n this paper, Coherence Enhancement Diffusion (CED) is boosted feeding external orientation using new
robust orientation estimation. In CED, proper scale selection is very important as the gradient vector at
that scale reflects the orientation of local ridge. For this purpose a new scheme is proposed in which pre
calculated orientation, by using local and integration scales. From the experiments it is found the proposed
scheme is working much better in noisy environment as compared to the traditional Coherence
Enhancement Diffusion
Boosting ced using robust orientation estimationijma
In this paper, Coherence Enhancement Diffusion (CED) is boosted feeding external orientation using new
robust orientation estimation. In CED, proper scale selection is very important as the gradient vector at
that scale reflects the orientation of local ridge. For this purpose a new scheme is proposed in which pre
calculated orientation, by using local and integration scales. From the experiments it is found the proposed
scheme is working much better in noisy environment as compared to the traditional Coherence
Enhancement Diffusion
Coherence enhancement diffusion using robust orientation estimationcsandit
In this paper, a new robust orientation estimation for Coherence Enhancement Diffusion (CED)
is proposed. In CED, proper scale selection is very important as the gradient vector at that
scale reflects the orientation of local ridge. For this purpose, a new scheme is proposed in
which pre calculated orientation, by using orientation diffusion, is used to find the correct true
local scale. From the experiments it is found that the proposed scheme is working much better
in noisy environment as compared to the traditional Coherence Enhancement Diffusion.
Segmentation Based Multilevel Wide Band Compression for SAR Images Using Coif...CSCJournals
Synthetic aperture radar (SAR) data represents a significant resource of information for a large variety of researchers. Thus, there is a strong interest in developing data encoding and decoding algorithms which can obtain higher compression ratios while keeping image quality to an acceptable level. In this work, results of different wavelet-based image compression and segmentation based wavelet image compression are assessed through controlled experiments on synthetic SAR images. The effects of dissimilar wavelet functions, number of decompositions are examined in order to find optimal family for SAR images. The choice of optimal wavelets in segmentation based wavelet image compression is coiflet for low frequency and high frequency component. The results presented here is a good reference for SAR application developers to choose the wavelet families and also it concludes that wavelets transform is rapid, robust and reliable tool for SAR image compression. Numerical results confirm the potency of this approach.
In this paper we discuss the speckle reduction in images with the recently proposed Wavelet Embedded Anisotropic Diffusion (WEAD) and Wavelet Embedded Complex Diffusion (WECD). Both these methods are improvements over anisotropic and complex diffusion by adding wavelet based bayes shrink in its second stage. Both WEAD and WECD produce excellent results when compared with the existing speckle reduction filters.
The document proposes a hybrid method called Wavelet Embedded Anisotropic Diffusion (WEAD) for image denoising. WEAD is a two-stage filter that first applies anisotropic diffusion to reduce noise, followed by wavelet-based Bayesian shrinkage. This reduces the convergence time of anisotropic diffusion, allowing the image to be denoised with less blurring compared to anisotropic diffusion or wavelet methods alone. Experimental results on various images demonstrate that WEAD achieves better denoising performance than anisotropic diffusion or Bayesian shrinkage methods, as measured by higher PSNR and SSIM scores and fewer required iterations.
This document provides an overview of digital image processing. It discusses what image processing entails, including enhancing images, extracting information, and pattern recognition. It also describes various image processing techniques such as radiometric and geometric correction, image enhancement, classification, and accuracy assessment. Radiometric correction aims to reduce noise from sources like the atmosphere, sensors, and terrain. Geometric correction geometrically registers images. Image enhancement improves interpretability. Classification categorizes pixels. The document outlines both supervised and unsupervised classification methods.
Survey on Single image Super Resolution TechniquesIOSR Journals
Super-resolution is the process of recovering a high-resolution image from multiple lowresolutionimages
of the same scene. The key objective of super-resolution (SR) imaging is to reconstruct a
higher-resolution image based on a set of images, acquired from the same scene and denoted as ‘lowresolution’
images, to overcome the limitation and/or ill-posed conditions of the image acquisition process for
facilitating better content visualization and scene recognition. In this paper, we provide a comprehensive review
of existing super-resolution techniques and highlight the future research challenges. This includes the
formulation of an observation model and coverage of the dominant algorithm – Iterative back projection.We
critique these methods and identify areas which promise performance improvements. In this paper, future
directions for super-resolution algorithms are discussed. Finally results of available methods are given.
Survey On Satellite Image Resolution Techniques using Wavelet TransformIJSRD
Satellite images are used in many research fields. The main problem with the satellite images are their low resolution and blurring effects. Thus, in order to use these images, we need to enhance their quality. Thus, in this paper we have described various wavelet transform techniques such as WZP (Wavelet Zero Padding), CS-WZP (Cyclic Spinning WZP), UWT (Undecimated Wavelet Transform) and DWT (Discrete Wavelet Transform). These all are wavelet transform techniques which are used for image resolution enhancement. In these all techniques and algorithms, we give a low resolution image obtained from any satellite image as the input and get a high resolution image as the output. The comparison of these techniques is made based on two factors MSE (Mean Squared Error) and PSNR (Peak Signal to Noise Ratio).
Boosting ced using robust orientation estimationijma
In this paper, Coherence Enhancement Diffusion (CED) is boosted feeding external orientation using new
robust orientation estimation. In CED, proper scale selection is very important as the gradient vector at
that scale reflects the orientation of local ridge. For this purpose a new scheme is proposed in which pre
calculated orientation, by using local and integration scales. From the experiments it is found the proposed
scheme is working much better in noisy environment as compared to the traditional Coherence
Enhancement Diffusion
Coherence enhancement diffusion using robust orientation estimationcsandit
In this paper, a new robust orientation estimation for Coherence Enhancement Diffusion (CED)
is proposed. In CED, proper scale selection is very important as the gradient vector at that
scale reflects the orientation of local ridge. For this purpose, a new scheme is proposed in
which pre calculated orientation, by using orientation diffusion, is used to find the correct true
local scale. From the experiments it is found that the proposed scheme is working much better
in noisy environment as compared to the traditional Coherence Enhancement Diffusion.
Segmentation Based Multilevel Wide Band Compression for SAR Images Using Coif...CSCJournals
Synthetic aperture radar (SAR) data represents a significant resource of information for a large variety of researchers. Thus, there is a strong interest in developing data encoding and decoding algorithms which can obtain higher compression ratios while keeping image quality to an acceptable level. In this work, results of different wavelet-based image compression and segmentation based wavelet image compression are assessed through controlled experiments on synthetic SAR images. The effects of dissimilar wavelet functions, number of decompositions are examined in order to find optimal family for SAR images. The choice of optimal wavelets in segmentation based wavelet image compression is coiflet for low frequency and high frequency component. The results presented here is a good reference for SAR application developers to choose the wavelet families and also it concludes that wavelets transform is rapid, robust and reliable tool for SAR image compression. Numerical results confirm the potency of this approach.
In this paper we discuss the speckle reduction in images with the recently proposed Wavelet Embedded Anisotropic Diffusion (WEAD) and Wavelet Embedded Complex Diffusion (WECD). Both these methods are improvements over anisotropic and complex diffusion by adding wavelet based bayes shrink in its second stage. Both WEAD and WECD produce excellent results when compared with the existing speckle reduction filters.
The document proposes a hybrid method called Wavelet Embedded Anisotropic Diffusion (WEAD) for image denoising. WEAD is a two-stage filter that first applies anisotropic diffusion to reduce noise, followed by wavelet-based Bayesian shrinkage. This reduces the convergence time of anisotropic diffusion, allowing the image to be denoised with less blurring compared to anisotropic diffusion or wavelet methods alone. Experimental results on various images demonstrate that WEAD achieves better denoising performance than anisotropic diffusion or Bayesian shrinkage methods, as measured by higher PSNR and SSIM scores and fewer required iterations.
This document provides an overview of digital image processing. It discusses what image processing entails, including enhancing images, extracting information, and pattern recognition. It also describes various image processing techniques such as radiometric and geometric correction, image enhancement, classification, and accuracy assessment. Radiometric correction aims to reduce noise from sources like the atmosphere, sensors, and terrain. Geometric correction geometrically registers images. Image enhancement improves interpretability. Classification categorizes pixels. The document outlines both supervised and unsupervised classification methods.
Survey on Single image Super Resolution TechniquesIOSR Journals
Super-resolution is the process of recovering a high-resolution image from multiple lowresolutionimages
of the same scene. The key objective of super-resolution (SR) imaging is to reconstruct a
higher-resolution image based on a set of images, acquired from the same scene and denoted as ‘lowresolution’
images, to overcome the limitation and/or ill-posed conditions of the image acquisition process for
facilitating better content visualization and scene recognition. In this paper, we provide a comprehensive review
of existing super-resolution techniques and highlight the future research challenges. This includes the
formulation of an observation model and coverage of the dominant algorithm – Iterative back projection.We
critique these methods and identify areas which promise performance improvements. In this paper, future
directions for super-resolution algorithms are discussed. Finally results of available methods are given.
