Pub Date : 2001-09-26DOI: 10.1109/ICIAP.2001.957047
S. Fischer, G. Cristóbal
Most image compression methods are based on the use of the DCT or (bi-)orthogonal wavelets. However, in many cases improved performance in terms of visual quality can be expected if we consider a human visual system based model. The aim of this paper is to explore the potential of image compression techniques based on the use of nonorthogonal filters such as Gabor wavelets. The compression scheme is performed by a linear wavelet transform with filters similar to 2D Gabor functions through a quantizer based on measurements of the contrast sensitivity function of the human visual system (HVS). The compression performance is evaluated by entropy and error measures. Because of the non-orthogonality property, different image decompositions will have the same reconstruction. Thus, between all possible decompositions, one can be interested specifically in a minimum entropy wavelet transform that minimizes the information redundancy. This process can be considered as a nonlinear Gabor-wavelet transform that can be employed for compression applications. The overall optimization procedure has been implemented as an iterative algorithm producing a significant reduction in the information redundancy.
{"title":"Minimum entropy transform using Gabor wavelets for image compression","authors":"S. Fischer, G. Cristóbal","doi":"10.1109/ICIAP.2001.957047","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957047","url":null,"abstract":"Most image compression methods are based on the use of the DCT or (bi-)orthogonal wavelets. However, in many cases improved performance in terms of visual quality can be expected if we consider a human visual system based model. The aim of this paper is to explore the potential of image compression techniques based on the use of nonorthogonal filters such as Gabor wavelets. The compression scheme is performed by a linear wavelet transform with filters similar to 2D Gabor functions through a quantizer based on measurements of the contrast sensitivity function of the human visual system (HVS). The compression performance is evaluated by entropy and error measures. Because of the non-orthogonality property, different image decompositions will have the same reconstruction. Thus, between all possible decompositions, one can be interested specifically in a minimum entropy wavelet transform that minimizes the information redundancy. This process can be considered as a nonlinear Gabor-wavelet transform that can be employed for compression applications. The overall optimization procedure has been implemented as an iterative algorithm producing a significant reduction in the information redundancy.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127062386","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957011
Juhui Wang, A. Trubuil, C. Graffigne
One essential assumption used in object detection and labeling by imaging is that the photometric properties of the object are homogeneous. This homogeneity requirement is often violated in microscopy imaging. Classical methods are usually of high computational cost and fail to give a stable solution. This paper presents a low computational complexity and robust method for 3D biological object detection and labeling. The developed approach is based on a statistical, non-parametric framework. The image is first divided into regular non-overlapped regions and each region is evaluated according to a general photometric variability model. The regions not consistent with this model are considered as aberrations in the data and excluded from the analysis procedure. Simultaneously, the interior parts of the object are detected. They correspond to regions where the supposed model is valid. In the second stage, the valid regions from the same object are merged under a set of hypotheses. These hypotheses are generated by taking into account photometric and geometric properties of objects and the merging is realized according to an iterative algorithm. The approach has been applied in investigations of the spatial distribution of nuclei on colonic glands of rats observed with with help of confocal fluorescence microscopy.
{"title":"3D biological object detection and labeling in multidimensional microscopy imaging","authors":"Juhui Wang, A. Trubuil, C. Graffigne","doi":"10.1109/ICIAP.2001.957011","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957011","url":null,"abstract":"One essential assumption used in object detection and labeling by imaging is that the photometric properties of the object are homogeneous. This homogeneity requirement is often violated in microscopy imaging. Classical methods are usually of high computational cost and fail to give a stable solution. This paper presents a low computational complexity and robust method for 3D biological object detection and labeling. The developed approach is based on a statistical, non-parametric framework. The image is first divided into regular non-overlapped regions and each region is evaluated according to a general photometric variability model. The regions not consistent with this model are considered as aberrations in the data and excluded from the analysis procedure. Simultaneously, the interior parts of the object are detected. They correspond to regions where the supposed model is valid. In the second stage, the valid regions from the same object are merged under a set of hypotheses. These hypotheses are generated by taking into account photometric and geometric properties of objects and the merging is realized according to an iterative algorithm. The approach has been applied in investigations of the spatial distribution of nuclei on colonic glands of rats observed with with help of confocal fluorescence microscopy.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126981243","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957003
T. Shioyama, Haiyuan Wu, Y. Nishibe, Naoki Nakamura, Suguru Kitawaki
This paper proposes a method for image analysis of a crosswalk and a traffic light. The method provides information not only about the length of a crosswalk, but also about the colour of the traffic light. The length of a crosswalk is estimated by projective geometry using white lines painted on the road at a crosswalk. Furthermore, the state of the traffic light, that is, the colour of green (walk signal) or red (stop signal), is detected by searching the green (or red) traffic light using affine moment invariants. In order to evaluate the performance, experimental results estimating the length and detecting the traffic light are presented.
