Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586755
B. Hamelin, Y. Goussard, J. Dussault
Numerical efficiency and convergence are matters of importance for regularized statistical reconstruction in X-ray tomography. We propose a performance comparison of four numerical methods that fall into two categories: first, variants of the SPS framework, a modern take on expectation-maximization-type algorithms, that benefit from acceleration through ordered subset strategies and were developed specifically for tomographic reconstruction; second, Hessian-free general-purpose nonlinear solvers with bound constraints, used to minimize directly the regularized objective function. The comparison is established on a common target for the noise-to-resolution trade-off of the reconstructed images. The experiments show that while the ordered-subsets separable paraboloidal surrogate iteration variant is the fastest to reach the target, its nonconvergent nature precludes the use of a rigorous stopping rule. Conversely, the other three methods are convergent and can be stopped using a common criterion related to the noise-to-resolution target. Among convergent techniques, general purpose solvers achieve the highest efficiency.
{"title":"Comparison of optimization techniques for regularized statistical reconstruction in X-ray tomography","authors":"B. Hamelin, Y. Goussard, J. Dussault","doi":"10.1109/IPTA.2010.5586755","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586755","url":null,"abstract":"Numerical efficiency and convergence are matters of importance for regularized statistical reconstruction in X-ray tomography. We propose a performance comparison of four numerical methods that fall into two categories: first, variants of the SPS framework, a modern take on expectation-maximization-type algorithms, that benefit from acceleration through ordered subset strategies and were developed specifically for tomographic reconstruction; second, Hessian-free general-purpose nonlinear solvers with bound constraints, used to minimize directly the regularized objective function. The comparison is established on a common target for the noise-to-resolution trade-off of the reconstructed images. The experiments show that while the ordered-subsets separable paraboloidal surrogate iteration variant is the fastest to reach the target, its nonconvergent nature precludes the use of a rigorous stopping rule. Conversely, the other three methods are convergent and can be stopped using a common criterion related to the noise-to-resolution target. Among convergent techniques, general purpose solvers achieve the highest efficiency.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129315009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586793
Marie Ploquin, J. Girault, D. Kouamé
In biomedical ultrasound imaging, there is a great need of high-resolved images for diagnosis or therapeutic purpose. This paper presents a resolution enhancement algorithm based both on Laplacian pyramid decomposition and on autoregressive (AR) model prediction. The idea is to use the Laplacian pyramid decomposition to estimate the high frequency (HF) image. Classically, after a bicubic-spline interpolation and a correction by an empirical control function, this HF image prediction is added to the bicubic-spline interpolated low frequency (LF) image. The resulting image is improved but the bicubic-spline interpolations tend to smooth the speckle. As a consequence, an empirical correction function based on the original image histogram has to be added to the HF image prediction. To face these issues, we propose an alternative to the bicubic-spline interpolation using an AR model instead. The resulting image is enhanced, and the empirical control function is not needed any more. Both methods are compared on synthetic images with different noise levels and distances to resolve. The resolution improvement was quantified in each case using a resolution criterion and the PSNR through the Monte-Carlo method. Then, the two methods are applied on an in vivo 20 MHz ultrasound image and the effectiveness of the proposed algorithm is shown.
