Pub Date : 2008-11-01DOI: 10.1109/IPTA.2008.4743742
A. Ouahabi, S. Jaffard, D. A. Aouit
In this paper, we propose a new method to identify three typically fracture surface morphologies based upon image analysis. The image is characterized via its multifractal spectrum, which mode yields the most frequent Holder exponent. Moreover, we recall the properties of several multifractal formalisms based on wavelet coefficients. In this context, we compare mathematically multifractal formalisms based on the wavelet transform modulus maxima approach and a new multifractal formalism based on wavelet leaders. It is shown that they compare very favourably to those obtained by wavelet coefficient based ones. Moreover, a practical extension to two dimensional signals (images) is validated. We illustrate this paper by some applications in fractography.
{"title":"Wavelet based Multifractal Analysis in Fractography","authors":"A. Ouahabi, S. Jaffard, D. A. Aouit","doi":"10.1109/IPTA.2008.4743742","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743742","url":null,"abstract":"In this paper, we propose a new method to identify three typically fracture surface morphologies based upon image analysis. The image is characterized via its multifractal spectrum, which mode yields the most frequent Holder exponent. Moreover, we recall the properties of several multifractal formalisms based on wavelet coefficients. In this context, we compare mathematically multifractal formalisms based on the wavelet transform modulus maxima approach and a new multifractal formalism based on wavelet leaders. It is shown that they compare very favourably to those obtained by wavelet coefficient based ones. Moreover, a practical extension to two dimensional signals (images) is validated. We illustrate this paper by some applications in fractography.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123432260","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743744
F. Tensaouti, M. Delion, J. Lotterie, P. Clarisse, I. Berry
Diffusion Tensor Imaging (DTI) and tractography are able to model fiber architecture within the white matter. In the laboratory, we developped a software Sisyphe, which is an integrated environment for neuroimaging post-processing and visualization. In this work, we extend this tool to further incorporate white matter DTI fiber tracking. We evaluate the reproducibility and reliability of our algorithm by studying the pyramidal tract.
{"title":"Reproducibility and reliability of the DTI fiber tracking algorithm integrated in the Sisyphe software","authors":"F. Tensaouti, M. Delion, J. Lotterie, P. Clarisse, I. Berry","doi":"10.1109/IPTA.2008.4743744","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743744","url":null,"abstract":"Diffusion Tensor Imaging (DTI) and tractography are able to model fiber architecture within the white matter. In the laboratory, we developped a software Sisyphe, which is an integrated environment for neuroimaging post-processing and visualization. In this work, we extend this tool to further incorporate white matter DTI fiber tracking. We evaluate the reproducibility and reliability of our algorithm by studying the pyramidal tract.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131089852","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743780
A. Porebski, N. Vandenbroucke, L. Macaire
In this paper, we present a new approach for color texture classification by use of Haralick features extracted from co-occurrence matrices computed from local binary pattern (LBP) images. These LBP images, which are different from the color LBP initially proposed by Maenpaa and Pietikainen, are extracted from color texture images, which are coded in 28 different color spaces. An iterative procedure then selects among the extracted features, those which discriminate the textures, in order to build a low dimensional feature space. Experimental results, achieved with the BarkTex database, show the interest of this method with which a satisfying rate of well-classified images (85.6%) is obtained, with a 10-dimensional feature space.
{"title":"Haralick feature extraction from LBP images for color texture classification","authors":"A. Porebski, N. Vandenbroucke, L. Macaire","doi":"10.1109/IPTA.2008.4743780","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743780","url":null,"abstract":"In this paper, we present a new approach for color texture classification by use of Haralick features extracted from co-occurrence matrices computed from local binary pattern (LBP) images. These LBP images, which are different from the color LBP initially proposed by Maenpaa and Pietikainen, are extracted from color texture images, which are coded in 28 different color spaces. An iterative procedure then selects among the extracted features, those which discriminate the textures, in order to build a low dimensional feature space. Experimental results, achieved with the BarkTex database, show the interest of this method with which a satisfying rate of well-classified images (85.6%) is obtained, with a 10-dimensional feature space.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114365230","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743764
P. Lenkiewicz, M. Pereira, M. Freire, J. Fernandes
Digital processing of medical images has helped physicians and patients during past years by allowing examination and diagnosis on a very precise level. Nowadays possibly the biggest deal of support it can offer for modern healthcare is the use of high performance computing architectures to treat the huge amounts of data that can be collected by modern acquisition devices. This paper presents a parallel processing implementation of an image segmentation algorithm that operates on a computer cluster equipped with 10 processing units. Thanks to well-organized distribution of the workload we manage to significantly shorten the execution time of the developed algorithm and reach a performance gain very close to linear.