{"title":"Image analysis of crosswalk","authors":"T. Shioyama, Haiyuan Wu, Y. Nishibe, Naoki Nakamura, Suguru Kitawaki","doi":"10.1109/ICIAP.2001.957003","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957003","url":null,"abstract":"This paper proposes a method for image analysis of a crosswalk and a traffic light. The method provides information not only about the length of a crosswalk, but also about the colour of the traffic light. The length of a crosswalk is estimated by projective geometry using white lines painted on the road at a crosswalk. Furthermore, the state of the traffic light, that is, the colour of green (walk signal) or red (stop signal), is detected by searching the green (or red) traffic light using affine moment invariants. In order to evaluate the performance, experimental results estimating the length and detecting the traffic light are presented.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124148593","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.956986
A. Robles-Kelly, E. Hancock
This paper presents an iterative maximum likelihood framework for motion segmentation. Our representation of the segmentation problem is based on a similarity matrix for the motion vectors for pairs of pixel blocks. By applying eigendecomposition to the similarity matrix, we develop a maximum likelihood method for grouping the pixel blocks into objects which share a common motion vector. We experiment with the resulting clustering method on a number of real-world motion sequences. Here ground truth data indicates that the method can result in motion classification errors as low as 3%.
{"title":"Maximum likelihood motion segmentation using eigendecomposition","authors":"A. Robles-Kelly, E. Hancock","doi":"10.1109/ICIAP.2001.956986","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956986","url":null,"abstract":"This paper presents an iterative maximum likelihood framework for motion segmentation. Our representation of the segmentation problem is based on a similarity matrix for the motion vectors for pairs of pixel blocks. By applying eigendecomposition to the similarity matrix, we develop a maximum likelihood method for grouping the pixel blocks into objects which share a common motion vector. We experiment with the resulting clustering method on a number of real-world motion sequences. Here ground truth data indicates that the method can result in motion classification errors as low as 3%.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121594012","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.956980
M. Bicego, Vittorio Murino
In computer vision, two-dimensional shape classification is a complex and well-studied topic, often basic for three-dimensional object recognition. Object contours are a widely chosen feature for representing objects, useful in many respects for classification problems. We address the use of hidden Markov models (HMM) for shape analysis, based on chain code representation of object contours. HMM represent a widespread approach to the modeling of sequences, and are largely used for many applications, but unfortunately are poorly considered in the literature concerning shape analysis, and in any case, without reference to noise or occlusion sensitivity. The HMM approach to shape modeling is tested, probing good invariance of this method in terms of noise, occlusions, and object scaling.
{"title":"2D shape recognition by hidden Markov models","authors":"M. Bicego, Vittorio Murino","doi":"10.1109/ICIAP.2001.956980","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956980","url":null,"abstract":"In computer vision, two-dimensional shape classification is a complex and well-studied topic, often basic for three-dimensional object recognition. Object contours are a widely chosen feature for representing objects, useful in many respects for classification problems. We address the use of hidden Markov models (HMM) for shape analysis, based on chain code representation of object contours. HMM represent a widespread approach to the modeling of sequences, and are largely used for many applications, but unfortunately are poorly considered in the literature concerning shape analysis, and in any case, without reference to noise or occlusion sensitivity. The HMM approach to shape modeling is tested, probing good invariance of this method in terms of noise, occlusions, and object scaling.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121959085","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957014
L. Gregory, J. Kittler
Visual information retrieval presents many challenges for the computer vision community. The terabytes of visual information stored in digital image and video libraries will remain inaccessible if the problems of indexing and retrieval are not addressed. We present techniques for content based image retrieval using higher level contextual information. The content is represented and queried using attributed relational graphs, with colour attributes and relaxation labelling techniques. We present retrieval examples using both synthetic and real images of national flags. This, although a simplistic problem, highlights the shortcomings and difficulties associated with content based retrieval systems.
{"title":"Using contextual information for image retrieval","authors":"L. Gregory, J. Kittler","doi":"10.1109/ICIAP.2001.957014","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957014","url":null,"abstract":"Visual information retrieval presents many challenges for the computer vision community. The terabytes of visual information stored in digital image and video libraries will remain inaccessible if the problems of indexing and retrieval are not addressed. We present techniques for content based image retrieval using higher level contextual information. The content is represented and queried using attributed relational graphs, with colour attributes and relaxation labelling techniques. We present retrieval examples using both synthetic and real images of national flags. This, although a simplistic problem, highlights the shortcomings and difficulties associated with content based retrieval systems.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129761098","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.956993
C. Colombo, A. Bimbo, A. Valli
Non-intrusive human body tracking is a key issue in advanced human-computer interaction, with key applications ranging from virtual reality to videoconferencing and telepresence. This paper describes a system for vision-based tracking of body posture. The system is explicitly designed to provide a robust yet simple and inexpensive solution to real-time body tracking through a careful choice of visual and kinematic models. Human posture representation is fully compatible with the MPEG-4 standard. Results of system application to a computer graphics scenario (animation of 3D avatars) are presented and discussed.
