Pub Date : 2016-09-25DOI: 10.1109/ICIP.2016.7533022
S. Roux, P. Abry, B. Vedel, S. Jaffard, H. Wendt
Scale invariance has proven a crucial concept in texture modeling and analysis. Isotropic and self-similar fractional Brownian fields (2D-fBf) are often used as the natural reference process to model scale free textures. Its analysis is standardly conducted using the 2D discrete wavelet transform. Generalizations of 2D-fBf were considered independently in two respects: Anisotropy in the texture is allowed while preserving exact self-similarity, analysis then needs to be conducted using the 2D-Hyperbolic wavelet transform; Multifractality enables more versatile scale free models but requires isotropy, analysis is then achieved using wavelet leaders. The present paper proposes a first unifying extension, which is enabled through the following two key contributions: The definition of 2D process that incorporates jointly anisotropy and multi-fractality : The definition of the corresponding analysis tool, the hyperbolic wavelet leaders. Their relevance are studied by numerical simulations using synthetic scale free textures.
{"title":"Hyperbolic wavelet leaders for anisotropic multifractal texture analysis","authors":"S. Roux, P. Abry, B. Vedel, S. Jaffard, H. Wendt","doi":"10.1109/ICIP.2016.7533022","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7533022","url":null,"abstract":"Scale invariance has proven a crucial concept in texture modeling and analysis. Isotropic and self-similar fractional Brownian fields (2D-fBf) are often used as the natural reference process to model scale free textures. Its analysis is standardly conducted using the 2D discrete wavelet transform. Generalizations of 2D-fBf were considered independently in two respects: Anisotropy in the texture is allowed while preserving exact self-similarity, analysis then needs to be conducted using the 2D-Hyperbolic wavelet transform; Multifractality enables more versatile scale free models but requires isotropy, analysis is then achieved using wavelet leaders. The present paper proposes a first unifying extension, which is enabled through the following two key contributions: The definition of 2D process that incorporates jointly anisotropy and multi-fractality : The definition of the corresponding analysis tool, the hyperbolic wavelet leaders. Their relevance are studied by numerical simulations using synthetic scale free textures.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"49 1","pages":"3558-3562"},"PeriodicalIF":0.0,"publicationDate":"2016-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85398767","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 : 2016-09-25DOI: 10.1109/ICIP.2016.7533100
T. Theodoridis, A. Tefas, I. Pitas
In this work, we propose a multi-view temporal video segmentation approach that employs a Gaussian scoring process for determining the best segmentation positions. By exploiting the semantic action information that the dense trajectories video description offers, this method can detect intra-shot actions as well, unlike shot boundary detection approaches. We compare the temporal segmentation results of the proposed method to both single-view and multi-view methods, and also compare the action recognition results obtained on ground truth video segments to the ones obtained on the proposed multi-view segments, on the IMPART multi-view action data set.
{"title":"Multi-view semantic temporal video segmentation","authors":"T. Theodoridis, A. Tefas, I. Pitas","doi":"10.1109/ICIP.2016.7533100","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7533100","url":null,"abstract":"In this work, we propose a multi-view temporal video segmentation approach that employs a Gaussian scoring process for determining the best segmentation positions. By exploiting the semantic action information that the dense trajectories video description offers, this method can detect intra-shot actions as well, unlike shot boundary detection approaches. We compare the temporal segmentation results of the proposed method to both single-view and multi-view methods, and also compare the action recognition results obtained on ground truth video segments to the ones obtained on the proposed multi-view segments, on the IMPART multi-view action data set.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"25 1","pages":"3947-3951"},"PeriodicalIF":0.0,"publicationDate":"2016-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89304766","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 : 2016-09-25DOI: 10.1109/ICIP.2016.7533151
Martin Alain, C. Guillemot, D. Thoreau, P. Guillotel
This paper describes a novel scheme to reduce the quantization noise of compressed videos and improve the overall coding performances. The proposed scheme first consists in clustering noisy patches of the compressed sequence. Then, at the encoder side, linear mappings are learned for each cluster between the noisy patches and the corresponding source patches. The linear mappings are then transmitted to the decoder where they can be applied to perform de-noising. The method has been tested with the HEVC standard, leading to a bitrate saving of up to 9.63%.
