Pub Date : 2003-09-17DOI: 10.1109/ICIAP.2003.1234111
S. Battiato, G. Gallo, F. Stanco
To enlarge a digital image from a single frame preserving the perceptive cues is a relevant research issue. The best known algorithms take into account the presence of edges in the luminance channel, to interpolate correctly the samples/pixels of the original image. This approach allows the production of pictures where the interpolated artifacts (aliasing blurring effect,...) are limited but where high frequencies are not properly preserved. The zooming algorithm proposed in this paper on the other hand reduces the noise and enhances the contrast to the borders/edges of the enlarged picture using classical anisotropic diffusion improved by a smart heuristic strategy. The method requires limited computational resources and it works on gray-level images, RGB color pictures and Bayer data. Our experiments show that this algorithm outperforms in quality and efficiency the classical interpolation methods (replication, bilinear, bicubic).
{"title":"Smart interpolation by anisotropic diffusion","authors":"S. Battiato, G. Gallo, F. Stanco","doi":"10.1109/ICIAP.2003.1234111","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234111","url":null,"abstract":"To enlarge a digital image from a single frame preserving the perceptive cues is a relevant research issue. The best known algorithms take into account the presence of edges in the luminance channel, to interpolate correctly the samples/pixels of the original image. This approach allows the production of pictures where the interpolated artifacts (aliasing blurring effect,...) are limited but where high frequencies are not properly preserved. The zooming algorithm proposed in this paper on the other hand reduces the noise and enhances the contrast to the borders/edges of the enlarged picture using classical anisotropic diffusion improved by a smart heuristic strategy. The method requires limited computational resources and it works on gray-level images, RGB color pictures and Bayer data. Our experiments show that this algorithm outperforms in quality and efficiency the classical interpolation methods (replication, bilinear, bicubic).","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123971624","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234099
J. Assfalg, M. Bertini, C. Colombo, A. Bimbo, W. Nunziati
Live logging and posterity logging are the two basic applications for video databases. The former aims at providing effective annotation of video in quasi-real time and supports extraction of meaningful clips from the live stream; the latter provides annotation for later reuse of video material and is the prerequisite for retrieval by content from video digital libraries. Both require that information is adequately structured with interchange format and that annotation is performed, to a great extent, automatically. The video information structure must encompass both low-intermediate level video organization and event relationships that define specific highlights and situations. Analysis of the visual data of the video stream permits hints to be extracted, events identified and highlights detected. All of this must be supported by a-priori knowledge of the subject and effective reasoning engines capable of capturing the inherent semantics of the visual events.
{"title":"Highlight extraction in soccer videos","authors":"J. Assfalg, M. Bertini, C. Colombo, A. Bimbo, W. Nunziati","doi":"10.1109/ICIAP.2003.1234099","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234099","url":null,"abstract":"Live logging and posterity logging are the two basic applications for video databases. The former aims at providing effective annotation of video in quasi-real time and supports extraction of meaningful clips from the live stream; the latter provides annotation for later reuse of video material and is the prerequisite for retrieval by content from video digital libraries. Both require that information is adequately structured with interchange format and that annotation is performed, to a great extent, automatically. The video information structure must encompass both low-intermediate level video organization and event relationships that define specific highlights and situations. Analysis of the visual data of the video stream permits hints to be extracted, events identified and highlights detected. All of this must be supported by a-priori knowledge of the subject and effective reasoning engines capable of capturing the inherent semantics of the visual events.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"689 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116825754","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234043
Chikahito Nakajima, N. Itoh
We are developing a support system for maintenance training of electric power facilities by augmented reality. A user of the system wears a head-mounted display (HMD), with a small camera and with a sensor on top of the head, and stands in front of a blue screen. The system recognizes an object and estimates its position and pose from an image that is captured by the small camera. The object recognition and the position-pose estimation are performed by image processing without any special image marks or sensors. After the object recognition and the position-pose estimation, the system overlays computer graphics on the object images. The computer graphics show operational guidance, instructions, or dynamic inside movements of the object on the HMD. We describe an outline of the system and evaluation results of the system functions: the object recognition, the position-pose estimation and the operational guidance.
