Pub Date : 2001-09-26DOI: 10.1109/ICIAP.2001.957021
Albert Pujol, J. Villanueva, H. Wechsler
This paper shows a self-organized system designed to obtain compressed representations of instances of a population of visual forms. It is shown how, when applied to face shape information, the system evolves into a prototype of the population and induces automatic warping, or caricaturing, transformations where geometrical differences between forms are increased, improving, as a consequence, recognition performance. In this way, the proposed system provides a unified account for the whole chain of face processing tasks including data compression, detection, and recognition. Experimental data is presented to show the feasibility of our approach in terms of performance and robustness to changes in illumination and face expressions.
{"title":"Learning and caricaturing the face space using self-organization and Hebbian learning for face processing","authors":"Albert Pujol, J. Villanueva, H. Wechsler","doi":"10.1109/ICIAP.2001.957021","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957021","url":null,"abstract":"This paper shows a self-organized system designed to obtain compressed representations of instances of a population of visual forms. It is shown how, when applied to face shape information, the system evolves into a prototype of the population and induces automatic warping, or caricaturing, transformations where geometrical differences between forms are increased, improving, as a consequence, recognition performance. In this way, the proposed system provides a unified account for the whole chain of face processing tasks including data compression, detection, and recognition. Experimental data is presented to show the feasibility of our approach in terms of performance and robustness to changes in illumination and face expressions.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"186 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":"114745063","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.2001.956983
P. Navarrete, Javier Ruiz-del-Solar
Different eigenspace-based approaches have been proposed for the recognition of faces. They differ mostly in the kind of projection method used and in the similarity matching criterion employed. A first goal of this paper is to present a comparison between some of these different approaches. A second goal is to outline an adaptive, neural-based security access control system.
{"title":"Eigenspace-based recognition of faces: comparisons and a new approach","authors":"P. Navarrete, Javier Ruiz-del-Solar","doi":"10.1109/ICIAP.2001.956983","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956983","url":null,"abstract":"Different eigenspace-based approaches have been proposed for the recognition of faces. They differ mostly in the kind of projection method used and in the similarity matching criterion employed. A first goal of this paper is to present a comparison between some of these different approaches. A second goal is to outline an adaptive, neural-based security access control system.","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":"134639603","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.2001.957048
P. Parada, J. Ruiz-del-Solar, W. Plagges, M. Koppen
The TEXRET (texture retrieval) system is a new texture database retrieval system, which is based on soft-computing technologies and that is under development. One of its main features is the generation of the requested textures when they are not found in the database, which allows a continuous growing of the database. The texture generation process, implemented using causal autoregressive models and interactive genetic algorithms, is described.
{"title":"Interactive texture synthesis","authors":"P. Parada, J. Ruiz-del-Solar, W. Plagges, M. Koppen","doi":"10.1109/ICIAP.2001.957048","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957048","url":null,"abstract":"The TEXRET (texture retrieval) system is a new texture database retrieval system, which is based on soft-computing technologies and that is under development. One of its main features is the generation of the requested textures when they are not found in the database, which allows a continuous growing of the database. The texture generation process, implemented using causal autoregressive models and interactive genetic algorithms, is described.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"24 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":"133624778","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.2001.956990
V. Cantoni, L. Lombardi, M. Porta, Nicolas Sicard
We introduce two different representation approaches and propose two techniques to estimate the position of vanishing points in an image, one bused on a probabilistic strategy and the other focused on a deterministic analysis. Unlike most of the methods so far developed, which exploit the Gaussian sphere, the new techniques operate in the (/spl rho/, /spl theta/) polar parameter space and in the (x, y) image plane coordinate space. Both the solutions are described and compared, through the discussion of the results obtained from their application to real images.
{"title":"Vanishing point detection: representation analysis and new approaches","authors":"V. Cantoni, L. Lombardi, M. Porta, Nicolas Sicard","doi":"10.1109/ICIAP.2001.956990","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956990","url":null,"abstract":"We introduce two different representation approaches and propose two techniques to estimate the position of vanishing points in an image, one bused on a probabilistic strategy and the other focused on a deterministic analysis. Unlike most of the methods so far developed, which exploit the Gaussian sphere, the new techniques operate in the (/spl rho/, /spl theta/) polar parameter space and in the (x, y) image plane coordinate space. Both the solutions are described and compared, through the discussion of the results obtained from their application to real images.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"69 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":"132761037","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.2001.957040
M. D. Santo, G. Percannella, Carlo Sansone, M. Vento
The paper presents a system for the automatic MPEG format. In contrast to the approaches proposed up to now, it employs a multi-expert classification system arranged according to a multi-stage architecture. The system is able to recognize not only four pure classes (music, speech, silence and noise) but also confused audio signals, such as the ones resulting from the overlap of pure audio components (for example, speech overlapped with music or noise, etc.). An extensive experimental analysis has been carried on a large audio database extracted from about 30 moving pictures recorded on low-quality magnetic media. Results confirm the effectiveness of the approach, with an average improvement of about 45% with respect to single classifier solutions.