{"title":"Learning clustering-based linear mappings for quantization noise removal","authors":"Martin Alain, C. Guillemot, D. Thoreau, P. Guillotel","doi":"10.1109/ICIP.2016.7533151","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7533151","url":null,"abstract":"This paper describes a novel scheme to reduce the quantization noise of compressed videos and improve the overall coding performances. The proposed scheme first consists in clustering noisy patches of the compressed sequence. Then, at the encoder side, linear mappings are learned for each cluster between the noisy patches and the corresponding source patches. The linear mappings are then transmitted to the decoder where they can be applied to perform de-noising. The method has been tested with the HEVC standard, leading to a bitrate saving of up to 9.63%.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"1 1","pages":"4200-4204"},"PeriodicalIF":0.0,"publicationDate":"2016-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86184540","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 : 2016-09-25DOI: 10.1109/ICIP.2016.7532766
J. Pasquet, M. Chaumont, G. Subsol, Mustapha Derras
Deep neural networks yield positive object detection results in aerial imaging. To deal with the massive computational time required, we propose to connect an SVM Network to the different feature maps of a CNN. After the training of this SVM Network, we use an activation path to cross the network in a predefined order. We stop the crossing as quickly as possible. This early exit from the CNN allows us to reduce the computational burden. Experimental results are obtained for an industrial application in urban object detection. We show that potentially the computation cost could be reduced by 98%. Additionally, performance is slightly improved; for example, for a 55% recall, precision increases by 5%.
{"title":"Speeding-up a convolutional neural network by connecting an SVM network","authors":"J. Pasquet, M. Chaumont, G. Subsol, Mustapha Derras","doi":"10.1109/ICIP.2016.7532766","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7532766","url":null,"abstract":"Deep neural networks yield positive object detection results in aerial imaging. To deal with the massive computational time required, we propose to connect an SVM Network to the different feature maps of a CNN. After the training of this SVM Network, we use an activation path to cross the network in a predefined order. We stop the crossing as quickly as possible. This early exit from the CNN allows us to reduce the computational burden. Experimental results are obtained for an industrial application in urban object detection. We show that potentially the computation cost could be reduced by 98%. Additionally, performance is slightly improved; for example, for a 55% recall, precision increases by 5%.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"18 1","pages":"2286-2290"},"PeriodicalIF":0.0,"publicationDate":"2016-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76357481","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 : 2016-09-25DOI: 10.1109/ICIP.2016.7532750
J. Xia, L. Bombrun, Y. Berthoumieu, C. Germain
Images are usually represented by different groups of features, such as color, shape and texture attributes. In this paper, we propose a classification approach that integrates multiple features, such as spectral and spatial information. We refer this approach to multiple feature learning via rotation (MFL-R) strategy, which adopt a rotation-based ensemble method by using a data transformation approach. Five data transformation methods, including principal component analysis (PCA), neighborhood preserving embedding (NPE), linear local tangent space alignment (LLTSA), linearity preserving projection (LPP) and multiple feature combination via manifold learning and patch alignment (MLPA) are used in the MFL-R framework. Experimental results over two hyperspectral remote sensing images demonstrate that MFL-R with MLPA gains better performances and is not sensitive to the tuning parameters.
{"title":"Multiple features learning via rotation strategy","authors":"J. Xia, L. Bombrun, Y. Berthoumieu, C. Germain","doi":"10.1109/ICIP.2016.7532750","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7532750","url":null,"abstract":"Images are usually represented by different groups of features, such as color, shape and texture attributes. In this paper, we propose a classification approach that integrates multiple features, such as spectral and spatial information. We refer this approach to multiple feature learning via rotation (MFL-R) strategy, which adopt a rotation-based ensemble method by using a data transformation approach. Five data transformation methods, including principal component analysis (PCA), neighborhood preserving embedding (NPE), linear local tangent space alignment (LLTSA), linearity preserving projection (LPP) and multiple feature combination via manifold learning and patch alignment (MLPA) are used in the MFL-R framework. Experimental results over two hyperspectral remote sensing images demonstrate that MFL-R with MLPA gains better performances and is not sensitive to the tuning parameters.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"9 6 1","pages":"2206-2210"},"PeriodicalIF":0.0,"publicationDate":"2016-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86449357","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 : 2016-09-25DOI: 10.1109/ICIP.2016.7532511
Yu Fan, M. Larabi, F. A. Cheikh, C. Fernandez-Maloigne
The just noticeable difference (JND) notion reflects the maximum tolerable distortion. It has been extensively used for the optimization of 2D applications. For stereoscopic 3D (S3D) content, this notion is different since it relies on different mechanisms linked to our binocular vision. Unlike 2D, 3D-JND models appeared recently and the related literature is rather limited. These models can be used for the sake of compression and quality assessment improvement for S3D content. In this paper, we propose a deep and comparative study of the existing 3D-JND models. Additionally, in order to analyze their performance, the 3D-JND models have been integrated in recent metric dedicated to stereoscopic image quality assessment (SIQA). The results are reported on two widely used S3D image databases.