{"title":"Real-time tracking and reproduction of 3D human body motion","authors":"C. Colombo, A. Bimbo, A. Valli","doi":"10.1109/ICIAP.2001.956993","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956993","url":null,"abstract":"Non-intrusive human body tracking is a key issue in advanced human-computer interaction, with key applications ranging from virtual reality to videoconferencing and telepresence. This paper describes a system for vision-based tracking of body posture. The system is explicitly designed to provide a robust yet simple and inexpensive solution to real-time body tracking through a careful choice of visual and kinematic models. Human posture representation is fully compatible with the MPEG-4 standard. Results of system application to a computer graphics scenario (animation of 3D avatars) are presented and discussed.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131043690","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957029
I. Sintorn, G. Borgefors
We investigate weighted distance transforms in 2D images in rectangular grids. We use a local neighborhood of size 3/spl times/3 and assume a rectangular grid with arbitrary ratio between the sides. The weights (local distances) are optimized by minimizing the maximum error over linear trajectories, which is an all-digital approach. General solutions for all ratios are presented. We also present numeric results for the cases when the ratio between the sides equals 1 (comparable with studies of weighted distance transforms in the square grid), 4/3 and 3. Integer solutions for both real and integer scale factors are presented.
{"title":"Weighted distance transforms in rectangular grids","authors":"I. Sintorn, G. Borgefors","doi":"10.1109/ICIAP.2001.957029","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957029","url":null,"abstract":"We investigate weighted distance transforms in 2D images in rectangular grids. We use a local neighborhood of size 3/spl times/3 and assume a rectangular grid with arbitrary ratio between the sides. The weights (local distances) are optimized by minimizing the maximum error over linear trajectories, which is an all-digital approach. General solutions for all ratios are presented. We also present numeric results for the cases when the ratio between the sides equals 1 (comparable with studies of weighted distance transforms in the square grid), 4/3 and 3. Integer solutions for both real and integer scale factors are presented.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131061681","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957007
Datong Chen, K. Shearer, H. Bourlard
Stripes are common sub-structures of text characters, and the scale of these stripes varies little within a word. This scale consistency thus provides us with a useful feature for text detection and segmentation. A new form of filter is derived from the Gabor filter, and it is shown that this filter can efficiently estimate the scales of these stripes. The contrast of text in video can then be increased by enhancing the edges of only those stripes found to correspond to a suitable scale. More specifically the algorithm presented here enhances the stripes in three pre-selected scale ranges. The resulting enhancement yields much better performance from the binarization process, which is the step required before character recognition.
{"title":"Text enhancement with asymmetric filter for video OCR","authors":"Datong Chen, K. Shearer, H. Bourlard","doi":"10.1109/ICIAP.2001.957007","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957007","url":null,"abstract":"Stripes are common sub-structures of text characters, and the scale of these stripes varies little within a word. This scale consistency thus provides us with a useful feature for text detection and segmentation. A new form of filter is derived from the Gabor filter, and it is shown that this filter can efficiently estimate the scales of these stripes. The contrast of text in video can then be increased by enhancing the edges of only those stripes found to correspond to a suitable scale. More specifically the algorithm presented here enhances the stripes in three pre-selected scale ranges. The resulting enhancement yields much better performance from the binarization process, which is the step required before character recognition.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134219410","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 : 2001-09-26DOI: 10.1109/ICIAP.2001.957037
F. Cheng, W. Christmas, J. Kittler
Motion description is an example of high-level video processing. It is attracting increasing interest in the computer vision community, due to its wide spectrum of applications. In such applications as multimedia database systems, motion descriptors act as a high-level query tool. We propose a periodic motion detection and description algorithm. We demonstrate that the descriptor extracted by the algorithm can characterise the human running behaviour. It can also serve as a basis for the classification of the human running activity. Experimental results based on Barcelona Olympic Games image sequences show the benefits of the proposed algorithm.
{"title":"Detection and description of human running behaviour in sports video multimedia database","authors":"F. Cheng, W. Christmas, J. Kittler","doi":"10.1109/ICIAP.2001.957037","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957037","url":null,"abstract":"Motion description is an example of high-level video processing. It is attracting increasing interest in the computer vision community, due to its wide spectrum of applications. In such applications as multimedia database systems, motion descriptors act as a high-level query tool. We propose a periodic motion detection and description algorithm. We demonstrate that the descriptor extracted by the algorithm can characterise the human running behaviour. It can also serve as a basis for the classification of the human running activity. Experimental results based on Barcelona Olympic Games image sequences show the benefits of the proposed algorithm.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134139081","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：