{"title":"Accelerating 3D Medical Image Segmentation with High Performance Computing","authors":"P. Lenkiewicz, M. Pereira, M. Freire, J. Fernandes","doi":"10.1109/IPTA.2008.4743764","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743764","url":null,"abstract":"Digital processing of medical images has helped physicians and patients during past years by allowing examination and diagnosis on a very precise level. Nowadays possibly the biggest deal of support it can offer for modern healthcare is the use of high performance computing architectures to treat the huge amounts of data that can be collected by modern acquisition devices. This paper presents a parallel processing implementation of an image segmentation algorithm that operates on a computer cluster equipped with 10 processing units. Thanks to well-organized distribution of the workload we manage to significantly shorten the execution time of the developed algorithm and reach a performance gain very close to linear.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122514426","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743738
R. Kachouri, K. Djemal, H. Maaref, D. Masmoudi, Nabil Derbel
Content-based image retrieval (CBIR) techniques are becoming increasingly important in various fields. One of the most important steps in CBIR systems is feature extraction. However, using not appropriate features in heterogeneous image database during retrieval process does not provide a complete description of an image. Indeed, each feature is able to describe some characteristics related to the shape, the color or the texture of the objects in image, but it can not cover the entire visual characteristics of the image. Therefore, many researchers have explored the use of multiple features to describe an image. In this paper, we propose the extraction and the relevance evaluation of several features for an heterogeneous image database classification and recognition, then we study the image retrieval system effectiveness with a new hierarchical feature model. The obtained results prove that using the new hierarchical feature model is more efficient than the use of the classical aggregated features in an image retrieval system.
{"title":"Feature extraction and relevance evaluation for heterogeneous image database recognition","authors":"R. Kachouri, K. Djemal, H. Maaref, D. Masmoudi, Nabil Derbel","doi":"10.1109/IPTA.2008.4743738","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743738","url":null,"abstract":"Content-based image retrieval (CBIR) techniques are becoming increasingly important in various fields. One of the most important steps in CBIR systems is feature extraction. However, using not appropriate features in heterogeneous image database during retrieval process does not provide a complete description of an image. Indeed, each feature is able to describe some characteristics related to the shape, the color or the texture of the objects in image, but it can not cover the entire visual characteristics of the image. Therefore, many researchers have explored the use of multiple features to describe an image. In this paper, we propose the extraction and the relevance evaluation of several features for an heterogeneous image database classification and recognition, then we study the image retrieval system effectiveness with a new hierarchical feature model. The obtained results prove that using the new hierarchical feature model is more efficient than the use of the classical aggregated features in an image retrieval system.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129575823","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743762
Jonghyun Park, Wanhyun Cho, Sun-Worl Kim, Soonyoung Park, Myungeun Lee, C. Jeong, Junsik Lim, Gueesang Lee
A novel image registration algorithm that uses two kinds of information is presented: One kind is the shape information of an object and the other kind is the intensity information of a voxel and its neighborhoods consisting of the object. We, first, segment the medical volume data using the Markov random field model and the ICM algorithm and extract the surface region of the object from a segmented volume data. Second, we use the hidden labeling variables and likelihood method to statistically model the intensity distribution of each voxel at the surface region. We adopt the Bernoulli probability model to formulate a prior distribution of the labeling variable for the transformed voxels. The Gaussian mixture model is taken as a probability distribution function for the intensity of the transformed voxel. We use the EM algorithm to get the proper estimators for the parameters of the complete-data log likelihood function. The EM algorithm consists of two steps: the E-step and M-step. In the E-step, we compute the posterior distribution of the labeling variable by taking the expectation for the log-likelihood function. Next, we drive the estimators for all of the parameters by maximizing this function iteratively in the M-step. Then, we define a new registration measure with the Q-function obtained by the EM algorithm. We evaluate the precision of the proposed approach by comparing the registration traces of the Q- function obtained from the original image and its transformed image with respect to x-translation and rotation. The experimental results show that our method has great potential power to register various medical images given by different modalities.