{"title":"On the performance of 3D just noticeable difference models","authors":"Yu Fan, M. Larabi, F. A. Cheikh, C. Fernandez-Maloigne","doi":"10.1109/ICIP.2016.7532511","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7532511","url":null,"abstract":"The just noticeable difference (JND) notion reflects the maximum tolerable distortion. It has been extensively used for the optimization of 2D applications. For stereoscopic 3D (S3D) content, this notion is different since it relies on different mechanisms linked to our binocular vision. Unlike 2D, 3D-JND models appeared recently and the related literature is rather limited. These models can be used for the sake of compression and quality assessment improvement for S3D content. In this paper, we propose a deep and comparative study of the existing 3D-JND models. Additionally, in order to analyze their performance, the 3D-JND models have been integrated in recent metric dedicated to stereoscopic image quality assessment (SIQA). The results are reported on two widely used S3D image databases.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"95 1","pages":"1017-1021"},"PeriodicalIF":0.0,"publicationDate":"2016-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83183427","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 : 2016-09-25DOI: 10.1109/ICIP.2016.7533160
Sami Jaballah, M. Larabi, J. B. Tahar
In this paper, we present a novel perceptually-based optimization for the improvement of stereoscopic video coding efficiency. The main idea of this proposed scheme is to adaptively adjust the quantization parameter by taking into account the Human Visual System perceptual characteristics. For this, a saliency map is generated from both views and then segmented into salient and non-salient regions. To make the proposed scheme effective, and inspired from the binocular suppression theory, the asymmetry is ensured by altering the saliency map and not the view. As a result, the proposed perceptual coding scheme effectively reduces the bit-budget without affecting the perceptual quality based on an optimization approach with asymmetric video coding taking into account the saliency map of each view. Experimental results on HEVC-MV show that the proposed algorithm can achieve over 20% bit-rate saving while preserving the perceived image quality.
{"title":"Perceptually-adaptive quantization for stereoscopic video coding","authors":"Sami Jaballah, M. Larabi, J. B. Tahar","doi":"10.1109/ICIP.2016.7533160","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7533160","url":null,"abstract":"In this paper, we present a novel perceptually-based optimization for the improvement of stereoscopic video coding efficiency. The main idea of this proposed scheme is to adaptively adjust the quantization parameter by taking into account the Human Visual System perceptual characteristics. For this, a saliency map is generated from both views and then segmented into salient and non-salient regions. To make the proposed scheme effective, and inspired from the binocular suppression theory, the asymmetry is ensured by altering the saliency map and not the view. As a result, the proposed perceptual coding scheme effectively reduces the bit-budget without affecting the perceptual quality based on an optimization approach with asymmetric video coding taking into account the saliency map of each view. Experimental results on HEVC-MV show that the proposed algorithm can achieve over 20% bit-rate saving while preserving the perceived image quality.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"33 1","pages":"4245-4249"},"PeriodicalIF":0.0,"publicationDate":"2016-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80336014","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 : 2016-09-25DOI: 10.1109/ICIP.2016.7533019
Ioana Ilea, L. Bombrun, C. Germain, R. Terebeș, M. Borda, Y. Berthoumieu
This paper introduces a generalization of the Fisher vectors to the Riemannian manifold. The proposed descriptors, called Riemannian Fisher vectors, are defined first, based on the mixture model of Riemannian Gaussian distributions. Next, their expressions are derived and they are applied in the context of texture image classification. The results are compared to those given by the recently proposed algorithms, bag of Riemannian words and R-VLAD. In addition, the most discriminant Riemannian Fisher vectors are identified.