Survey On Satellite Image Resolution Techniques using Wavelet TransformIJSRD
Satellite images are used in many research fields. The main problem with the satellite images are their low resolution and blurring effects. Thus, in order to use these images, we need to enhance their quality. Thus, in this paper we have described various wavelet transform techniques such as WZP (Wavelet Zero Padding), CS-WZP (Cyclic Spinning WZP), UWT (Undecimated Wavelet Transform) and DWT (Discrete Wavelet Transform). These all are wavelet transform techniques which are used for image resolution enhancement. In these all techniques and algorithms, we give a low resolution image obtained from any satellite image as the input and get a high resolution image as the output. The comparison of these techniques is made based on two factors MSE (Mean Squared Error) and PSNR (Peak Signal to Noise Ratio).
A comparative study of dimension reduction methods combined with wavelet tran...ijcsit
In this paper, we present a comparative study of dimension reduction methods combined with wavelet
transform. This study is carried out for mammographic image classification. It is performed in three stages:
extraction of features characterizing the tissue areas then a dimension reduction was achieved by four
different methods of discrimination and finally the classification phase was carried. We have late compared
the performance of two classifiers KNN and decision tree.
Results show the classification accuracy in some cases has reached 100%. We also found that generally the
classification accuracy increases with the dimension but stabilizes after a certain value which is
approximately d=60.
This paper proposes a new algorithm for single-image super-resolution that exploits image compressibility in the wavelet domain using compressed sensing theory. The algorithm incorporates the downsampling low-pass filter into the measurement matrix to decrease coherence between the wavelet basis and sampling basis, allowing use of wavelets. It then uses a greedy algorithm to solve for sparse wavelet coefficients representing the high-resolution image. Results show improved performance over existing super-resolution approaches without requiring training data.
Data-Driven Motion Estimation With Spatial AdaptationCSCJournals
The pel-recursive computation of 2-D optical flow raises a wealth of issues, such as the treatment of outliers, motion discontinuities and occlusion. Our proposed approach deals with these issues within a common framework. It relies on the use of a data-driven technique called Generalised Cross Validation to estimate the best regularisation scheme for a given pixel. In our model, the regularisation parameter is a general matrix whose entries can account for different sources of error. The motion vector estimation takes into consideration local image properties following a spatially adaptive approach where each moving pixel is supposed to have its own regularisation matrix. Preliminary experiments indicate that this approach provides robust estimates of the optical flow.
Sub-windowed laser speckle image velocimetry by fast fourier transform technique
Abstract
In this work, laser speckle velocimetry, a unique optical method for velocity measurement of fluid flow has been described. A laser sheet is developed and is illuminated on microscopic seeded particles to produce the speckle pattern at the recording plane. Double frame- single-exposure speckle images are captured in such a way that the second speckle image is shifted exactly in a known direction. The auto-correlation method has the ambiguity of direction of flow. To rectify this, spatial shift of the second image has been premeditated. Cross-correlation of sub interrogation areas is obtained by Fast Fourier Transform technique. Four sub-windows processed to obtain the velocity information with vector map analysis precisely.
Modified adaptive bilateral filter for image contrast enhancementeSAT Publishing House
This paper proposes a two-phase method for removing noise and enhancing image resolution using an adaptive bilateral filter. In the first phase, total variation regularization is used to identify pixels likely contaminated by noise. In the second phase, the image is reconstructed by applying an adaptive technique only to candidate pixels identified for enhancement. Experimental results show the proposed method performs better than median-based filters or edge-preserving regularization methods at preserving texture, details and edges even at high noise levels.
An efficient image segmentation approach through enhanced watershed algorithmAlexander Decker
This document proposes an efficient image segmentation approach combining an enhanced watershed algorithm and color histogram analysis. The watershed algorithm is applied to preprocessed images after merging the results with an enhanced edge detection. Over-segmentation issues are addressed through a post-processing step applying color histogram analysis to each segmented region, improving overall performance. The document provides background on image segmentation techniques, reviews related work applying watershed algorithms, and discusses challenges like over-segmentation that watershed approaches can face.
This paper presents a new approach for the enhancement of Synthetic Radar Imagery using Discrete Wavelet Transform and its variants. Some of the approaches like nonlocal filtering (NLF) techniques, and multiscale iterative reconstruction (e.g., the BM3D method) do not solve the RE/SR imaging inverse problems in descriptive settings imposing some structured regularization constraints and exploits the sparsity of the desired image representations for resolution enhancement (RE) and superresolution (SR) of coherent remote sensing (RS). Such approaches are not properly adapted to the SR recovery of the speckle-corrupted low resolution (LR) coherent radar imagery. These pitfalls are eradicated by using DWT approach wherein the despeckled/deblurred HR image is recovered from the LR speckle/blurry corrupted radar image by applying some of the descriptive-experiment-design-regularization (DEDR) based re-constructive steps. Next, the multistage RE is consequently performed in each scaled refined SR frame via the iterative reconstruction of the upscaled radar images, followed by the discrete-wavelet-transform-based sparsity promoting denoising with guaranteed consistency preservation in each resolution frame. The performance of the method proposed is compared in terms of the number of iterations taken by it with other techniques existing in the literature.
DERIVATION OF SEPARABILITY MEASURES BASED ON CENTRAL COMPLEX GAUSSIAN AND WIS...grssieee
The document derives expressions for Bhattacharyya distance and divergence measures between complex Gaussian and Wishart distributions. It summarizes that Bhattacharyya distance and divergence perform consistently in measuring separability of target classes from polarimetric synthetic aperture radar (POLSAR) data, with divergence being more computationally expensive. The measures are applied to simulated and real POLSAR data to classify land cover types.
Welcome to 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
Web image annotation by diffusion maps manifold learning algorithmijfcstjournal
Automatic image annotation is one of the most challenging problems in machine vision areas. The goal of this task is to predict number of keywords automatically for images captured in real data. Many methods are based on visual features in order to calculate similarities between image samples. But the computation cost of these approaches is very high. These methods require many training samples to be stored in memory. To lessen thisburden, a number of techniques have been developed to reduce the number
of features in a dataset. Manifold learning is a popular approach to nonlinear dimensionality reduction. In
this paper, we investigate Diffusion maps manifold learning method for webimage auto-annotation task.Diffusion maps
manifold learning method isused to reduce the dimension of some visual features. Extensive experiments and analysis onNUS-WIDE-LITE web image dataset with
different visual featuresshow how this manifold learning dimensionality reduction method can be applied effectively to image annotation.
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.
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
Improved nonlocal means based on pre classification and invariant block matchingIAEME Publication
One of the most popular image denoising methods based on self-similarity is called nonlocal
means (NLM). Though it can achieve remarkable performance, this method has a few shortcomings,
e.g., the computationally expensive calculation of the similarity measure, and the lack of reliable
candidates for some non repetitive patches. In this paper, we propose to improve NLM by integrating
Gaussian blur, clustering, and row image weighted averaging into the NLM framework.
Experimental results show that the proposed technique can perform denoising better than the original
NLM both quantitatively and visually, especially when the noise level is high.
An Efficient Algorithm for the Segmentation of Astronomical ImagesIOSR Journals
This document proposes an efficient algorithm for segmenting celestial objects from astronomical images. The algorithm uses multiple preprocessing steps including removing bright point sources, stationary wavelet transform, total variation denoising, and adaptive histogram equalization. Level set segmentation is then used as the key technique for segmentation. Preprocessing helps overcome issues like noise, weak object edges, and low contrast. Level set segmentation can segment objects while retaining their texture and shape information for subsequent classification. The algorithm is tested on various celestial objects and shown to effectively segment them.
The document describes a method for multiresolution image fusion using nonsubsampled contourlet transform (NSCT). NSCT provides multiresolution analysis with shift invariance and directionality. The method uses NSCT to learn edges from a high-resolution panchromatic image and fuse it with low-resolution multispectral images. Maximum a posteriori estimation with a Markov random field prior is used to optimize the fused image. Experimental results on fusing QuickBird satellite images show the proposed method produces higher quality fused images compared to other fusion methods.
Single image super resolution with improved wavelet interpolation and iterati...iosrjce
IOSR journal of VLSI and Signal Processing (IOSRJVSP) is a double blind peer reviewed International Journal that publishes articles which contribute new results in all areas of VLSI Design & Signal Processing. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced VLSI Design & Signal Processing concepts and establishing new collaborations in these areas.Design and realization of microelectronic systems using VLSI/ULSI technologies require close collaboration among scientists and engineers in the fields of systems architecture, logic and circuit design, chips and wafer fabrication, packaging, testing and systems applications. Generation of specifications, design and verification must be performed at all abstraction levels, including the system, register-transfer, logic, circuit, transistor and process levels.
Band Clustering for the Lossless Compression of AVIRIS Hyperspectral ImagesIDES Editor
Hyperspectral images can be efficiently compressed
through a linear predictive model, as for example the one
used in the SLSQ algorithm. In this paper we exploit this
predictive model on the AVIRIS images by individuating,
through an off-line approach, a common subset of bands, which
are not spectrally related with any other bands. These bands
are not useful as prediction reference for the SLSQ 3-D
predictive model and we need to encode them via other
prediction strategies which consider only spatial correlation.
We have obtained this subset by clustering the AVIRIS bands
via the clustering by compression approach. The main result
of this paper is the list of the bands, not related with the
others, for AVIRIS images. The clustering trees obtained for
AVIRIS and the relationship among bands they depict is also
an interesting starting point for future research.