{"title":"A support system for maintenance training by augmented reality","authors":"Chikahito Nakajima, N. Itoh","doi":"10.1109/ICIAP.2003.1234043","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234043","url":null,"abstract":"We are developing a support system for maintenance training of electric power facilities by augmented reality. A user of the system wears a head-mounted display (HMD), with a small camera and with a sensor on top of the head, and stands in front of a blue screen. The system recognizes an object and estimates its position and pose from an image that is captured by the small camera. The object recognition and the position-pose estimation are performed by image processing without any special image marks or sensors. After the object recognition and the position-pose estimation, the system overlays computer graphics on the object images. The computer graphics show operational guidance, instructions, or dynamic inside movements of the object on the HMD. We describe an outline of the system and evaluation results of the system functions: the object recognition, the position-pose estimation and the operational guidance.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122996184","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234074
J. Assfalg, A. Bimbo, P. Pala
In the field of content-based retrieval of multimedia documents, 3D models have recently gained increasing attention for a number of reasons: advancements in 3D hardware and software technologies; their ever decreasing prices and increasing availability; affordable 3D authoring tools; the establishment of such open standards for 3D data interchange as VRML and X3D. We present a solution for content-based retrieval of 3D models that relies on a description of each model by means of a curvature map. After an initial preprocessing of the model, differential properties of points on the surface of the 3D object are evaluated; the model surface is then warped into an ellipsoid, and is mapped onto a 2D image, retaining the curvature information of the original model. Matching is performed by comparing the map of the query against the maps of database models. In particular, this approach exploits weighted walkthroughs to describe curvature maps. Experimental results reveal that this technique, initially developed to describe images, can be successfully applied to curvature maps.
{"title":"Retrieval of 3D objects using curvature maps and weighted walkthroughs","authors":"J. Assfalg, A. Bimbo, P. Pala","doi":"10.1109/ICIAP.2003.1234074","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234074","url":null,"abstract":"In the field of content-based retrieval of multimedia documents, 3D models have recently gained increasing attention for a number of reasons: advancements in 3D hardware and software technologies; their ever decreasing prices and increasing availability; affordable 3D authoring tools; the establishment of such open standards for 3D data interchange as VRML and X3D. We present a solution for content-based retrieval of 3D models that relies on a description of each model by means of a curvature map. After an initial preprocessing of the model, differential properties of points on the surface of the 3D object are evaluated; the model surface is then warped into an ellipsoid, and is mapped onto a 2D image, retaining the curvature information of the original model. Matching is performed by comparing the map of the query against the maps of database models. In particular, this approach exploits weighted walkthroughs to describe curvature maps. Experimental results reveal that this technique, initially developed to describe images, can be successfully applied to curvature maps.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124797336","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234097
H. Samet
Similarity searching is an important task when trying to find patterns in applications which involve mining different types of data such as images, video, time series, text documents, DNA sequences, etc. Similarity searching often reduces to finding the k nearest neighbors to a query object. A description is given of how to use an estimate of the maximum possible distance at which a nearest neighbor can be found to prune the search process in a depth-first branch-and-bound k-nearest neighbor finding algorithm. Using the MaxNearestDist estimator (Larsen, S. and Kanal, L.N., 1986) in the depth-first k-nearest neighbor algorithm provides a middle ground between a pure depth-first and a best-first k-nearest neighbor algorithm.