{"title":"Laplacian pyramid decomposition-type method for resolution enhancement of ultrasound images","authors":"Marie Ploquin, J. Girault, D. Kouamé","doi":"10.1109/IPTA.2010.5586793","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586793","url":null,"abstract":"In biomedical ultrasound imaging, there is a great need of high-resolved images for diagnosis or therapeutic purpose. This paper presents a resolution enhancement algorithm based both on Laplacian pyramid decomposition and on autoregressive (AR) model prediction. The idea is to use the Laplacian pyramid decomposition to estimate the high frequency (HF) image. Classically, after a bicubic-spline interpolation and a correction by an empirical control function, this HF image prediction is added to the bicubic-spline interpolated low frequency (LF) image. The resulting image is improved but the bicubic-spline interpolations tend to smooth the speckle. As a consequence, an empirical correction function based on the original image histogram has to be added to the HF image prediction. To face these issues, we propose an alternative to the bicubic-spline interpolation using an AR model instead. The resulting image is enhanced, and the empirical control function is not needed any more. Both methods are compared on synthetic images with different noise levels and distances to resolve. The resolution improvement was quantified in each case using a resolution criterion and the PSNR through the Monte-Carlo method. Then, the two methods are applied on an in vivo 20 MHz ultrasound image and the effectiveness of the proposed algorithm is shown.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"526 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122708036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586783
Q. Pham, A. Lapeyronnie, C. Baudry, L. Lucat, P. Sayd, S. Ambellouis, D. Sodoyer, A. Flancquart, A.-C. Barcelo, F. Heer, F. Ganansia, V. Delcourt
Focusing on improving security in public transports (here: trains), this paper presents a research project implementing an audio-video surveillance system. Combining audio analysis, video tracking and dedicated integration of audio-video acquisition and storage equipments, the proposed system addresses the task of providing an operator with a partially-supervised tool for tracking suspected persons along the train.
{"title":"Audio-video surveillance system for public transportation","authors":"Q. Pham, A. Lapeyronnie, C. Baudry, L. Lucat, P. Sayd, S. Ambellouis, D. Sodoyer, A. Flancquart, A.-C. Barcelo, F. Heer, F. Ganansia, V. Delcourt","doi":"10.1109/IPTA.2010.5586783","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586783","url":null,"abstract":"Focusing on improving security in public transports (here: trains), this paper presents a research project implementing an audio-video surveillance system. Combining audio analysis, video tracking and dedicated integration of audio-video acquisition and storage equipments, the proposed system addresses the task of providing an operator with a partially-supervised tool for tracking suspected persons along the train.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"8 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114034548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586749
S. Sharif, Mohamed Deriche, N. Maalej
The deformable Geodesic Active Contour (GAC) method is one of the most important techniques used in object boundaries detection in images. In this work, we modify the automatic GAC technique by incorporating priori information extracted from the region of interest. We introduce a new stopping function to speed up convergence and improve accuracy. The proposed technique was applied to both synthetic and real medical images. We show an improvement in speed of more than 40% together with an excellent accuracy compared to the traditional GAC model.
{"title":"A fast Geodesic Active Contour model for medical images segmentation using prior analysis","authors":"S. Sharif, Mohamed Deriche, N. Maalej","doi":"10.1109/IPTA.2010.5586749","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586749","url":null,"abstract":"The deformable Geodesic Active Contour (GAC) method is one of the most important techniques used in object boundaries detection in images. In this work, we modify the automatic GAC technique by incorporating priori information extracted from the region of interest. We introduce a new stopping function to speed up convergence and improve accuracy. The proposed technique was applied to both synthetic and real medical images. We show an improvement in speed of more than 40% together with an excellent accuracy compared to the traditional GAC model.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128177702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586725
Changki Min, S. Jin, Hyeongchul Oh, Sang-Jun Park, Jechang Jeong
H.264/AVC is the newest one among several video compression standards. The main goals of H.264/AVC are to achieve efficient compression performance and a network friendly video coding. However, if an error occurs when transmitting compressed video, error concealment is needed to prevent error propagation and to improve the video quality. In this paper, we propose the temporal error concealment algorithm which provides high performance for H.264/AVC. The proposed algorithm uses the property that the motion vectors (MVs) between the error macroblock (MB) and the neighboring MB have high similarity to select a group of candidate MVs, when an error occurs in the inter-coded frame. Next, weighted overlapped boundary matching algorithm using the credibility of information selects the best candidate MV among a group of candidate MVs. The experimental results show that the proposed algorithm improves PSNR up to 3.02 dB compared with the boundary matching algorithm (BMA).