Image Denoising Using Earth Mover's Distance and Local HistogramsCSCJournals
In this paper an adaptive range and domain filtering is presented. In the proposed method local histograms are computed to tune the range and domain extensions of bilateral filter. Noise histogram is estimated to measure the noise level at each pixel in the noisy image. The extensions of range and domain filters are determined based on pixel noise level. Experimental results show that the proposed method effectively removes the noise while preserves the details. The proposed method performs better than bilateral filter and restored test images have higher PSNR than those obtained by applying popular Bayesshrink wavelet denoising method.
Ijri ece-01-02 image enhancement aided denoising using dual tree complex wave...Ijripublishers Ijri
This paper presents a novel way to reduce noise introduced or exacerbated by image enhancement methods, in particular algorithms based on the random spray sampling technique, but not only. According to the nature of sprays, output images of spray-based methods tend to exhibit noise with unknown statistical distribution. To avoid inappropriate assumptions on the statistical characteristics of noise, a different one is made. In fact, the non-enhanced image is considered to be either free of noise or affected by non-perceivable levels of noise. Taking advantage of the higher sensitivity of the human visual system to changes in brightness, the analysis can be limited to the luma channel of both the non-enhanced and enhanced image. Also, given the importance of directional content in human vision, the analysis is performed through the dual-tree complex wavelet transform , lanczos interpolator and edge preserving smoothing filters. Unlike the discrete wavelet transform, the DTWCT allows for distinction of data directionality in the transform space. For each level of the transform, the standard deviation of the non-enhanced image coefficients is computed across the six orientations of the DTWCT, then it is normalized.
Keywords: dual-tree complex wavelet transform (DTWCT), lanczos interpolator, edge preserving smoothing filters.
This paper presents an approach for image restoration in the presence of blur and noise. The image is divided into independent regions modeled with a Gaussian prior. Wavelet-based methods are used for image denoising, while classical Wiener filtering is used for deblurring. The algorithm finds the maximum a posteriori estimate at the intersection of convex sets generated by Wiener filtering. It provides efficient image restoration without sacrificing the simplicity of filtering, and generates a better restored image compared to previous methods.
This paper presents an approach for image restoration in the presence of blur and noise. The image is divided into independent regions modeled with a Gaussian prior. Wavelet based methods are used for image denoising, while classical Wiener filtering is used for deblurring. The algorithm finds the maximum a posteriori estimate at the intersection of convex sets generated by Wiener filtering. It provides efficient image restoration without sacrificing the simplicity of filtering, and generates a better restored image.
A comparative study of dimension reduction methods combined with wavelet tran...ijcsit
In this paper, we present a comparative study of dimension reduction methods combined with wavelet
transform. This study is carried out for mammographic image classification. It is performed in three stages:
extraction of features characterizing the tissue areas then a dimension reduction was achieved by four
different methods of discrimination and finally the classification phase was carried. We have late compared
the performance of two classifiers KNN and decision tree.
Results show the classification accuracy in some cases has reached 100%. We also found that generally the
classification accuracy increases with the dimension but stabilizes after a certain value which is
approximately d=60.
This paper proposes a new algorithm for single-image super-resolution that exploits image compressibility in the wavelet domain using compressed sensing theory. The algorithm incorporates the downsampling low-pass filter into the measurement matrix to decrease coherence between the wavelet basis and sampling basis, allowing use of wavelets. It then uses a greedy algorithm to solve for sparse wavelet coefficients representing the high-resolution image. Results show improved performance over existing super-resolution approaches without requiring training data.
Data-Driven Motion Estimation With Spatial AdaptationCSCJournals
The pel-recursive computation of 2-D optical flow raises a wealth of issues, such as the treatment of outliers, motion discontinuities and occlusion. Our proposed approach deals with these issues within a common framework. It relies on the use of a data-driven technique called Generalised Cross Validation to estimate the best regularisation scheme for a given pixel. In our model, the regularisation parameter is a general matrix whose entries can account for different sources of error. The motion vector estimation takes into consideration local image properties following a spatially adaptive approach where each moving pixel is supposed to have its own regularisation matrix. Preliminary experiments indicate that this approach provides robust estimates of the optical flow.
Sub-windowed laser speckle image velocimetry by fast fourier transform technique
Abstract
In this work, laser speckle velocimetry, a unique optical method for velocity measurement of fluid flow has been described. A laser sheet is developed and is illuminated on microscopic seeded particles to produce the speckle pattern at the recording plane. Double frame- single-exposure speckle images are captured in such a way that the second speckle image is shifted exactly in a known direction. The auto-correlation method has the ambiguity of direction of flow. To rectify this, spatial shift of the second image has been premeditated. Cross-correlation of sub interrogation areas is obtained by Fast Fourier Transform technique. Four sub-windows processed to obtain the velocity information with vector map analysis precisely.
Modified adaptive bilateral filter for image contrast enhancementeSAT Publishing House
This paper proposes a two-phase method for removing noise and enhancing image resolution using an adaptive bilateral filter. In the first phase, total variation regularization is used to identify pixels likely contaminated by noise. In the second phase, the image is reconstructed by applying an adaptive technique only to candidate pixels identified for enhancement. Experimental results show the proposed method performs better than median-based filters or edge-preserving regularization methods at preserving texture, details and edges even at high noise levels.
An efficient image segmentation approach through enhanced watershed algorithmAlexander Decker
This document proposes an efficient image segmentation approach combining an enhanced watershed algorithm and color histogram analysis. The watershed algorithm is applied to preprocessed images after merging the results with an enhanced edge detection. Over-segmentation issues are addressed through a post-processing step applying color histogram analysis to each segmented region, improving overall performance. The document provides background on image segmentation techniques, reviews related work applying watershed algorithms, and discusses challenges like over-segmentation that watershed approaches can face.
This paper presents a new approach for the enhancement of Synthetic Radar Imagery using Discrete Wavelet Transform and its variants. Some of the approaches like nonlocal filtering (NLF) techniques, and multiscale iterative reconstruction (e.g., the BM3D method) do not solve the RE/SR imaging inverse problems in descriptive settings imposing some structured regularization constraints and exploits the sparsity of the desired image representations for resolution enhancement (RE) and superresolution (SR) of coherent remote sensing (RS). Such approaches are not properly adapted to the SR recovery of the speckle-corrupted low resolution (LR) coherent radar imagery. These pitfalls are eradicated by using DWT approach wherein the despeckled/deblurred HR image is recovered from the LR speckle/blurry corrupted radar image by applying some of the descriptive-experiment-design-regularization (DEDR) based re-constructive steps. Next, the multistage RE is consequently performed in each scaled refined SR frame via the iterative reconstruction of the upscaled radar images, followed by the discrete-wavelet-transform-based sparsity promoting denoising with guaranteed consistency preservation in each resolution frame. The performance of the method proposed is compared in terms of the number of iterations taken by it with other techniques existing in the literature.
DERIVATION OF SEPARABILITY MEASURES BASED ON CENTRAL COMPLEX GAUSSIAN AND WIS...grssieee
The document derives expressions for Bhattacharyya distance and divergence measures between complex Gaussian and Wishart distributions. It summarizes that Bhattacharyya distance and divergence perform consistently in measuring separability of target classes from polarimetric synthetic aperture radar (POLSAR) data, with divergence being more computationally expensive. The measures are applied to simulated and real POLSAR data to classify land cover types.
Welcome to 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
Web image annotation by diffusion maps manifold learning algorithmijfcstjournal
Automatic image annotation is one of the most challenging problems in machine vision areas. The goal of this task is to predict number of keywords automatically for images captured in real data. Many methods are based on visual features in order to calculate similarities between image samples. But the computation cost of these approaches is very high. These methods require many training samples to be stored in memory. To lessen thisburden, a number of techniques have been developed to reduce the number
of features in a dataset. Manifold learning is a popular approach to nonlinear dimensionality reduction. In
this paper, we investigate Diffusion maps manifold learning method for webimage auto-annotation task.Diffusion maps
manifold learning method isused to reduce the dimension of some visual features. Extensive experiments and analysis onNUS-WIDE-LITE web image dataset with
different visual featuresshow how this manifold learning dimensionality reduction method can be applied effectively to image annotation.
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.
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
Improved nonlocal means based on pre classification and invariant block matchingIAEME Publication
One of the most popular image denoising methods based on self-similarity is called nonlocal
means (NLM). Though it can achieve remarkable performance, this method has a few shortcomings,
e.g., the computationally expensive calculation of the similarity measure, and the lack of reliable
candidates for some non repetitive patches. In this paper, we propose to improve NLM by integrating
Gaussian blur, clustering, and row image weighted averaging into the NLM framework.
Experimental results show that the proposed technique can perform denoising better than the original
NLM both quantitatively and visually, especially when the noise level is high.
An Efficient Algorithm for the Segmentation of Astronomical ImagesIOSR Journals
This document proposes an efficient algorithm for segmenting celestial objects from astronomical images. The algorithm uses multiple preprocessing steps including removing bright point sources, stationary wavelet transform, total variation denoising, and adaptive histogram equalization. Level set segmentation is then used as the key technique for segmentation. Preprocessing helps overcome issues like noise, weak object edges, and low contrast. Level set segmentation can segment objects while retaining their texture and shape information for subsequent classification. The algorithm is tested on various celestial objects and shown to effectively segment them.