{"title":"Texture image classification with Riemannian fisher vectors","authors":"Ioana Ilea, L. Bombrun, C. Germain, R. Terebeș, M. Borda, Y. Berthoumieu","doi":"10.1109/ICIP.2016.7533019","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7533019","url":null,"abstract":"This paper introduces a generalization of the Fisher vectors to the Riemannian manifold. The proposed descriptors, called Riemannian Fisher vectors, are defined first, based on the mixture model of Riemannian Gaussian distributions. Next, their expressions are derived and they are applied in the context of texture image classification. The results are compared to those given by the recently proposed algorithms, bag of Riemannian words and R-VLAD. In addition, the most discriminant Riemannian Fisher vectors are identified.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"16 1","pages":"3543-3547"},"PeriodicalIF":0.0,"publicationDate":"2016-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91216307","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 : 2016-09-01DOI: 10.1109/ICIP.2016.7532879
Jorge Batista, K. Krakowski, Luís Machado, P. Martins, F. Leite
Manifold-based domain adaptation algorithms are receiving increasing attention in computer vision to model distribution shifts between source and target domain. In contrast to early works, that mainly explore intermediate subspaces along geodesics, in this work we propose to interpolate subspaces through C1-smooth curves on the Grassmann manifold. The new methodis based on the geometric Casteljau algorithm that is used to generate smooth interpolating polynomial curves on non-euclidean spaces and can be extended to generate polynomial splines that interpolate a given set of data on the Grassmann manifold. To evaluate the usefulness of the proposed interpolating curves on vision related problems, several experiments were conducted. We show the advantage of using smooth subspaces interpolation in multi-source unsupervised domain adaptation problems and in object recognition problems across datasets.
{"title":"Multi-source domain adaptation using C⁁1-smooth subspaces interpolation","authors":"Jorge Batista, K. Krakowski, Luís Machado, P. Martins, F. Leite","doi":"10.1109/ICIP.2016.7532879","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7532879","url":null,"abstract":"Manifold-based domain adaptation algorithms are receiving increasing attention in computer vision to model distribution shifts between source and target domain. In contrast to early works, that mainly explore intermediate subspaces along geodesics, in this work we propose to interpolate subspaces through C1-smooth curves on the Grassmann manifold. The new methodis based on the geometric Casteljau algorithm that is used to generate smooth interpolating polynomial curves on non-euclidean spaces and can be extended to generate polynomial splines that interpolate a given set of data on the Grassmann manifold. To evaluate the usefulness of the proposed interpolating curves on vision related problems, several experiments were conducted. We show the advantage of using smooth subspaces interpolation in multi-source unsupervised domain adaptation problems and in object recognition problems across datasets.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"1 1","pages":"2846-2850"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75870341","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 : 2016-09-01DOI: 10.1109/ICIP.2016.7532946
D. Svoboda, V. Ulman, Peter Kovác, B. Salingova, L. Tesarová, I. Koutná, P. Matula
Cardiovascular diseases belong to the most widespread illnesses in the developed countries. Therefore, the regenerative medicine and tissue modeling applications are highly interested in studying the ability of endothelial cells, derived from human stem cells, to form vascular networks. Several characteristics can be measured on images of these networks and hence describe the quality of the endothelial cells. With advances in the image processing, automatic analysis of these complex images becomes increasingly common. In this study, we introduce a new graph structure and additional constraints to the cellular Potts model, a framework commonly utilized in computational biology. Our extension allows to generate visually plausible synthetic image sequences of evolving fluorescently labeled vascular networks with ground truth data. Such generated datasets can be subsequently used for testing and validating methods employed for the analysis and measurement of the images of real vascular networks.
{"title":"Vascular network formation in silico using the extended cellular potts model","authors":"D. Svoboda, V. Ulman, Peter Kovác, B. Salingova, L. Tesarová, I. Koutná, P. Matula","doi":"10.1109/ICIP.2016.7532946","DOIUrl":"https://doi.org/10.1109/ICIP.2016.7532946","url":null,"abstract":"Cardiovascular diseases belong to the most widespread illnesses in the developed countries. Therefore, the regenerative medicine and tissue modeling applications are highly interested in studying the ability of endothelial cells, derived from human stem cells, to form vascular networks. Several characteristics can be measured on images of these networks and hence describe the quality of the endothelial cells. With advances in the image processing, automatic analysis of these complex images becomes increasingly common. In this study, we introduce a new graph structure and additional constraints to the cellular Potts model, a framework commonly utilized in computational biology. Our extension allows to generate visually plausible synthetic image sequences of evolving fluorescently labeled vascular networks with ground truth data. Such generated datasets can be subsequently used for testing and validating methods employed for the analysis and measurement of the images of real vascular networks.","PeriodicalId":6521,"journal":{"name":"2016 IEEE International Conference on Image Processing (ICIP)","volume":"158 1","pages":"3180-3183"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75113460","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：