagnosis of Induction Motor Using Labview
S. SwarnaLatha*,R.Mahesh**
* Department of electronics and communication engineering, S.V. University, Tirupati
** Department of Electrical and electronics engineering, S.V. University, Tirupati.
ABSTRACT
This paper deals with the fault severity Gravity centerof the region and the x coordinate of
detection and diagnosisof induction motor fault the mean upper point ofthe region (dist_xc_tlr) are
based on image processing using particle analysis. based on visual features. This will allow the
Index of compactness and distance between xc identification of turn faults in the stator winding and
coordinate of gravity center of the region and x its correspondent severity. The identification ofthe
coordinate of the mean upper point of the region faulty phase is another important feature of the
(dist_xc_tlr) are two features extracting by image proposed method.
processing. Using the fuzzy logic strategy, a better
understanding of heuristics underlying the motor 2. PARKβS VECTOR APPROACH
faults detection and diagnosis process can be The analysis of the three-phase induction
achieved by means of automating fault diagnosis motor can be simplified using Clark-Concordia
without the intervention of anoperator. transformation. This transformation allows the
reduction of a three-phase system into a two-phase
1. INTRODUCTION equivalent system. In three phase induction motor the
Three-phase induction motor plays a very connection to the mains usually does not considers
important role in the industrial life. These motors are the neutral. Under this situation the three phase
one of the most widely used electrical machines. To induction motor Ξ±Ξ² line currents are given by:
ensure a continuous and safety operation for these
2 1 1
motors, preventive maintenance programs, with fault ππΌ = ππ β ππ β π
detection techniques, must be considered. Many 3 6 6 π
condition monitoring methods have been proposed
for the induction machine fault detection and 1 1
ππ½ = π β π
classification [1]. 2 π 2 π
Condition monitoring schemes have A healthy three-phase induction motor
concentrated on sensingspecific failure modes. Stator generates a circular pattern, assuming an elliptic
faults are one of the majorelectrical machines pattern whose major axis orientation is associated to
malfunctions. These faults are linked withthe the faulty phase. This elliptic pattern also changes
harmonics spectrum of the stator current. So, one of according to the fault severity. For more severe faults
themost significant methods based on the analysis of the eccentricity of the ellipse increases. This is shown
the machineline currents is the motor current using Labview graphical coding presented as Fig.1
signature analysis (MCSA)[2]-[4]. This method is and Fig.2
based on the motor line currentmonitoring and
consequent inspection of its deviations in 3. IMAGE PROCESSING BASED
thefrequency domain. Another approach based on the SYSTEM
analysis of machine line currents is the Park's vector A feature-based recognition of stator pattern
approach [5]-[6]. This method is based on the current independent of their shape, size and
identification of the stator current Concordia patterns. orientation is the goal of the proposed method.
This enables the identification of the stator fault and Finding efficient invariants features are the key to
its extension by a pattern recognition method. The solve this problem. Particular attention is paid to
Park's vector approach can be used to detect a faulty visual-based features obtained in the image
motor based on the shape of its pattern. processing system.The proposed image processing is
Under this context, this paper proposes a divided in three stages: image composition, particle
new method forthe detection of a three-phase analysis and feature extraction as shown in Fig.3. The
induction motor stator fault. Thismethod is based on inputs for the image processing based system are the
the image identification of the statorcurrent Ξ±Ξ² currents and the outputs are I.O.C and dist_xc_tlr
Concordia patterns. The index of compactness feature values.
(I.O.C.)and distance between the xc coordinate of the
47 | P a g e
2. S. SwarnaLatha, R.Mahesh / International Journal of Engineering Research and Applications
(IJERA) ISSN: 2248-9622 www.ijera.com
Vol. 2, Issue5, September- October 2012, pp.047-051
3.1. IMAGE COMPOSITION and at the same time obtain some properties that help
In the image composition stage, the Ξ±Ξ² stator feature extraction the NI vision particle analysis
currents are first represented as an image in order to palette is used [7]. This method leads to anefficient
be used in the pattern recognition method. Each pixel calculation of the region area and its contour
belonging to the object contour represents each Ξ±Ξ² perimeter.
sample current.
A binary image can be considered as a Image contour
particular case of a grey image with I(x,y)=1 for
pixels that belongs to an object, and I(x,y)=0 for
pixels that belongs to the background. Fig.4 shows
the Ξ±Ξ² stator currents represented in the image plain
after image composition process.
Figure4. Image plan for the Ξ±Ξ² line currents
During the contour following right and left upper
points(tr_p, tl_p) of the region were obtained using
particle measurement of first pixel through which the
last pixel on the first line of the region.
3.3. FEATURE EXTRACTION
The feature extraction stage uses the area of
the object and the contour perimeter to compute the
index of compactness. To obtain the distance
between the xc coordinate of the gravity center of the
region and the x coordinate of the mean upper point
of the region it is necessary to compute the gravity
center (xc, yc)[8].