The document describes a method for multiresolution image fusion using nonsubsampled contourlet transform (NSCT). NSCT provides multiresolution analysis with shift invariance and directionality. The method uses NSCT to learn edges from a high-resolution panchromatic image and fuse it with low-resolution multispectral images. Maximum a posteriori estimation with a Markov random field prior is used to optimize the fused image. Experimental results on fusing QuickBird satellite images show the proposed method produces higher quality fused images compared to other fusion methods.
Single image super resolution with improved wavelet interpolation and iterati...iosrjce
IOSR journal of VLSI and Signal Processing (IOSRJVSP) is a double blind peer reviewed International Journal that publishes articles which contribute new results in all areas of VLSI Design & Signal Processing. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced VLSI Design & Signal Processing concepts and establishing new collaborations in these areas.Design and realization of microelectronic systems using VLSI/ULSI technologies require close collaboration among scientists and engineers in the fields of systems architecture, logic and circuit design, chips and wafer fabrication, packaging, testing and systems applications. Generation of specifications, design and verification must be performed at all abstraction levels, including the system, register-transfer, logic, circuit, transistor and process levels.
Band Clustering for the Lossless Compression of AVIRIS Hyperspectral ImagesIDES Editor
Hyperspectral images can be efficiently compressed
through a linear predictive model, as for example the one
used in the SLSQ algorithm. In this paper we exploit this
predictive model on the AVIRIS images by individuating,
through an off-line approach, a common subset of bands, which
are not spectrally related with any other bands. These bands
are not useful as prediction reference for the SLSQ 3-D
predictive model and we need to encode them via other
prediction strategies which consider only spatial correlation.
We have obtained this subset by clustering the AVIRIS bands
via the clustering by compression approach. The main result
of this paper is the list of the bands, not related with the
others, for AVIRIS images. The clustering trees obtained for
AVIRIS and the relationship among bands they depict is also
an interesting starting point for future research.
Image Denoising Using Earth Mover's Distance and Local HistogramsCSCJournals
In this paper an adaptive range and domain filtering is presented. In the proposed method local histograms are computed to tune the range and domain extensions of bilateral filter. Noise histogram is estimated to measure the noise level at each pixel in the noisy image. The extensions of range and domain filters are determined based on pixel noise level. Experimental results show that the proposed method effectively removes the noise while preserves the details. The proposed method performs better than bilateral filter and restored test images have higher PSNR than those obtained by applying popular Bayesshrink wavelet denoising method.
Ijri ece-01-02 image enhancement aided denoising using dual tree complex wave...Ijripublishers Ijri
This paper presents a novel way to reduce noise introduced or exacerbated by image enhancement methods, in particular algorithms based on the random spray sampling technique, but not only. According to the nature of sprays, output images of spray-based methods tend to exhibit noise with unknown statistical distribution. To avoid inappropriate assumptions on the statistical characteristics of noise, a different one is made. In fact, the non-enhanced image is considered to be either free of noise or affected by non-perceivable levels of noise. Taking advantage of the higher sensitivity of the human visual system to changes in brightness, the analysis can be limited to the luma channel of both the non-enhanced and enhanced image. Also, given the importance of directional content in human vision, the analysis is performed through the dual-tree complex wavelet transform , lanczos interpolator and edge preserving smoothing filters. Unlike the discrete wavelet transform, the DTWCT allows for distinction of data directionality in the transform space. For each level of the transform, the standard deviation of the non-enhanced image coefficients is computed across the six orientations of the DTWCT, then it is normalized.
Keywords: dual-tree complex wavelet transform (DTWCT), lanczos interpolator, edge preserving smoothing filters.
This paper presents an approach for image restoration in the presence of blur and noise. The image is divided into independent regions modeled with a Gaussian prior. Wavelet-based methods are used for image denoising, while classical Wiener filtering is used for deblurring. The algorithm finds the maximum a posteriori estimate at the intersection of convex sets generated by Wiener filtering. It provides efficient image restoration without sacrificing the simplicity of filtering, and generates a better restored image compared to previous methods.
This paper presents an approach for image restoration in the presence of blur and noise. The image is divided into independent regions modeled with a Gaussian prior. Wavelet based methods are used for image denoising, while classical Wiener filtering is used for deblurring. The algorithm finds the maximum a posteriori estimate at the intersection of convex sets generated by Wiener filtering. It provides efficient image restoration without sacrificing the simplicity of filtering, and generates a better restored image.
Ijri ece-01-02 image enhancement aided denoising using dual tree complex wave...Ijripublishers Ijri
This paper presents a novel way to reduce noise introduced or exacerbated by image enhancement methods, in particular
algorithms based on the random spray sampling technique, but not only. According to the nature of sprays,
output images of spray-based methods tend to exhibit noise with unknown statistical distribution. To avoid inappropriate
assumptions on the statistical characteristics of noise, a different one is made. In fact, the non-enhanced image is
considered to be either free of noise or affected by non-perceivable levels of noise. Taking advantage of the higher sensitivity
of the human visual system to changes in brightness, the analysis can be limited to the luma channel of both the
non-enhanced and enhanced image. Also, given the importance of directional content in human vision, the analysis is
performed through the dual-tree complex wavelet transform , lanczos interpolator and edge preserving smoothing filters.
Unlike the discrete wavelet transform, the DTWCT allows for distinction of data directionality in the transform space.
For each level of the transform, the standard deviation of the non-enhanced image coefficients is computed across the
six orientations of the DTWCT, then it is normalized.
Keywords: dual-tree complex wavelet transform (DTWCT), lanczos interpolator, edge preserving smoothing filters.
Noise Removal in SAR Images using Orthonormal Ridgelet TransformIJERA Editor
Development in the field of image processing for reducing speckle noise from digital images/satellite images is a challenging task for image processing applications. Previously many algorithms were proposed to de-speckle the noise in digital images. Here in this article we are presenting experimental results on de-speckling of Synthetic Aperture RADAR (SAR) images. SAR images have wide applications in remote sensing and mapping the surfaces of all planets. SAR can also be implemented as "inverse SAR" by observing a moving target over a substantial time with a stationary antenna. Hence denoising of SAR images is an essential task for viewing the information. Here we introduce a transformation technique called ―Ridgelet‖, which is an extension level of wavelet. Ridgelet analysis can be done in the similar way how wavelet analysis was done in the Radon domain as it translates singularities along lines into point singularities under different frequencies. Simulation results were show cased for proving that proposed work is more reliable than compared to other de-speckling processes, and the quality of de-speckled image is measured in terms of Peak Signal to Noise Ratio and Mean Square Error
Noise Removal in SAR Images using Orthonormal Ridgelet TransformIJERA Editor
Development in the field of image processing for reducing speckle noise from digital images/satellite images is a challenging task for image processing applications. Previously many algorithms were proposed to de-speckle the noise in digital images. Here in this article we are presenting experimental results on de-speckling of Synthetic Aperture RADAR (SAR) images. SAR images have wide applications in remote sensing and mapping the surfaces of all planets. SAR can also be implemented as "inverse SAR" by observing a moving target over a substantial time with a stationary antenna. Hence denoising of SAR images is an essential task for viewing the information. Here we introduce a transformation technique called ―Ridgelet‖, which is an extension level of wavelet. Ridgelet analysis can be done in the similar way how wavelet analysis was done in the Radon domain as it translates singularities along lines into point singularities under different frequencies. Simulation results were show cased for proving that proposed work is more reliable than compared to other de-speckling processes, and the quality of de-speckled image is measured in terms of Peak Signal to Noise Ratio and Mean Square Error.
This document discusses and compares different thresholding techniques for image denoising using wavelet transforms. It introduces the concept of image denoising using wavelet transforms, which involves applying a forward wavelet transform, estimating clean coefficients using thresholding, and applying the inverse transform. It then describes several common thresholding methods - hard, soft, universal, improved, Bayes shrink, and neigh shrink. Simulation results on test images corrupted with additive white Gaussian noise show that the proposed improved thresholding technique achieves lower MSE and higher PSNR than the universal hard thresholding method, demonstrating better noise removal performance while preserving image details.
This document discusses different techniques for image denoising using wavelet thresholding. It begins with an introduction to image denoising and the wavelet transform approach. Then it describes various thresholding methods used in wavelet-based image denoising, including hard, soft, universal, improved, Bayes shrink, and neigh shrink thresholding. It also reviews prior literature comparing these different techniques. Finally, it presents simulated results on test images comparing the performance of universal hard thresholding and improved thresholding based on mean squared error and peak signal-to-noise ratio metrics under varying levels of additive white Gaussian noise. The improved thresholding method achieved better denoising performance according to the quantitative metrics.
Path Loss Prediction by Robust Regression Methodsijceronline
International Journal of Computational Engineering Research (IJCER) is dedicated to protecting personal information and will make every reasonable effort to handle collected information appropriately. All information collected, as well as related requests, will be handled as carefully and efficiently as possible in accordance with IJCER standards for integrity and objectivity.