{"title":"Classifying audio of movies by a multi-expert system","authors":"M. D. Santo, G. Percannella, Carlo Sansone, M. Vento","doi":"10.1109/ICIAP.2001.957040","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957040","url":null,"abstract":"The paper presents a system for the automatic MPEG format. In contrast to the approaches proposed up to now, it employs a multi-expert classification system arranged according to a multi-stage architecture. The system is able to recognize not only four pure classes (music, speech, silence and noise) but also confused audio signals, such as the ones resulting from the overlap of pure audio components (for example, speech overlapped with music or noise, etc.). An extensive experimental analysis has been carried on a large audio database extracted from about 30 moving pictures recorded on low-quality magnetic media. Results confirm the effectiveness of the approach, with an average improvement of about 45% with respect to single classifier solutions.","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":"121938031","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.2001.957079
J. Chassery, F. Dupont, Isabelle Sivignon, Joëlle Vittone
Triangulation, quadrangulation problems and more generally 3D object polyhedrization are an important subject of research. In digital geometry, a 3D object is seen as a set of voxels placed in a representation space only constituted of integers. The objective of the polyhedrization is to obtain a complete description of the object with faces, edges and vertices. The recognition of digital planes is a first step which is very important. We focus on digital naive planes that have been studied through their configurations of tricubes: of (n,m)-cubes and connected or not connected voxels set. The link between the normal equation of a plane and configuration of voxels set has been studied by the construction of the corresponding Farey net. We can find many references about the recognition of digital planes. Some algorithms were related to the construction of the convex hull of the studied voxels set. Other approaches use linear programming, mean square approximation or Fourier-Motzkin transform. The first algorithms entirely discrete recognized rectangular pieces of naive planes. Wwe describe an incremental algorithm to recognize any coplanar voxels set as a digital naive plane by using Farey nets. Then we propose a polyhedrization method able to give all the digital naive planes of the surface of the 3D object.
{"title":"Digital geometry fundaments: application to plane recognition","authors":"J. Chassery, F. Dupont, Isabelle Sivignon, Joëlle Vittone","doi":"10.1109/ICIAP.2001.957079","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957079","url":null,"abstract":"Triangulation, quadrangulation problems and more generally 3D object polyhedrization are an important subject of research. In digital geometry, a 3D object is seen as a set of voxels placed in a representation space only constituted of integers. The objective of the polyhedrization is to obtain a complete description of the object with faces, edges and vertices. The recognition of digital planes is a first step which is very important. We focus on digital naive planes that have been studied through their configurations of tricubes: of (n,m)-cubes and connected or not connected voxels set. The link between the normal equation of a plane and configuration of voxels set has been studied by the construction of the corresponding Farey net. We can find many references about the recognition of digital planes. Some algorithms were related to the construction of the convex hull of the studied voxels set. Other approaches use linear programming, mean square approximation or Fourier-Motzkin transform. The first algorithms entirely discrete recognized rectangular pieces of naive planes. Wwe describe an incremental algorithm to recognize any coplanar voxels set as a digital naive plane by using Farey nets. Then we propose a polyhedrization method able to give all the digital naive planes of the surface of the 3D object.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"97 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":"122241362","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.2001.957034
A. Blake, Michel Gangnet, P. Pérez, J. Vermaak
The research summarised here is working towards automatic control systems for cameras, in support of remote meetings. Progress is reported on several fronts: use of active contours to track heads, stereo sound analysis applying particle filtering to handle both visual and aural clutter, and the use of exemplars for stabilisation of inter-frame matching.