{"title":"Image Registration using Bayes Theory and a Maximum Likelihood Framework with an EM Algorithm","authors":"Jonghyun Park, Wanhyun Cho, Sun-Worl Kim, Soonyoung Park, Myungeun Lee, C. Jeong, Junsik Lim, Gueesang Lee","doi":"10.1109/IPTA.2008.4743762","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743762","url":null,"abstract":"A novel image registration algorithm that uses two kinds of information is presented: One kind is the shape information of an object and the other kind is the intensity information of a voxel and its neighborhoods consisting of the object. We, first, segment the medical volume data using the Markov random field model and the ICM algorithm and extract the surface region of the object from a segmented volume data. Second, we use the hidden labeling variables and likelihood method to statistically model the intensity distribution of each voxel at the surface region. We adopt the Bernoulli probability model to formulate a prior distribution of the labeling variable for the transformed voxels. The Gaussian mixture model is taken as a probability distribution function for the intensity of the transformed voxel. We use the EM algorithm to get the proper estimators for the parameters of the complete-data log likelihood function. The EM algorithm consists of two steps: the E-step and M-step. In the E-step, we compute the posterior distribution of the labeling variable by taking the expectation for the log-likelihood function. Next, we drive the estimators for all of the parameters by maximizing this function iteratively in the M-step. Then, we define a new registration measure with the Q-function obtained by the EM algorithm. We evaluate the precision of the proposed approach by comparing the registration traces of the Q- function obtained from the original image and its transformed image with respect to x-translation and rotation. The experimental results show that our method has great potential power to register various medical images given by different modalities.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127372796","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743783
A. Faro, D. Giordano, G. Scarciofalo, C. Spampinato
In this paper we propose a two-step filter for removing salt-and-pepper impulse noise. In the first phase, a Naive Bayesian network is used to identify pixels, which are likely to be contaminated by noise (noise candidates). In the second phase, the noisy pixels are restored according to a regularization method (based on the optimization of a convex functional) to apply only to those selected noise candidates. The proposed method shows a significant improvement compared to other non linear filters or regularization methods in terms of image details preservation and noise reduction. Our algorithm is also able to remove salt-and-pepper-noise with high noise levels since 70% until 90%.
{"title":"Bayesian Networks for Edge Preserving Salt and Pepper Image Denoising","authors":"A. Faro, D. Giordano, G. Scarciofalo, C. Spampinato","doi":"10.1109/IPTA.2008.4743783","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743783","url":null,"abstract":"In this paper we propose a two-step filter for removing salt-and-pepper impulse noise. In the first phase, a Naive Bayesian network is used to identify pixels, which are likely to be contaminated by noise (noise candidates). In the second phase, the noisy pixels are restored according to a regularization method (based on the optimization of a convex functional) to apply only to those selected noise candidates. The proposed method shows a significant improvement compared to other non linear filters or regularization methods in terms of image details preservation and noise reduction. Our algorithm is also able to remove salt-and-pepper-noise with high noise levels since 70% until 90%.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132415249","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 : 2008-11-01DOI: 10.1109/ipta.2008.4743751
I. Cheikhrouhou, K. Djemal, D. Sellami, H. Maaref, N. Derbel
In this article, we present a new mass description dedicated to differentiate between different mass shapes in mammography. This discrimination aims to reach a better mammography classification rate to be used by radiologists as a second opinion to make the final decision about the malignancy probability of radiographic breast images. Therefore, we used a geometrical feature which is perimeter measurement (P) and 3 morphological features which focus on mass borders by discriminating circumscribed from spiculated shapes. These features are: contour derivative variation (CDV), skeleton end points (SEP) and we propose a new one noted Spiculation (SPICUL). Their performance were evaluated one by one before collecting them for mammography classification into the 4 BIRADS categories. For classification, we used support vector machine (SVM) with Gaussian kernel as classifier for its higher performance. The accuracy of our model with contour features for classifying malignancies was 93% in the case of two class model (malignant and benign) and 85.7% in the 4 class model (BIRADS I,II,III and IV).