Fusion Based Gaussian noise Removal in the Images using Curvelets and Wavelet...CSCJournals
This document presents a fusion-based method for removing Gaussian noise from images using curvelets and wavelets with a Gaussian filter. The proposed method aims to address artifacts that appear when using curvelets alone. It first applies Gaussian filtering, wavelet denoising, and curvelet denoising separately. It then fuses the results of these three approaches to obtain a better denoised image with fewer artifacts. The method is tested on various standard test images and medical images corrupted with white Gaussian noise. Results are evaluated using peak signal-to-noise ratio and weighted peak signal-to-noise ratio, which accounts for human visual sensitivity.
OBIA on Coastal Landform Based on Structure Tensor csandit
This paper presents the OBIA method based on structure tensor to identify complex coastal
landforms. That is, develop Hessian matrix by Gabor filtering and calculate multiscale structure
tensor. Extract edge information of image from the trace of structure tensor and conduct
watershed segment of the image. Then, develop texons and create texton histogram. Finally,
obtain the final results by means of maximum likelihood classification with KL divergence as
the similarity measurement. The study findings show that structure tensor could obtain
multiscale and all-direction information with small data redundancy. Moreover, the method
described in the current paper has high classification accuracy
ANALYSIS OF INTEREST POINTS OF CURVELET COEFFICIENTS CONTRIBUTIONS OF MICROS...sipij
This paper focuses on improved edge model based on Curvelet coefficients analysis. Curvelet transform is
a powerful tool for multiresolution representation of object with anisotropic edge. Curvelet coefficients
contributions have been analyzed using Scale Invariant Feature Transform (SIFT), commonly used to study
local structure in images. The permutation of Curvelet coefficients from original image and edges image
obtained from gradient operator is used to improve original edges. Experimental results show that this
method brings out details on edges when the decomposition scale increases.
Improved nonlocal means based on pre classification and invariant block matchingIAEME Publication
This document summarizes an article that proposes improvements to the nonlocal means (NLM) image denoising algorithm. The proposed method first applies Gaussian blurring to pre-process the noisy image. It then extracts features from image patches using Hu's moment invariants. Next, it performs k-means clustering on the feature vectors to group similar patches. Finally, it applies row image weighted averaging to reconstruct the image. The experimental results showed this method can perform better denoising than the original NLM, especially at higher noise levels, by providing more reliable candidate patches for the weighted averaging.
Local Phase Oriented Structure Tensor To Segment Texture Images With Intensit...CSCJournals
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.
Improvement of Anomaly Detection Algorithms in Hyperspectral Images Using Dis...sipij
Recently anomaly detection (AD) has become an important application for target detection in hyperspectral remotely sensed images. In many applications, in addition to high accuracy of detection we need a fast and reliable algorithm as well. This paper presents a novel method to improve the performance of current AD algorithms. The proposed method first calculates Discrete Wavelet Transform (DWT) of every pixel vector of image using Daubechies4 wavelet. Then, AD algorithm performs on four bands of “Wavelet transform” matrix which are the approximation of main image. In this research some benchmark AD algorithms including Local RX, DWRX and DWEST have been implemented on Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) hyperspectral datasets. Experimental results demonstrate significant improvement of runtime in proposed method. In addition, this method improves the accuracy of AD algorithms because of DWT’s power in extracting approximation coefficients of signal, which contain the main behaviour of signal, and abandon the redundant information in hyperspectral image data.
The document discusses an algorithm called Adaptive Multichannel Component Analysis (AMMCA) for separating image sources from mixtures using adaptively learned dictionaries. It begins by reviewing image denoising using learned dictionaries, then extends this to image separation from single mixtures. The key contribution is applying this approach to separating sources from multichannel mixtures by learning local dictionaries for each source during the separation process. The algorithm is described and simulated results are shown separating two images from a noisy mixture using the learned dictionaries. In conclusion, AMMCA is able to separate sources without prior knowledge of their sparsity domains by fusing dictionary learning into the separation process.
An Ultrasound Image Despeckling Approach Based on Principle Component AnalysisCSCJournals
This document presents a new principle component analysis (PCA)-based approach for reducing speckle noise in ultrasound images. Speckle noise inherently degrades ultrasound image quality but also contains clinically useful textural information. The proposed method segments the image, calculates the covariance matrix for each segment, averages the covariance matrices to obtain a global covariance matrix, selects the dominant eigenvectors from this matrix to form a projection matrix, projects the image segments onto this matrix to denoise them, and recombines the denoised segments. When applied to simulated and real ultrasound images, it outperformed wavelet denoising, total variation filtering, and anisotropic diffusion filtering in terms of edge preservation and noise removal while maintaining textural information, as
EDGE DETECTION IN RADAR IMAGES USING WEIBULL DISTRIBUTIONcsitconf
Radar images can reveal information about the shape of the surface terrain as well as its
physical and biophysical properties. Radar images have long been used in geological studies to
map structural features that are revealed by the shape of the landscape. Radar imagery also has
applications in vegetation and crop type mapping, landscape ecology, hydrology, and
volcanology. Image processing is using for detecting for objects in radar images. Edge
detection; which is a method of determining the discontinuities in gray level images; is a very
important initial step in Image processing. Many classical edge detectors have been developed
over time. Some of the well-known edge detection operators based on the first derivative of the
image are Roberts, Prewitt, Sobel which is traditionally implemented by convolving the image
with masks. Also Gaussian distribution has been used to build masks for the first and second
derivative. However, this distribution has limit to only symmetric shape. This paper will use to
construct the masks, the Weibull distribution which was more general than Gaussian because it
has symmetric and asymmetric shape. The constructed masks are applied to images and we
obtained good results.
EDGE DETECTION IN RADAR IMAGES USING WEIBULL DISTRIBUTIONcscpconf
Radar images can reveal information about the shape of the surface terrain as well as its physical and biophysical properties. Radar images have long been used in geological studies to
map structural features that are revealed by the shape of the landscape. Radar imagery also has applications in vegetation and crop type mapping, landscape ecology, hydrology, and
volcanology. Image processing is using for detecting for objects in radar images. Edge detection; which is a method of determining the discontinuities in gray level images; is a very
important initial step in Image processing. Many classical edge detectors have been developed over time. Some of the well-known edge detection operators based on the first derivative of the image are Roberts, Prewitt, Sobel which is traditionally implemented by convolving the image with masks. Also Gaussian distribution has been used to build masks for the first and second derivative. However, this distribution has limit to only symmetric shape. This paper will use to construct the masks, the Weibull distribution which was more general than Gaussian because it has symmetric and asymmetric shape. The constructed masks are applied to images and we obtained good results.
Similar to Boosting CED Using Robust Orientation Estimation (20)
International Conference on NLP, Artificial Intelligence, Machine Learning an...gerogepatton
International Conference on NLP, Artificial Intelligence, Machine Learning and Applications (NLAIM 2024) offers a premier global platform for exchanging insights and findings in the theory, methodology, and applications of NLP, Artificial Intelligence, Machine Learning, and their applications. The conference seeks substantial contributions across all key domains of NLP, Artificial Intelligence, Machine Learning, and their practical applications, aiming to foster both theoretical advancements and real-world implementations. With a focus on facilitating collaboration between researchers and practitioners from academia and industry, the conference serves as a nexus for sharing the latest developments in the field.
Comparative analysis between traditional aquaponics and reconstructed aquapon...bijceesjournal
The aquaponic system of planting is a method that does not require soil usage. It is a method that only needs water, fish, lava rocks (a substitute for soil), and plants. Aquaponic systems are sustainable and environmentally friendly. Its use not only helps to plant in small spaces but also helps reduce artificial chemical use and minimizes excess water use, as aquaponics consumes 90% less water than soil-based gardening. The study applied a descriptive and experimental design to assess and compare conventional and reconstructed aquaponic methods for reproducing tomatoes. The researchers created an observation checklist to determine the significant factors of the study. The study aims to determine the significant difference between traditional aquaponics and reconstructed aquaponics systems propagating tomatoes in terms of height, weight, girth, and number of fruits. The reconstructed aquaponics system’s higher growth yield results in a much more nourished crop than the traditional aquaponics system. It is superior in its number of fruits, height, weight, and girth measurement. Moreover, the reconstructed aquaponics system is proven to eliminate all the hindrances present in the traditional aquaponics system, which are overcrowding of fish, algae growth, pest problems, contaminated water, and dead fish.
UNLOCKING HEALTHCARE 4.0: NAVIGATING CRITICAL SUCCESS FACTORS FOR EFFECTIVE I...amsjournal
The Fourth Industrial Revolution is transforming industries, including healthcare, by integrating digital,
physical, and biological technologies. This study examines the integration of 4.0 technologies into
healthcare, identifying success factors and challenges through interviews with 70 stakeholders from 33
countries. Healthcare is evolving significantly, with varied objectives across nations aiming to improve
population health. The study explores stakeholders' perceptions on critical success factors, identifying
challenges such as insufficiently trained personnel, organizational silos, and structural barriers to data
exchange. Facilitators for integration include cost reduction initiatives and interoperability policies.
Technologies like IoT, Big Data, AI, Machine Learning, and robotics enhance diagnostics, treatment
precision, and real-time monitoring, reducing errors and optimizing resource utilization. Automation
improves employee satisfaction and patient care, while Blockchain and telemedicine drive cost reductions.