The index of compactness and the distance
Figure1. Front Panel displaying fault pattern between the xccoordinate of the gravity center of the
region and the x coordinate of the mean upper point
of the region are the key features for the fault
diagnosis procedure.
Assume that the pixels in the digital image
are piecewise constant and the dimension of the
bounded region image for each object is denoted by
MΓN pixels, the visual features, area and perimeter,
used to determine the I.O.C. can be obtained as [9]:
π π
π΄ πΌ = πΌ(π₯, π¦)
π₯=1 π¦ =1
π πΌ = π΄ππ π₯π¦
π₯,π¦
Figure2. Graphical code for pattern generation Where Arcxy is the length of the arc along the object
contour, where x and y are neighbors.
NI Vision dist_xc_tlr The index of compactness is then given by:
Image
particle Feature
Pattern(IΞ±
analysis extraction
& π΄(πΌ)
vs IΞ²) IOC πΌππΆ πΌ =
palette π(πΌ)2
Physically, the index of compactness denotes the
Figure3. Structure of image processing based system fraction of maximum area that can be encircled by
the perimeter actually occupied by the object.
3.2. PARTICLE ANALYSIS The coordinate xc of the gravity center is given by:
π π
In the pattern recognition method, after image π₯=1 π¦=1 πΌ(π₯, π¦) . π₯
π₯π =
composition it is necessary to determine the shape of π΄(πΌ)
the region. To represent the boundary of the region
48 | P a g e
3. S. SwarnaLatha, R.Mahesh / International Journal of Engineering Research and Applications
(IJERA) ISSN: 2248-9622 www.ijera.com
Vol. 2, Issue5, September- October 2012, pp.047-051
The distance between the xc coordinate of the
gravity center of the region and the x coordinate of
Motor
the mean upper point of the region is given by:
π‘π _ π + π‘π _ π
πππ π‘ _ π₯ π _ π‘ππ πΌ = π₯ π β
2
Where tl_p and tr_p are the x coordinates of Three-phase
Image Processing
the top-left and the top-right points of the region. based System (NI Fault
to two-phase Vision β Particle
In fig.5 it is shown that distance between the xc Detection
coordinates of the gravity center of the region and the (NI Labview) analysis)
x coordinates of the mean point between the top-left
and top-right points of the regionevaluation code. Figure6.Structure of proposed fault detection system
TABLE.1. Simulation results
Fault type I.O.C Dist_xc_tlr
No fault 0.0822694 -0.529
Phase A reduced 0.0224325 -0.506
fault
Phase A higher fault 0.0812921 -0.508
Phase B reduced 0.0750095 24.4
fault
Phase B higher fault 0.0584286 59.4
Phase C reduced 0.0751506 -25
fault
Phase C higher fault 0.0581938 -60.5
Figure 5. Graphical code for feature extraction
4. INDUCTION MOTOR FAULT
DETECTION AND INDICATION Fig: 78
A block diagram of the induction motor IΞ± 9
detection and simulation results of fault type with
I.O.C and dist_xc_tlr are presented in fig.6 and Ξ±Ξ²vector
table.1 respectively. pattern for
IΞ² different
SIMULATION RESULTS severities
The system shown in fig.6 was simulated in of faults
the Labview environment. The induction motor was
initially simulated without fault. In this case the
corresponding Ξ±Ξ² vector pattern is a circle.
Table.1 presents the obtained results for the two
A multi-input single output (MISO) fuzzy
features. When the induction motor has no fault the
controller is fed with a fuzzy rule based system.
index of compactness is, approximately, 0.0822694.
Inputs are IOC and dist_xc_tlrthat are obtained from
Fig.7 presents the current vector pattern for the
processed image and output is fuzzy output value.
healthy motor, which does not present any
This output is given to a fault severity detection and
eccentricity. For a small induction motor fault, the
indication system which shows severity of fault as a
index of compactness decreases to 0.0224325,
color variation. If the severity of fault is low then it
denoting that the Ξ±Ξ² pattern exhibits some
shows orange color indication, red for high severity
eccentricity.
of fault and green for no fault case. Fig.10 and fig.11
As can be seen by the results presented in
shows the graphical user interface with fault
Table.1 the distance between the xccoordinate of the
severitydetector and indicators and graphical code for
region gravity center and the mean pointbetween the
fault phase detection and color indication
top-left and top-right points of the
respectively.
region(dist_xc_tlr), is different for each phase fault,
Fault indication system is given with fuzzy
denoting thisdistance value the faulty phase. As the
output value with IOC and dist_xc_tlr values
fault becomesmore severe, the I.O.C decreases and
obtained from image processing system as input to
the dist_xc_tlr increaseits absolute value.Figure 7, 8
fuzzy system results in auto fault phase detection and
and 9 shows the simulation results of current pattern
fault severity indication. Fig.12 shows entire process
for healthy motor, motor with severe fault, and motor
of detection and indication as a simple block diagram
with small fault respectively.
representation.
