Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.784964
M. Werman, D. Keren
We offer a simple paradigm for fitting models, parametric and non-parametric, to noisy data, which resolves some of the problems associated with classic MSE algorithms. This is done by considering each point on the model as a possible source for each data point. The paradigm also allows to solve problems which are not defined in the classical MSE approach, such as fitting a segment (as opposed to a line). It is shown to be non-biased, and to achieve excellent results for general curves, even in the presence of strong discontinuities. Results are shown for a number of fitting problems, including lines, circles, segments, and general curves, contaminated by Gaussian and uniform noise.
{"title":"A novel Bayesian method for fitting parametric and non-parametric models to noisy data","authors":"M. Werman, D. Keren","doi":"10.1109/CVPR.1999.784964","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784964","url":null,"abstract":"We offer a simple paradigm for fitting models, parametric and non-parametric, to noisy data, which resolves some of the problems associated with classic MSE algorithms. This is done by considering each point on the model as a possible source for each data point. The paradigm also allows to solve problems which are not defined in the classical MSE approach, such as fitting a segment (as opposed to a line). It is shown to be non-biased, and to achieve excellent results for general curves, even in the presence of strong discontinuities. Results are shown for a number of fitting problems, including lines, circles, segments, and general curves, contaminated by Gaussian and uniform noise.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"12 1","pages":"552-558 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73069392","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 : 1999-06-23DOI: 10.1109/CVPR.1999.784719
Yining Deng, B. S. Manjunath, H. Shin
In this work, a new approach to fully automatic color image segmentation, called JSEG, is presented. First, colors in the image are quantized to several representing classes that can be used to differentiate regions in the image. Then, image pixel colors are replaced by their corresponding color class labels, thus forming a class-map of the image. A criterion for "good" segmentation using this class-map is proposed. Applying the criterion to local windows in the class-map results in the "J-image", in which high and low values correspond to possible region boundaries and region centers, respectively. A region growing method is then used to segment the image based on the multi-scale J-images. Experiments show that JSEG provides good segmentation results on a variety of images.
{"title":"Color image segmentation","authors":"Yining Deng, B. S. Manjunath, H. Shin","doi":"10.1109/CVPR.1999.784719","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784719","url":null,"abstract":"In this work, a new approach to fully automatic color image segmentation, called JSEG, is presented. First, colors in the image are quantized to several representing classes that can be used to differentiate regions in the image. Then, image pixel colors are replaced by their corresponding color class labels, thus forming a class-map of the image. A criterion for \"good\" segmentation using this class-map is proposed. Applying the criterion to local windows in the class-map results in the \"J-image\", in which high and low values correspond to possible region boundaries and region centers, respectively. A region growing method is then used to segment the image based on the multi-scale J-images. Experiments show that JSEG provides good segmentation results on a variety of images.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"11 1","pages":"446-451 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74720926","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786966
T. Mitsunaga, S. Nayar
A simple algorithm is described that computes the radiometric response function of an imaging system, from images of an arbitrary scene taken using different exposures. The exposure is varied by changing either the aperture setting or the shutter speed. The algorithm does not require precise estimates of the exposures used. Rough estimates of the ratios of the exposures (e.g. F-number settings on an inexpensive lens) are sufficient for accurate recovery of the response function as well as the actual exposure ratios. The computed response function is used to fuse the multiple images into a single high dynamic range radiance image. Robustness is tested using a variety of scenes and cameras as well as noisy synthetic images generated using 100 randomly selected response curves. Automatic rejection of image areas that have large vignetting effects or temporal scene variations make the algorithm applicable to not just photographic but also video cameras.
{"title":"Radiometric self calibration","authors":"T. Mitsunaga, S. Nayar","doi":"10.1109/CVPR.1999.786966","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786966","url":null,"abstract":"A simple algorithm is described that computes the radiometric response function of an imaging system, from images of an arbitrary scene taken using different exposures. The exposure is varied by changing either the aperture setting or the shutter speed. The algorithm does not require precise estimates of the exposures used. Rough estimates of the ratios of the exposures (e.g. F-number settings on an inexpensive lens) are sufficient for accurate recovery of the response function as well as the actual exposure ratios. The computed response function is used to fuse the multiple images into a single high dynamic range radiance image. Robustness is tested using a variety of scenes and cameras as well as noisy synthetic images generated using 100 randomly selected response curves. Automatic rejection of image areas that have large vignetting effects or temporal scene variations make the algorithm applicable to not just photographic but also video cameras.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"117 1","pages":"374-380 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79383802","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 : 1999-06-23DOI: 10.1109/CVPR.1999.784968
Tammy Riklin-Raviv, A. Shashua
The paper addresses the problem of "class-based" recognition and image-synthesis with varying illumination. The class-based synthesis and recognition tasks are defined as follows: given a single input image of an object, and a sample of images with varying illumination conditions of other objects of the same general class, capture the equivalence relationship (by generation of new images or by invariants) among all images of the object corresponding to new illumination conditions. The key result in our approach is based on a definition of an illumination invariant signature image, we call the "quotient" image, which enables an analytic generation of the image space with varying illumination from a single input image and a very small sample of other objects of the class-in our experiments as few as two objects. In many cases the recognition results outperform by far conventional methods and the image-synthesis is of remarkable quality considering the size of the database of example images and the mild pre-process required for making the algorithm work.