Successful integration requires skilled professionals and supportive policies, promising efficient resource
use, lower error rates, and accelerated processes, leading to optimized global healthcare outcomes.
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELgerogepatton
As digital technology becomes more deeply embedded in power systems, protecting the communication
networks of Smart Grids (SG) has emerged as a critical concern. Distributed Network Protocol 3 (DNP3)
represents a multi-tiered application layer protocol extensively utilized in Supervisory Control and Data
Acquisition (SCADA)-based smart grids to facilitate real-time data gathering and control functionalities.
Robust Intrusion Detection Systems (IDS) are necessary for early threat detection and mitigation because
of the interconnection of these networks, which makes them vulnerable to a variety of cyberattacks. To
solve this issue, this paper develops a hybrid Deep Learning (DL) model specifically designed for intrusion
detection in smart grids. The proposed approach is a combination of the Convolutional Neural Network
(CNN) and the Long-Short-Term Memory algorithms (LSTM). We employed a recent intrusion detection
dataset (DNP3), which focuses on unauthorized commands and Denial of Service (DoS) cyberattacks, to
train and test our model. The results of our experiments show that our CNN-LSTM method is much better
at finding smart grid intrusions than other deep learning algorithms used for classification. In addition,
our proposed approach improves accuracy, precision, recall, and F1 score, achieving a high detection
accuracy rate of 99.50%.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
The CBC machine is a common diagnostic tool used by doctors to measure a patient's red blood cell count, white blood cell count and platelet count. The machine uses a small sample of the patient's blood, which is then placed into special tubes and analyzed. The results of the analysis are then displayed on a screen for the doctor to review. The CBC machine is an important tool for diagnosing various conditions, such as anemia, infection and leukemia. It can also help to monitor a patient's response to treatment.
1. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
DOI : 10.5121/ijma.2014.6203 23
BOOSTING CED USING ROBUST
ORIENTATION ESTIMATION
Tariq M. Khan2
, Mohammad A. U. Khan1
, Yinan Kong3
1,3
Department of Engineering, Macquarie University, Sydney, Australia
2
Department of Electrical and Computer Engineering,
Effat University, Jeddah, Saudi Arabia.
ABSTRACT
In this paper, Coherence Enhancement Diffusion (CED) is boosted feeding external orientation using new
robust orientation estimation. In CED, proper scale selection is very important as the gradient vector at
that scale reflects the orientation of local ridge. For this purpose a new scheme is proposed in which pre
calculated orientation, by using local and integration scales. From the experiments it is found the proposed
scheme is working much better in noisy environment as compared to the traditional Coherence
Enhancement Diffusion
KEYWORDS
Fingerprint Image Enhancement, Coherence Enhancement Diffusion Directional Filter Bank (DFB),
Decimation free Directional Filter Bank (DDFB).
1. INTRODUCTION
Biometric is a science that deals with the identification of human by using their traits or
characteristics. It is based on measurable and distinctive characteristics which are used to label
and describe individuals [1]. Examples include, face recognition, DNA, palm print, hand
geometry, retina, iris recognition and finger- print. Fingerprint identification is one of the oldest
biometric techniques which have been successfully used in numerous applications [2]. Every
person has a unique and immutable fingerprint. A fingerprint surface contains series of ridges and
valleys/furrows. These patterns of ridges and furrows defines the uniqueness of a fingerprint.
Normally, ridge patterns are decomposed into local ridge characteristics, ridge bifurcation or
ridge ending. These local ridge characteristics are generally known as minutiae points.
Reliable extraction of minutiae is one of the critical step in an automatic fingerprint identification
system. A minutiae based fingerprint matching algorithm heavily relies on the quality of
fingerprint images [1]. In poor quality fingerprint images noise destroy the ridge structure.
Although, a human can identify true minutia of noisy image, but for computer (especially in
online fingerprint identification) the minutiae points’ detection is very difficult process. Thus,
fingerprint image enhancement is believed to be the most important step in minutiae based
fingerprint identification methods [3].
A general fingerprint enhancement approach composed of an initial estimation of local image
parameters, followed by a contextual filtering stage, where local filters are adaptive to the local
image characteristics. In last decade, nonlinear Partial Differential Equation (PDE) based
diffusion has attracted much attention, because of its adaptive behaviour [4]. Nonlinear image
diffusion was first introduced by Prona and Malik [5]. On the basis of their study, numbers of
non-linear diffusion filters have been proposed [6, 7, 8, 9, 10]. Most of these techniques are based
2. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
24
on a scalar diffusivity which bound the diffusion flux always along the gradient direction. These
techniques are linear and isotropic in nature and have same common disadvantages, like edge
blurring. To overcome the short-come of this isotropic diffusion, anisotropic diffusion, which is
nonlinear by nature, is proposed by Joachim Weickert [11] to keep oriented structure preserved.
This technique is well known as Coherence Enhancement Diffusion (CED). In CED, the local
structures of an image are used to diffuse the image, large coherence results large diffusion.
Weickert proposes to modify the eigenvalues of diffusion matrix ,
∑ by setting
( )
min max 2
1
, 1 exp
Q
λ α λ α α
−
= = + −
(1)
where α is a user defined parameter which is used to regulate the amount of smoothing.
Although, CED can enhance coherent structure, it fails for some non-linear local structures. One
of the reasons of its failure is that the eccentricity of diffusion is unbounded. Due to this, it gives
larger value of eccentricity in high contrast region. To overcome this constrain, in this paper, we
propose a Di- rectional Filter Bank (DFB) based robust orientation method to calculate reliable
orientation estimation. By Using the robust orientation estimation we propose a method which
automatically find the min
λ and max
λ . From experiments, it is found that the proposed scheme
not only preserve the global features but it also preserve the local feature under severe noise
conditions, which Almansa algorithm failed to preserve.
The rest of the paper is organized as follow. Section II details the Coherence Enhancement
Diffusion. In section III a new scheme for robust orientation estimation is proposed. Section IV
describes how the pre-computed orientation is used in Coherence Enhancement Diffusion. In
Section V testing and validation is presented and finally the paper is concluded in section VI.
2. COHERENCE ENHANCED DIFFUSION
The diffusion process is thought to be equivalent to the process of energy minimizing variation:
( ) ( ) ( )
( )
2
. T
E u u f tr u u dxdy
β
Ω
= − + Ψ ∇ ∇
∫ (2)
Where f is original image in domain Ω and u is the diffused image.
is a small position. When diffusion matrix is identity, the diffusion equation reduced to Linear
Scale-Space representation given by:
( )
1
2
t L div L
∂ = ∇ (3)
As fingerprint images have a very strong no isotropy, so we have to adapt the diffusion matrix to
local image structure known as second moment matrix. The PDE of Nonlinear Tensor diffusion
defined by [11] is given by:
( )
.
t L D L
∂ = ∇ ∇ (4)
where D is a diffusion tensor. For 2D images this diffusion tensor is then assumed to be:
3. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
25
a b
D
c d
=
(5)
This 2 by 2 matrix always generate an ellipse. It contains min
λ , max
λ and. Where min
λ the minor
axis of the ellipse is, max
λ is its major axis and is the rotation angle. In general this ellipse is
elongates in the direction orthogonal to the ridge. Coherence Enhancement Diffusion is a process
that correctly use min
λ and max
λ according the underlying ridge structure. The diffusion
tensor for nonlinear coherence enhancement can be of form:
0
0
u
T
v
c
D R R
c
=
(6)
where R is a rotation matrix which describes the local coordinate system which is aligned along
with the gradient vector observed at any scale u. Note that u
c and v
c can construct two one
dimensional directional kernel: one scaling or performing diffusion along the u direction and the
other performing diffusion along v direction. In other words we can say that by using appropriate
values of u
c and v
c we can perform diffusion along the ridge direction or across the ridge
direction. Normally u
c is used to diffuse the noise along the ridge direction and v
c for diffusion
across the ridge direction.
The rotation matrix R given in equation 6 gives the eigenvectors of structure tensor. The structure
tensor which implicitly calculates the angles of diffusion matrix is given by:
( ) ( )
( ) ( )
11 12
12 22
, , , ,
, , , ,
xx xy
xy yy
G x y G x y
s s
S
s s G x y G x y
σ σ
σ σ
= =
(7)
where ( )
, ,
xx
G x y σ , ( )
, ,
xy
G x y σ and ( )
, ,
yy
G x y σ represents the Gaussian derivative filters.
The Gaussian derivatives are mostly used for the scale space based vision applications.
Analytically we can easily calculate the eigenvectors of the structure tensor and rotation matrix R.