{"title":"Temporal error concealment algorithm for H.264/AVC using omnidirectional motion similarity","authors":"Changki Min, S. Jin, Hyeongchul Oh, Sang-Jun Park, Jechang Jeong","doi":"10.1109/IPTA.2010.5586725","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586725","url":null,"abstract":"H.264/AVC is the newest one among several video compression standards. The main goals of H.264/AVC are to achieve efficient compression performance and a network friendly video coding. However, if an error occurs when transmitting compressed video, error concealment is needed to prevent error propagation and to improve the video quality. In this paper, we propose the temporal error concealment algorithm which provides high performance for H.264/AVC. The proposed algorithm uses the property that the motion vectors (MVs) between the error macroblock (MB) and the neighboring MB have high similarity to select a group of candidate MVs, when an error occurs in the inter-coded frame. Next, weighted overlapped boundary matching algorithm using the credibility of information selects the best candidate MV among a group of candidate MVs. The experimental results show that the proposed algorithm improves PSNR up to 3.02 dB compared with the boundary matching algorithm (BMA).","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114339434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586790
Yann Ducrocq, Shahram Bahrami, L. Duvieubourg, F. Cabestaing
Humans have the capacity to move their eyes. Thanks to this capacity, they can orient their gaze to look at a relevant object inside a complex scene. In this paper, we have implemented a driver assistance application which tries to mimic this human capacity. We focus specially on highway driving situations, where the detection of obstacles must be done far away in front of the car. The implementation of the gaze control and orientation is obtained by an active vision system. We know that the human gaze is related to the visual attention which is a result of human perception and cognitive phenomenon. Several studies have shown that human perception and more specially the visual perception can be decomposed into a bottom-up process and a top-down process. Most of researches focused on the bottom-up process. In this work, in order to mimic the human behavior or at least improve vision systems, we use a new active stereovision setup and a model of the human visual perception based on the two previous approaches. Moreover, in a bottom-up approach, we add the depth information obtained with the stereoscopic sensor to the classical features used by other works. The top-down process is computed by the global knowledge of the scene and its features. Some results obtained by mean of a virtual road sequence, show the orientation of the field of view of the stereoscopic sensor toward relevant objects, given our criteria.
{"title":"A visual attention focusing system using an active stereoscopic vision sensor","authors":"Yann Ducrocq, Shahram Bahrami, L. Duvieubourg, F. Cabestaing","doi":"10.1109/IPTA.2010.5586790","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586790","url":null,"abstract":"Humans have the capacity to move their eyes. Thanks to this capacity, they can orient their gaze to look at a relevant object inside a complex scene. In this paper, we have implemented a driver assistance application which tries to mimic this human capacity. We focus specially on highway driving situations, where the detection of obstacles must be done far away in front of the car. The implementation of the gaze control and orientation is obtained by an active vision system. We know that the human gaze is related to the visual attention which is a result of human perception and cognitive phenomenon. Several studies have shown that human perception and more specially the visual perception can be decomposed into a bottom-up process and a top-down process. Most of researches focused on the bottom-up process. In this work, in order to mimic the human behavior or at least improve vision systems, we use a new active stereovision setup and a model of the human visual perception based on the two previous approaches. Moreover, in a bottom-up approach, we add the depth information obtained with the stereoscopic sensor to the classical features used by other works. The top-down process is computed by the global knowledge of the scene and its features. Some results obtained by mean of a virtual road sequence, show the orientation of the field of view of the stereoscopic sensor toward relevant objects, given our criteria.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132745191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586795
R. Khelifi, M. Adel, S. Bourennane
This paper deals with the development of a new texture analysis method based on both spatial and spectral information for texture classification purposes. The idea of Generalized Gray Level Difference Method (GGLDM) is to extend the concept of spatial Gray Level Difference Method(GLDM) by assuming texture joint information between spectral bands. In addition, new texture features measurement related to (GGLDM) which define the image properties have been also proposed. Extensive experiments have been carried out on many multi-spectral images for use in prostate cancer diagnosis and quantitative results showed the efficiency of this method compared to the Gray Level Difference Method (GLDM). The results indicate a significant improvement in classification accuracy.