{"title":"The quotient image: Class based recognition and synthesis under varying illumination conditions","authors":"Tammy Riklin-Raviv, A. Shashua","doi":"10.1109/CVPR.1999.784968","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784968","url":null,"abstract":"The paper addresses the problem of \"class-based\" recognition and image-synthesis with varying illumination. The class-based synthesis and recognition tasks are defined as follows: given a single input image of an object, and a sample of images with varying illumination conditions of other objects of the same general class, capture the equivalence relationship (by generation of new images or by invariants) among all images of the object corresponding to new illumination conditions. The key result in our approach is based on a definition of an illumination invariant signature image, we call the \"quotient\" image, which enables an analytic generation of the image space with varying illumination from a single input image and a very small sample of other objects of the class-in our experiments as few as two objects. In many cases the recognition results outperform by far conventional methods and the image-synthesis is of remarkable quality considering the size of the database of example images and the mild pre-process required for making the algorithm work.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"1 1","pages":"566-571 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79248673","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 : 1999-06-23DOI: 10.1109/CVPR.1999.784979
Yoram Gdalyahu, D. Weinshall, M. Werman
We present a stochastic clustering algorithm which uses pairwise similarity of elements, based on a new graph theoretical algorithm for the sampling of cuts in graphs. The stochastic nature of our method makes it robust against noise, including accidental edges and small spurious clusters. We demonstrate the robustness and superiority of our method for image segmentation on a few synthetic examples where other recently proposed methods (such as normalized-cut) fail. In addition, the complexity of our method is lower. We describe experiments with real images showing good segmentation results.
{"title":"Stochastic image segmentation by typical cuts","authors":"Yoram Gdalyahu, D. Weinshall, M. Werman","doi":"10.1109/CVPR.1999.784979","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784979","url":null,"abstract":"We present a stochastic clustering algorithm which uses pairwise similarity of elements, based on a new graph theoretical algorithm for the sampling of cuts in graphs. The stochastic nature of our method makes it robust against noise, including accidental edges and small spurious clusters. We demonstrate the robustness and superiority of our method for image segmentation on a few synthetic examples where other recently proposed methods (such as normalized-cut) fail. In addition, the complexity of our method is lower. We describe experiments with real images showing good segmentation results.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"46 1","pages":"596-601 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79675451","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 : 1999-06-23DOI: 10.1109/CVPR.1999.784985
Christophe Samson, L. Blanc-Féraud, J. Zerubia, G. Aubert
Herein, we present a variational model devoted to image classification coupled with an edge-preserving regularization process. In the last decade, the variational approach has proven its efficiency in the field of edge-preserving restoration. In this paper, we add a classification capability which contributes to provide images compound of homogeneous regions with regularized boundaries. The soundness of this model is based on the works developed on the phase transition theory in mechanics. The proposed algorithm is fast, easy to implement and efficient. We compare our results on both synthetic and satellite images with the ones obtained by a stochastic model using a Potts regularization.
{"title":"Simultaneous image classification and restoration using a variational approach","authors":"Christophe Samson, L. Blanc-Féraud, J. Zerubia, G. Aubert","doi":"10.1109/CVPR.1999.784985","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784985","url":null,"abstract":"Herein, we present a variational model devoted to image classification coupled with an edge-preserving regularization process. In the last decade, the variational approach has proven its efficiency in the field of edge-preserving restoration. In this paper, we add a classification capability which contributes to provide images compound of homogeneous regions with regularized boundaries. The soundness of this model is based on the works developed on the phase transition theory in mechanics. The proposed algorithm is fast, easy to implement and efficient. We compare our results on both synthetic and satellite images with the ones obtained by a stochastic model using a Potts regularization.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"8 1","pages":"618-623 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80834356","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786977
T. Thórhallsson, D. W. Murray
In this paper we specialize the projective unifocal, bifocal, and trifocal tensors to the affine case, and show how the tensors obtained relate to the registered tensors encountered in previous work. This enables us to obtain an affine specialization of known projective relations connecting points and lines across two or three views. In the simpler case of affine cameras we give neccessary and sufficient constraints on the components of the trifocal tensor together with a simple geometric interpretation. Finally, we show how the estimation of the tensors from point correspondences is achieved through factorization, and discuss the estimation from line correspondences.