The diffusion tensor D with components is given by:
( )
( ) ( )
( )
( )
( ) ( )
11 22
11
12
12
11 22
22 11
1/ 2
1/ 2
u v
u v
u v
u v
u v
c c s s
d c c
c c s
d
c c s s
d d c c
α
α
α
− − −
= − +
−
=
− − −
= = − −
(8)
Where
( )
2 2
11 22 12
4
s s s
α = − + (9)
Therefore, the eigenvalues of structure tensor are given by:
4. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
26
( )
( )
min 11 12
max 11 12
1/ 2
1/ 2
s s
s s
λ α
λ α
= + +
= + −
(10)
from these eigenvalues we can determine u
c and v
c as
( )
( )
2
min max 2
max 0.01, 1 /
0.01
u
v
c e k
c
λ λ
− −
= −
=
(11)
3. ROBUST ORIENTATION ESTIMATION
Reliable orientation estimation is very useful for enhancing the quality of features to be detected
in a given image. It can reduce the computation burden placed on post processing stage. In the
presence of noise, it is very hard to get the reliable orientation estimation. In literature, different
techniques have been used for orientation estimation e.g [12] uses a filter bank based approach,
[13] uses waveform projection and spectral estimation is used by [14]. It is reported that these
methods do not provide much accurate results, because they rely on fixed templates or filters. To
manipulate coarse orientation estimation, mathematical modelling using Bayesain network [15]
and complex polynomial are introduced. Later [16] introduces an enhanced gradient-based
approach for reliable orientation estimation. In this scheme, dominant orientation of a base block
from its four overlapping neighbourhoods is estimated and finally a best estimate is selected from
least noise-affected neighbourhood. However, gradients are unreliable and error-prone on
fingerprint images affected by noise like scares, smudges, dryness or wetness of finger [17].
[18] Uses directional filter bank (DFB) to extract the weak features of texture images. In DFB, the
directional images contain linear features in a narrow directional band. It is found from [18] that
these directional images contain significantly less noise as compared to the original image.
However, fixed block/scale is used to compute the gradients for local orientation among
directional images which restricts its capability for noise suppression. [19] propose a multiscale
based DFB for orientation estimation. In this paper we proposed a new multiscale orientation
estimation using Directional Filter Bank. We adopted the following steps.
Step I. The input image L(x; y) is decomposed into number of directional images L(x; y; i) using
Decimation-free Directional Filter bank [19], where i=1,2, ... ,n corresponding to
quantized orientations associated with each directional image.
Step II. At a scale t, each directional image L(x; y; i) is convolved by Gaussian Kernel as L(x; y;
i; t) = g(x; y; t) ∗ L(x; y; i). This provide us with a scale-space representation.
Step III. For each scaled image L(x; y; i; t) the second moment matrix is computed as,
2
2
x x y
simple
x y y
L L L
L L L
µ
=
(12)
This simple
µ is further smoothed using a Gaussian Kernel having scale S, where 2
t
β and
2,3,4,...,8
β = in our case
5. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
27
Step IV. For each t, we got number of second moment matrix ,
t s
µ for each β values. By using
eigenvalue analysis, each ,
t s
µ is decomposed which provide us max
λ for each ,
t s
µ We
develop a measure similar to one suggested in [? ], to pick one parameter t and S value
as,
( ) ( )
2
3/2
max
, ;
A x y i t λ
= (13)
Step V. For each directional image L(x; y; i) the energy measure is computed as,
( ) ( )
,
, ; max , ; , ,
t s
B x y i A x y i t S
= (14)
Step VI. This new energy measure B (x; y; i) associated with each directional image L(x; y; i),
reflects the strength of the orientations associated with a particular direction. Finally, we
lineally combine all the quantized orientation using their respective strength measure i
θ
and we got
( )
( )
( )
1
1
, ;
,
, ;
i
i
i
B x y i
x y
B x y i
ω
ω
θ θ
=
=
= ∑
∑
(15)
4. COHERENCE ENHANCEMENT DIFFUSION USING PRE-COMPUTED
ORIENTATION FIELD
The main difference of our proposed method to the other diffusion based methods, especially
from [20], is that the diffusion tensor is fed with pre-computed orientation field. As discussed in
section III, the proposed scheme for orientation estimation is more robust to noise and other
degradations in the fingerprint than the gradient based methods. By feeding pre-computed
orientation to diffusion can incredibly enhance low-quality fingerprints in particular. To embed
the pre-computed orientation with diffusion tensor, tensor rotation in needed instead to simple
vector multiplication. In tensor rotation, a rotation matrix is multiplied on left and a transpose of
rotation matrix is multiplied on right of tensor matrix:
' '
' '
xx xy xx xy
xy yy
xy yy
D D D D
a b a b
c d D D c d
D D
=
(16)
expansion of Eq. 16 yields.
( )
' 2 2
'
' 2 2
2
2
xx xx yy xy
xy xy xx yy
yy xx yy xy
D a D c D acD
D ad bc D abD cdD
D b D d D bdD
= + +
= + + +
= + +
(17)
6. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
28
Figure 1: Real Fingerprint Images: The performance of [19] and the proposed is given. Two noisy
images a) and d) from FVC database are used to test both the algorithms. b) and e) are the outputs
of orientation estimation by [19] and c) an f) and the outputs of proposed method.
Let ' ' '
,
xx xy yy
D A D Band D C
= = = . In order to rotate a reference frame through an angle
−θ , multiplication of ( )
R θ
− on left and ( )
T
R θ
− on right is required. This process can be
visualized as rotating the ellipse through an angle f
θ θ
=
cos sin cos sin
sin cos sin cos
xx xy
xy yy
D D
A B
B C D D
θ θ θ θ
θ θ θ θ
− −
=
(18)
expansion of Eq. 18 yields,
( )
2 2
2 2
2 2
cos sin 2sin cos
cos sin
sin cos 2sin cos
xx yy xy
xy xx yy
xx yy xy
A D D D
B D abD cdD
C D D D
θ θ θ θ
θ θ
θ θ θ θ
= + +
= + + +
= + +
(19)
The diagonal angle can be calculated by setting '
0
xy
D = . This implies,
( ) ( )
( )
( )
cos2 sin 2 0
tan 2 2 /
,
arctan 2 / / 2
xy diag xx xy
diag xy xx xy
diag xy xx xy
D D D
D D D
so
D D D
θ θ
θ
θ
+ − =
= −
= −
(20)
7. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
29
4.1 CALCULATING ROBUST EIGENVALUES
In order to compute more robust eigenvalues by using pre-computed orientation, we used the
hessian matrix of directional image I1 in new coordinates, given by [18], as,
2 2
1 1
2
11 12
2 2
21 22 1 1
2
I I
h h x x y
H
h h I I
x y y
∂ ∂
′ ′ ′
∂ ∂ ∂
′ = =
∂ ∂
′ ′ ′
∂ ∂ ∂
(21)
Where,
2 2 2 2
2 2
1 1 1 1
2 2 2
2 2 2 2
2 2
1 1 1 1
2 2 2
2 2 2 2
1 1 1 1
2 2
cos sin(2 ) sins
sin sin(2 ) cos
1 1
sin(2 ) cos(2 ) sin(2 )
2 2
i i i
i i i
i i i
I I I I
x x x y y
I I I I
y x x y y
I I I I
x y x x y y
θ θ θ
θ θ θ
θ θ θ
∂ ∂ ∂ ∂
= + +
′
∂ ∂ ∂ ∂ ∂
∂ ∂ ∂ ∂
= − +
′
∂ ∂ ∂ ∂ ∂
∂ ∂ ∂ ∂
= − + +
′ ′
∂ ∂ ∂ ∂ ∂ ∂
(22)
In [18] 11
h is defined as 1
λ and 22
h as 2
λ . In order to get better results in noisy condition
2
1
2
I
x
∂
′
∂
is replaced by A,
2
1
I
x y
∂
′ ′
∂ ∂
by B and
2
1
2
I
y
∂
′
∂
C, which yields,
2 2
1
2 2
2
cos sin(2 ) sin
sin sin(2 ) cos
r i i i
r i i i
A B C
A B C
λ θ θ θ
λ θ θ θ
−
−
= + +
= − +
(23)
4.2 FINAL DIFFUSION TENSOR
For final diffusion tensor matrix, we use,
1
2
0
cos sin cos sin
sin cos 0 sin cos
f f r
f f r
A B
B C
λ
θ θ θ θ
θ θ λ θ θ
−
−
− −
=
(24)
Let 1 1 2 1
cos , sin , sin cos
I x I y I x and I y
θ θ θ θ
= = = − = . By solving above matrix, we get
2 2
1 1 2 2
1 1 1 2 2 2
2 2
1 1 2 2
f r r
f r r
f r r
A I x I x
B I xI y I xI y
C I y I y
λ λ
λ λ
λ λ
− −
− −
− −
= +
= +
= +
(25)
5. TESTING AND VALIDATION
Statistically, the set of minutiae denoted by symbol M were algorithmically obtained and
evaluated against the set of minutiae marked by an expert denoted by symbol F and the minutiae
are classified into two types: termination and bifurcation. Each minutiae point m
compartmentalized into one of the following classes:
8. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
30
• Correct: The correlation between minutiae points generated through the algorithm and
those obtained from the expert is perfect position, i.e
( ) ( )
( )
F M
m F M and type m type m
∈ ∩ =
• False: The expert did not mark the location corresponding to the one obtained through the
algorithm, i.e ( )
,
m M m F
∈ ∉
• Missing: The minutiae location has been marked by the expert but couldn't be seen within
the algorithmically generated image, i.e ( )
,
m M m F
∉ ∈
• Misclassified: The minutiae location marked by the expert could be is also the one found
by the method with the exception that one has been classified as bifurcation and other has
been classified as termination, i.e ( ) ( )
( )
F M
m F M and type m type m
∈ ∩ ≠
Compartmentalization of all the minutiae set is followed by the performance measurement which
is computed statistically. This is done on minutiae obtained from the algorithm as well as
minutiae marked by the experts which makes the performance measurement relative to either total
number of minutiae found algorithmically or the total number of minutiae found by the expert
markings. The measures relative to minutiae marked by the expert which detects the aptitude of
the technique to detect correct minutiae are as follows:
• Missing minutiae is defined as
sin
Mis g
F
• False minutiae is defined as
False
F
• Misclassified minutiae is defined as
Missclassified
F
• Correct minutiae is defined as
Correct
F
• Total error which is the summation of false positive, false negative and misclassified
errors is defined as
sin
Mis g False Missclassified
F
∪ ∪
• Classification rate for the purpose of enhancing the graphical visualization is defined as
Correct
Missclassified
Large number of missing minutiae could be tolerated to certain extent but the large number of
false minutiae would lead to larger noise rate within the mapping stage. On the other hand,
prominence of classification error is based on the manner in which the mapping algorithm deals
with the types of minutiae. Using the techniques described above, the database of true minutiae
was generated, by using the sample images given in Fig. 6 which is used to evaluate the
9. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
31
orientation and scale-matched filters to produce improved input image along with the techniques
described above.