{"title":"New mass description in mammographies","authors":"I. Cheikhrouhou, K. Djemal, D. Sellami, H. Maaref, N. Derbel","doi":"10.1109/ipta.2008.4743751","DOIUrl":"https://doi.org/10.1109/ipta.2008.4743751","url":null,"abstract":"In this article, we present a new mass description dedicated to differentiate between different mass shapes in mammography. This discrimination aims to reach a better mammography classification rate to be used by radiologists as a second opinion to make the final decision about the malignancy probability of radiographic breast images. Therefore, we used a geometrical feature which is perimeter measurement (P) and 3 morphological features which focus on mass borders by discriminating circumscribed from spiculated shapes. These features are: contour derivative variation (CDV), skeleton end points (SEP) and we propose a new one noted Spiculation (SPICUL). Their performance were evaluated one by one before collecting them for mammography classification into the 4 BIRADS categories. For classification, we used support vector machine (SVM) with Gaussian kernel as classifier for its higher performance. The accuracy of our model with contour features for classifying malignancies was 93% in the case of two class model (malignant and benign) and 85.7% in the 4 class model (BIRADS I,II,III and IV).","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131085720","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743791
S. Bourouis, K. Hamrouni
The main objective of this paper is to provide an efficient tool for delineating brain tumors in three-dimensional magnetic resonance images. To achieve this goal, we use basically a region-based level-set approach and some conventional methods. Our proposed approach produces good results and decreases processing time. We present here the main stages of our system, and preliminary results which are very encouraging for clinical practice.
{"title":"An Efficient Framework for Brain Tumor Segmentation in Magnetic Resonance Images","authors":"S. Bourouis, K. Hamrouni","doi":"10.1109/IPTA.2008.4743791","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743791","url":null,"abstract":"The main objective of this paper is to provide an efficient tool for delineating brain tumors in three-dimensional magnetic resonance images. To achieve this goal, we use basically a region-based level-set approach and some conventional methods. Our proposed approach produces good results and decreases processing time. We present here the main stages of our system, and preliminary results which are very encouraging for clinical practice.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134208907","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 : 2008-11-01DOI: 10.1109/IPTA.2008.4743774
N. Cheaib, S. Otmane, K. Djemal, M. Mallem
In this paper, we present a groupware model that is based on the integration of Web services technologies with software agents. The purpose is to design a collaborative environment in the context of CAD (computer-aided diagnosis), enabling doctors to collaborate together in order to achieve a proper diagnosis of patients' files, and this by dynamically integrating new functionalities as Web services into their application, without stopping the diagnosis process, and hence achieving an efficient treatment. Our work is motivated by the fact that a collaborative and dynamic system is still missing in the hospitalization environment, where very few work in the literature has been done that aims to tailor the services by end-users for a better diagnosis process. We apply our model on the health care domain by providing a tailorable collaborative computer aided diagnosis.
{"title":"Groupware Design for Online Diagnosis Support","authors":"N. Cheaib, S. Otmane, K. Djemal, M. Mallem","doi":"10.1109/IPTA.2008.4743774","DOIUrl":"https://doi.org/10.1109/IPTA.2008.4743774","url":null,"abstract":"In this paper, we present a groupware model that is based on the integration of Web services technologies with software agents. The purpose is to design a collaborative environment in the context of CAD (computer-aided diagnosis), enabling doctors to collaborate together in order to achieve a proper diagnosis of patients' files, and this by dynamically integrating new functionalities as Web services into their application, without stopping the diagnosis process, and hence achieving an efficient treatment. Our work is motivated by the fact that a collaborative and dynamic system is still missing in the hospitalization environment, where very few work in the literature has been done that aims to tailor the services by end-users for a better diagnosis process. We apply our model on the health care domain by providing a tailorable collaborative computer aided diagnosis.","PeriodicalId":384072,"journal":{"name":"2008 First Workshops on Image Processing Theory, Tools and Applications","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132972338","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：