{"title":"The tensors of three affine views","authors":"T. Thórhallsson, D. W. Murray","doi":"10.1109/CVPR.1999.786977","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786977","url":null,"abstract":"In this paper we specialize the projective unifocal, bifocal, and trifocal tensors to the affine case, and show how the tensors obtained relate to the registered tensors encountered in previous work. This enables us to obtain an affine specialization of known projective relations connecting points and lines across two or three views. In the simpler case of affine cameras we give neccessary and sufficient constraints on the components of the trifocal tensor together with a simple geometric interpretation. Finally, we show how the estimation of the tensors from point correspondences is achieved through factorization, and discuss the estimation from line correspondences.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"259 1","pages":"450-456 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77111453","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786913
Qian Chen, G. Medioni
We formulate stereo matching as an extremal surface extraction problem. This is made possible by embedding the disparity surface inside a volume where the surface is composed of voxels with locally maximal similarity values. This formulation naturally implements the coherence principle, and allows us to incorporate most known global constraints. Time efficiency is achieved by executing the algorithm in a coarse-to-fine fashion, and only populating the full volume at the coarsest level. To make the system more practical, we present a rectification algorithm based on the fundamental matrix, avoiding full camera calibration. We present results on standard stereo pairs, and on our own data set. The results are qualitatively evaluated in terms of both the generated disparity maps and the 3-D models.
{"title":"A volumetric stereo matching method: application to image-based modeling","authors":"Qian Chen, G. Medioni","doi":"10.1109/CVPR.1999.786913","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786913","url":null,"abstract":"We formulate stereo matching as an extremal surface extraction problem. This is made possible by embedding the disparity surface inside a volume where the surface is composed of voxels with locally maximal similarity values. This formulation naturally implements the coherence principle, and allows us to incorporate most known global constraints. Time efficiency is achieved by executing the algorithm in a coarse-to-fine fashion, and only populating the full volume at the coarsest level. To make the system more practical, we present a rectification algorithm based on the fundamental matrix, avoiding full camera calibration. We present results on standard stereo pairs, and on our own data set. The results are qualitatively evaluated in terms of both the generated disparity maps and the 3-D models.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"13 1","pages":"29-34 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74372463","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786915
Qasim Iqbal, J. Aggarwal
This paper presents an application of perceptual grouping rules for content-based image retrieval. The semantic interrelationships between different primitive image features are exploited by perceptual grouping to detect the presence of manmade structures. A methodology based on these principles in a Bayesian framework for the retrieval of building images, and the results obtained are presented. The image database consists of monocular grayscale outdoor images taken from a ground-level camera.
{"title":"Applying perceptual grouping to content-based image retrieval: building images","authors":"Qasim Iqbal, J. Aggarwal","doi":"10.1109/CVPR.1999.786915","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786915","url":null,"abstract":"This paper presents an application of perceptual grouping rules for content-based image retrieval. The semantic interrelationships between different primitive image features are exploited by perceptual grouping to detect the presence of manmade structures. A methodology based on these principles in a Bayesian framework for the retrieval of building images, and the results obtained are presented. The image database consists of monocular grayscale outdoor images taken from a ground-level camera.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"3 1","pages":"42-48 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73471931","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786990
Jinggang Huang, D. Mumford
Large calibrated datasets of 'random' natural images have recently become available. These make possible precise and intensive statistical studies of the local nature of images. We report results ranging from the simplest single pixel intensity to joint distribution of 3 Haar wavelet responses. Some of these statistics shed light on old issues such as the near scale-invariance of image statistics and some are entirely new. We fit mathematical models to some of the statistics and explain others in terms of local image features.
{"title":"Statistics of natural images and models","authors":"Jinggang Huang, D. Mumford","doi":"10.1109/CVPR.1999.786990","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786990","url":null,"abstract":"Large calibrated datasets of 'random' natural images have recently become available. These make possible precise and intensive statistical studies of the local nature of images. We report results ranging from the simplest single pixel intensity to joint distribution of 3 Haar wavelet responses. Some of these statistics shed light on old issues such as the near scale-invariance of image statistics and some are entirely new. We fit mathematical models to some of the statistics and explain others in terms of local image features.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"8 1","pages":"541-547 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81949857","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：