Fig. 2 sample images used for evaluation measure
The table compares the result obtained using the above method.
Proposed Correct False Missing Misclassified
Image1 10 5 5 4
Image2 9 5 5 9
Image3 20 3 4 7
Image4 13 2 5 5
Image5 19 10 4 6
Image6 22 4 8 9
Image7 12 4 5 16
Image8 23 4 6 8
Mean 17.25 5.12 4.75 8
Table1. This table shows the evaluation measure comparing minutiae of proposed algorithm
10. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
32
[12]CED Correct False Missing Misclassified
Image1 14 2 4 2
Image2 5 4 2 15
Image3 8 3 4 20
Image4 1 4 2 5
Image5 3 2 4 22
Image6 16 7 3 20
Image7 4 2 2 30
Image8 16 3 6 7
Mean 9.875 3.375 3.5 15.12
Table2. This table shows the evaluation measure comparing minutiae of [11] CED Enhancement
algorithm
The average number of minutiae points present in the image marked by the expert and the ones
marked by the algorithm for all the eight images was taken, which represented F This was
computed to be 15 using which some performance measures were computed. For the proposed
method, classification error which is calculated as misclassified over correctly detected minutiae
was found to be
/
*100 1.8%
Missclassified F M
F
∩
= (26)
For the CED method, classification error which is calculated as misclassified over correctly
detected minutiae was found to be
/
*100 2.36%
Missclassified F M
F
∩
= (27)
In Fig3, the bar chart shows the performance evaluation measure of both schemes.
6. CONCLUSIONS
Coherence enhancement diffusion filters are the one which have control on the size/ shape of the
filter but, this use derivative for rotation matrix which is not considered as a reliable method.
Therefore, in this work presents a new and a reliable method for robust orientation estimation is
proposed to explicitly calculate the orientation field of a fingerprint image. By using this robust
orientation new local scales for Diffusion matrix are adaptively calculated. The experiments
conducted on the noisy images showed promising results of the proposed scheme.
11. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
33
Fig. 3. Performance Evaluation Measure of both schemes
REFERENCES
[1] L. Hong, Y. Wan, and A. Jain, “Fingerprint image enhancement: Algorithm and performance
evaluation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, pp. 777789,
1998.
[2] M. A. Khan amd A. Khan, T. Mahmmod, M. Abbas, and N. Muhammad, “Fingerprint image
enhancement using principal component analysis (pca) filters,” in International Conference on
Information and Emerging Technologies (ICIET), 2010.
[3] M.A.U. Khan, T. M. Khan, and S. A. Khan, “Coherence enhancement dif- fusion using multi-scale
dfb,” in 7th International Conference on Emerging Technologies, 2011.
[4] J Weickert, “A review of nonlinear diffusion filtering,” cale-Space Theory in Computer Vision, vol.
1252, pp. 3–28, 1997. [5] J Weickert, “A review of nonlinear diffusion filtering,” cale-Space
Theory in Computer Vision, vol. 1252, pp. 3–28, 1997.
[5] P Perona and J Malik, “Scale-space and edge detection using anisotropic diffusion.,” IEEE Trans
Mach Intell., vol. 12(7), pp. 629639, 1990.
[6] L Alvarez, P-L Lions, and J-M Morel, “Image selective smoothing and edge detection by nonlinear
diffusion,” II SIAM J Numer Anal, vol. 29, pp. 845866, 1992.
[7] G Sapiro, “Tannenbaum, affine invariant scale-space,” International Journal of Computer Vision, vol.
11, pp. 25–44, 1993.
[8] L Rudin, S Osher, and E Fatemi, “Nonlinear total variation based noise removal algorithms,” Modeliz
Mat Traitement d Images, p. 149179, 1992.
[9] HM Salinas and D Cabrera Fernandez, “Comparison of pde-based nonlinear diffusion approaches for
image enhancement and denoising in optical coherence tomography,” IEEE Transactions on Medical
Imaging, vol. 26, pp. 761–771, 2007.
[10] D Fang, Z Nanning, and X Jianru, “Image smoothing and sharpening based on nonlinear diffusion
equation.,” Signal Processsing, vol. 88(11), pp. 28502855, 2008.
[11] J Weickert, “Coherence-enhancing diffusion filtering,” Int. J. Computer Vision,, vol. 31, pp. 111–127,
1999.
12. The International Journal of Multimedia & Its Applications (IJMA) Vol.6, No.2, April 2014
34
[12] A.K. Jain, S. Pankanti, and L. Hong, “A multichannel approach to finger- print classification,” IEEE
Trans. Pattern Anal. Machine Intell, vol. 21, pp. 348359, 1999..
[13] ] B.G. Sherlock, D.M. Monro, and K. Millard, “Fingerprint enhancement by directional fourier
filtering,” IEE Proc. Vision, Image Signal Process., vol. 141, pp. 8794., 1994.
[14] C.L. Wilson, G.T. Candela, and C.I. Watson, “Neural network fingerprint classification,” J. Artif.
Neural Networks, vol. 1, pp. 203228, 1994.
[15] S.C. Dass, “Markov random field models for directional field and singularity extraction in figerprint
images,” IEEE Trans. Image Process, vol. 13, pp. 13581367, 2004.
[16] Yi Wang, Jiankun Hu, and Fengling Han, “Enhanced gradient-based algo- rithm for the estimation of
fingerprint orientation fields,” Applied Mathe- matics and Computation, vol. 185, pp. 823833, 2007.
[17] Gottschlich C, P. Mihailescu, and A. Munk, “Robust orientation field es- timation and extrapolation
using semilocal line sensors,” IEEE Trans. Inf. Forensics Sec., vol. 4, pp. 802811, 2009.
[18] P. T. H. Truc, M. A. U. Khan, Y. K. Lee, and T. S. Kim, “Vessel enhancement filter using directional
filter bank,” Computer Vision and Image Understand- ing, vol. 113, pp. 101–112, 2009.
[19] A.K. Jain, S. Pankanti, and L. Hong, “A multichannel approach to fingerprint classification,” IEEE
Trans. Pattern Anal. Machine Intell, vol. 21, pp. 348359, 1999.
[20] Muhammad A. K. Khan and Wadee Alhalabi, “Robust multi-scale orienta- tion estimation: Spatial
domain vs fourier domain,” in International Confer- ence on Communications, Signal Processing, and
their Applications, 2013.
[21] Andres Almansa and Tony LIndeberg, “Fingerprint enhancement by shape adaption of scale)space
operators with automatic scale selection,” IEEE transaction on image processing, vol. 9, pp. 2027–
2041, 2000.
AUTHORS
Dr Yinan Kong
Dr Kong leads the VLSI Research Group at Macquarie. He is also currently the
Director of Higher Degree Research, Department of Engineering, Macquarie
University, Sydney, Australia. Dr Kong obtained his PhD from the University of
Adelaide, Australia. During his research at the VLSI Research Group at Macquarie
University and Centre for High Performance Integrated Technologies and Systems
(CHiPTec) at the University of Adelaide, Dr Kong focused on digital VLSI design at
an arithmetic level for specific applications like cryptography and DSP. He achieved
the hardware construction of a 1024-bit RSA cryptosystem at only 0.4 ms per
decryption, the fastest ever FPGA implementation of RSA. In the meantime, he
developed Bachelor Degree of Computer Engineering at Macquarie Engineering as well as postgraduate
teaching in embedded computer system design and computer arithmetic with hardware focused.
Tariq Mahmood Khan
Tariq Mahmmod Khan is interested in both Digital Image Processing (with an
emphasis on biometrics) and VLSI. He is currently involved in the hardware
implementation of multi-modal biometrics project, led by Yinan Kong. The main goal
of this project is to develop a fast processor for different design approaches. The aim is
to test these approaches on a multi-modal biometric system consisting fingerprint, iris
and face. Prior to starting his PhD in Engineering at Macquarie University, he received
a degree in BS Computer Engineering from COMSATS Institute of Information &
Technology, Islamabad Pakistan and MSc in Computer Engineering from University
of Engineering & Technology, Taxila Pakistan.