{"title":"Integrated tracking with vision and sound","authors":"A. Blake, Michel Gangnet, P. Pérez, J. Vermaak","doi":"10.1109/ICIAP.2001.957034","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957034","url":null,"abstract":"The research summarised here is working towards automatic control systems for cameras, in support of remote meetings. Progress is reported on several fronts: use of active contours to track heads, stereo sound analysis applying particle filtering to handle both visual and aural clutter, and the use of exemplars for stabilisation of inter-frame matching.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"59 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":"130220037","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.2001.956978
A. Caplier
Seeing the talker's lips in addition to audition can improve speech understanding which is rather based on lip shape temporal evolution than on absolute mouth shape. We propose a totally automatic algorithm which can extract lip shape over an image sequence. The algorithm does not require any make-up or markers and works under natural lighting conditions. The lip detection algorithm uses an active shape model to describe the mouth. After a training step, the mouth model is iteratively deformed under constraints according to spatiotemporal energies. The robust prior detection of mouth corners and Cupidon's arch yields the automatic positioning of the initial shape which is very difficult and must be as accurate as possible. Temporal information integration comes from the definition of Kalman filters on the independent mouth parameters. Such filtering gives an initial shape close to the final one which speeds up the convergence rate. We point out on the behaviour of our algorithm when a transition open mouth/closed mouth or closed mouth/open mouth occurs.
{"title":"Lip detection and tracking","authors":"A. Caplier","doi":"10.1109/ICIAP.2001.956978","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.956978","url":null,"abstract":"Seeing the talker's lips in addition to audition can improve speech understanding which is rather based on lip shape temporal evolution than on absolute mouth shape. We propose a totally automatic algorithm which can extract lip shape over an image sequence. The algorithm does not require any make-up or markers and works under natural lighting conditions. The lip detection algorithm uses an active shape model to describe the mouth. After a training step, the mouth model is iteratively deformed under constraints according to spatiotemporal energies. The robust prior detection of mouth corners and Cupidon's arch yields the automatic positioning of the initial shape which is very difficult and must be as accurate as possible. Temporal information integration comes from the definition of Kalman filters on the independent mouth parameters. Such filtering gives an initial shape close to the final one which speeds up the convergence rate. We point out on the behaviour of our algorithm when a transition open mouth/closed mouth or closed mouth/open mouth occurs.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"47 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":"127404902","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.2001.957071
S. Vitabile, G. Pollaccia, G. Pilato, F. Sorbello
We present a system for the whole road sign detection and recognition task. Road sign regions are detected and extracted from real-world scenes on the basis of their color and shape features. Color segmentation is performed introducing a dynamic threshold in the pixel aggregation process on the HSV color space. The dynamic threshold allows the reduction of hue instability in real scenes depending on external brightness variation. Experimental results, using real road images in different environment conditions, are also reported.
{"title":"Road signs recognition using a dynamic pixel aggregation technique in the HSV color space","authors":"S. Vitabile, G. Pollaccia, G. Pilato, F. Sorbello","doi":"10.1109/ICIAP.2001.957071","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957071","url":null,"abstract":"We present a system for the whole road sign detection and recognition task. Road sign regions are detected and extracted from real-world scenes on the basis of their color and shape features. Color segmentation is performed introducing a dynamic threshold in the pixel aggregation process on the HSV color space. The dynamic threshold allows the reduction of hue instability in real scenes depending on external brightness variation. Experimental results, using real road images in different environment conditions, are also reported.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"7 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":"127985205","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.2001.957023
F. Dornaika
View synthesis becomes a focus of attention of both the computer graphics and computer vision communities. We present a new approach for synthesizing novel views from two uncalibrated images. The two reference images as well as the novel view do not share the same viewpoint. The developed approach incorporates computer vision methods. It consists of two stages. First, the parallax field between the reference images is recovered. Second, novel images are directly synthesized by exploiting the parallax invariance, using forward warping. Solutions to the visibility problem are proposed. Constructing realistic synthesized views from real image pairs are presented.
{"title":"View synthesis from two uncalibrated images","authors":"F. Dornaika","doi":"10.1109/ICIAP.2001.957023","DOIUrl":"https://doi.org/10.1109/ICIAP.2001.957023","url":null,"abstract":"View synthesis becomes a focus of attention of both the computer graphics and computer vision communities. We present a new approach for synthesizing novel views from two uncalibrated images. The two reference images as well as the novel view do not share the same viewpoint. The developed approach incorporates computer vision methods. It consists of two stages. First, the parallax field between the reference images is recovered. Second, novel images are directly synthesized by exploiting the parallax invariance, using forward warping. Solutions to the visibility problem are proposed. Constructing realistic synthesized views from real image pairs are presented.","PeriodicalId":365627,"journal":{"name":"Proceedings 11th International Conference on Image Analysis and Processing","volume":"22 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":"126368429","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：