{"title":"Texture classification for multi-spectral images using spatial and spectral Gray Level Differences","authors":"R. Khelifi, M. Adel, S. Bourennane","doi":"10.1109/IPTA.2010.5586795","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586795","url":null,"abstract":"This paper deals with the development of a new texture analysis method based on both spatial and spectral information for texture classification purposes. The idea of Generalized Gray Level Difference Method (GGLDM) is to extend the concept of spatial Gray Level Difference Method(GLDM) by assuming texture joint information between spectral bands. In addition, new texture features measurement related to (GGLDM) which define the image properties have been also proposed. Extensive experiments have been carried out on many multi-spectral images for use in prostate cancer diagnosis and quantitative results showed the efficiency of this method compared to the Gray Level Difference Method (GLDM). The results indicate a significant improvement in classification accuracy.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130225650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586797
L. Rossi, T. Molinier, M. Akhloufi, Y. Tison
This paper presents a stereovision framework developed to monitor and to measure laboratory fire spreads. New algorithms were developed for the estimation of fire characteristics like position, rate of spread, height, depth and the distance between the fire front and metrological instruments.
{"title":"Measurement of laboratory fire spread experiments by stereovision","authors":"L. Rossi, T. Molinier, M. Akhloufi, Y. Tison","doi":"10.1109/IPTA.2010.5586797","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586797","url":null,"abstract":"This paper presents a stereovision framework developed to monitor and to measure laboratory fire spreads. New algorithms were developed for the estimation of fire characteristics like position, rate of spread, height, depth and the distance between the fire front and metrological instruments.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114587139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586771
Fabian Lecron, M. Benjelloun, S. Mahmoudi
In this paper, we introduce a robust approach to detect points of interest in cervical spine radiographs. The perspective of this work is to segment the vertebrae on X-Ray images for the analysis of the vertebral mobility. In previous work, we proposed a segmentation technique based on Active Shape Model. The extraction and the detection of the vertebra corners can contribute to the automatic initialization of the Active Shape Model search and can give valuable information about the spine curvature. Here, we present the benefits of the polygonal approximation dedicated to the points of interest detection. The methodology developed here is composed of 3 stages: a contrast limited adaptive histogram equalization, a Canny edge detection filter and an edge polygonal approximation. The first histogram equalization step is a pretraitment needed to improve the image quality in order to perform a better contour detection. The Canny operator detects the edges in the radiograph which are used as an input to the polygonal approximation. The edges become segment lines whose intersections define corners. We compare the results obtained with our approach based on the polygonal approximation to results coming from the Harris corner detector.
{"title":"Points of interest detection in cervical spine radiographs by polygonal approximation","authors":"Fabian Lecron, M. Benjelloun, S. Mahmoudi","doi":"10.1109/IPTA.2010.5586771","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586771","url":null,"abstract":"In this paper, we introduce a robust approach to detect points of interest in cervical spine radiographs. The perspective of this work is to segment the vertebrae on X-Ray images for the analysis of the vertebral mobility. In previous work, we proposed a segmentation technique based on Active Shape Model. The extraction and the detection of the vertebra corners can contribute to the automatic initialization of the Active Shape Model search and can give valuable information about the spine curvature. Here, we present the benefits of the polygonal approximation dedicated to the points of interest detection. The methodology developed here is composed of 3 stages: a contrast limited adaptive histogram equalization, a Canny edge detection filter and an edge polygonal approximation. The first histogram equalization step is a pretraitment needed to improve the image quality in order to perform a better contour detection. The Canny operator detects the edges in the radiograph which are used as an input to the polygonal approximation. The edges become segment lines whose intersections define corners. We compare the results obtained with our approach based on the polygonal approximation to results coming from the Harris corner detector.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124013386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586828
F. Dufaux
This presentation surveys the current status of research activities on Distributed Video Coding (DVC). In particular, we review some recent contributions, identify challenges ahead, and outline perspectives.
{"title":"Distributed Video Coding: Status, challenges and outlook","authors":"F. Dufaux","doi":"10.1109/IPTA.2010.5586828","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586828","url":null,"abstract":"This presentation surveys the current status of research activities on Distributed Video Coding (DVC). In particular, we review some recent contributions, identify challenges ahead, and outline perspectives.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126525210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：