49 | P a g e
4. S. SwarnaLatha, R.Mahesh / International Journal of Engineering Research and Applications
(IJERA) ISSN: 2248-9622 www.ijera.com
Vol. 2, Issue5, September- October 2012, pp.047-051
REFERENCES
[1] G. B. Kliman, J. Stein, "Methods of motor
current signature analysis," Electric
Machines and Power Systems, vol. 20, no.5,
pp 463-474, September 1992.
[2] B. M. El Hadremi, "A review of induction
motor signature analysis as a medium for
fault detection", IEEE Trans. on Ind.
Electron., vol. 47, pp 984-993, Oct. 2000.
[3] S. Nandi, H. A. Toliyat, "Condition
monitoring and fault diagnosis of electrical
machines - A review," IEEE Industry
Applications Conference 1999, vol. 1, 1999,
pp. 197-204.
[4] S. Schoen, B. Lin, T. Habetler, J. Schlag, S.
Figure10. Fault phase and severity indicator
Farag, "An Unsupervised, On-Line System
for Induction Motor Fault Detection Using
Stator Current Monitoring," IEEE Trans. on
Ind. Applications, vol. 31, no 6, pp. 1280-
1286,Nov./Dec. 1995.
[5] A. J. M. Cardoso, S. M. A. Cruz, J. F. S.
Carvalho, E. S. Saraiva, "Rotor Cage Fault
Diagnosis in Three-Phase Induction Motors
by Park's Vector Approach," IEEE Industry
Applications Conference 1995, vol. 1, 1995,
pp. 642-646.
[6] A. J. M. Cardoso, S. M. A. Cruz, and D. S.
B. Fonseca, "Inter-turn stator winding fault
diagnosis in three-phase induction motors,
Figure11. Graphical code for fault phase detection by Park's Vector Approach," IEEE Trans.
and severity indication Energy Conversion, vol. 14, pp. 595- 598,
Sept. 1999.
[7] NI Vision Concepts manual - s.no.372916l
IOC [8] T.G.Amaral, V.F.Pries, J.F.Martins,
A.J.Pires, and M.M.Crisostomo, βImage
Processing to a Neuro-fuzzy classifier for
dist_xc_tlr
detection and diagnosis of induction motor
stator faultβ, the 33rd annual conference of
the IEEE industrial electronics society, nov,
5-8, 2007
Fuzzy System [9] T. G. Amaral, M. M. Crisostomo, V. F. Pires
and A. T. Almeida, "Visual Motion
Figure12. Fault detectionthrough fuzzy rule based Detection with Hand-Eye manipulator
system Using Statistic Moments Classifiers and
Fuzzy Logic Approach - Study, Application
5. CONCLUSION and Comparation," The 27th Annual
In this paper, based on the Ξ±Ξ² line current Conference of the IEEE Industrial
vector image pattern, for the identification of a three- Electronics Society, IECON'01, Denver,
phase induction motor stator phase fault was Colorado, USA, November 29to December
presented. In the system recognition, feature 2, 2001.
extraction based on index of compactness and the [10] R.Mahesh, and S.SwarnaLatha, βSimulation
distance between the xc coordinate of the pattern of detection of induction motor fault using
gravity center and the mean point between the top- image processing with particle analysisβ,
left and top-right points were done by particle National congress on Communications and
analysis that fed to fuzzy system,detects the faulty computer aided electronic systems(CCAES-
phase and indicates the severity of fault 2012), CBIT, Hyderabad, April 20 and 21st
automatically. 2012
50 | P a g e
5. S. SwarnaLatha, R.Mahesh / International Journal of Engineering Research and Applications
(IJERA) ISSN: 2248-9622 www.ijera.com
Vol. 2, Issue5, September- October 2012, pp.047-051
Authors Bibliography:
S.SwarnaLathareceived her
graduation degree from JNTUCEA
in the year 2000. She received her
post-graduation degree from JNTU
in the year 2004. She is pursuing
her Ph.D. from S.V.U.C.E,
Tirupati in the image processing domain. She
worked as lecturer at J.N.T.U.C.E.A, Anantapur for
4 years and she worked as assistant and Associate
professor in the department of E.C.E., at M.I.T.S,
Madanapalle, She worked as Associate professor at
C.M.R.I.T, Hyderabad and presently she is the
Associate Professor at S.V.U.C.E, Tirupati.
R.Mahesh received his graduation
degree from JNTUHin the year 2007.
He is pursuing post-graduation degree
at S.V.U.C.E, Tirupati. He worked as
assistant professor for 3 years in the
department of E.E.E., at Vemu
Institute of technology, Kothakota.
51 | P a g e