{"title":"Depth-first k-nearest neighbor finding using the MaxNearestDist estimator","authors":"H. Samet","doi":"10.1109/ICIAP.2003.1234097","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234097","url":null,"abstract":"Similarity searching is an important task when trying to find patterns in applications which involve mining different types of data such as images, video, time series, text documents, DNA sequences, etc. Similarity searching often reduces to finding the k nearest neighbors to a query object. A description is given of how to use an estimate of the maximum possible distance at which a nearest neighbor can be found to prune the search process in a depth-first branch-and-bound k-nearest neighbor finding algorithm. Using the MaxNearestDist estimator (Larsen, S. and Kanal, L.N., 1986) in the depth-first k-nearest neighbor algorithm provides a middle ground between a pure depth-first and a best-first k-nearest neighbor algorithm.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125572410","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234017
J. Bigün, Julian Fierrez, J. Ortega-Garcia, J. González-Rodríguez
The elements of multimodal authentication along with system models are presented. These include the machine experts as well as machine supervisors. In particular, fingerprint and speech based systems serve as illustration of a mobile authentication application. A novel signal adaptive supervisor, based on the input biometric signal quality, is evaluated. Experimental results on data collected from mobile telephones are reported; they demonstrate the benefits of the proposed scheme.
{"title":"Multimodal biometric authentication using quality signals in mobile communications","authors":"J. Bigün, Julian Fierrez, J. Ortega-Garcia, J. González-Rodríguez","doi":"10.1109/ICIAP.2003.1234017","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234017","url":null,"abstract":"The elements of multimodal authentication along with system models are presented. These include the machine experts as well as machine supervisors. In particular, fingerprint and speech based systems serve as illustration of a mobile authentication application. A novel signal adaptive supervisor, based on the input biometric signal quality, is evaluated. Experimental results on data collected from mobile telephones are reported; they demonstrate the benefits of the proposed scheme.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124689939","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234127
A. Britto
We combine complementary features based on foreground and background information in an HMM-based classifier to recognize handwritten digits. A zoning scheme based on column and row models provides a way of dividing the digit into zones without making the features size variant. This strategy allows us to avoid the digit normalization, while it provides a way of having information from specific zones of the digit. Recognition rates around 98% have been achieved using 60,000 digit samples of the NIST SD19 database.
{"title":"Complementary features combined in an HMM-based system to recognize handwritten digits","authors":"A. Britto","doi":"10.1109/ICIAP.2003.1234127","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234127","url":null,"abstract":"We combine complementary features based on foreground and background information in an HMM-based classifier to recognize handwritten digits. A zoning scheme based on column and row models provides a way of dividing the digit into zones without making the features size variant. This strategy allows us to avoid the digit normalization, while it provides a way of having information from specific zones of the digit. Recognition rates around 98% have been achieved using 60,000 digit samples of the NIST SD19 database.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"CE-25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126541424","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234104
M. Pietikäinen, Tomi Nurmela, Topi Mäenpää, Markus Turtinen
A new method for recognizing 3D-textured surfaces is proposed. Textures are modeled with multiple histograms of micro-textons, instead of the more macroscopic textons used in earlier studies. The micro-textons are extracted with a recently proposed multiresolution local binary pattern operator. Our approach has many advantages compared to the earlier approaches and provides the leading performance in the classification of Columbia-Utrecht database (CUReT) textures imaged under different viewpoints and illumination directions. An approach for learning appearance models for view-based texture recognition using self-organization of feature distributions is also proposed.. It can be used for quickly selecting model histograms and rejecting outliers, thus providing an efficient tool for vision system training, even when the feature data has a large variability.
{"title":"View-based recognition of 3D-textured surfaces","authors":"M. Pietikäinen, Tomi Nurmela, Topi Mäenpää, Markus Turtinen","doi":"10.1109/ICIAP.2003.1234104","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234104","url":null,"abstract":"A new method for recognizing 3D-textured surfaces is proposed. Textures are modeled with multiple histograms of micro-textons, instead of the more macroscopic textons used in earlier studies. The micro-textons are extracted with a recently proposed multiresolution local binary pattern operator. Our approach has many advantages compared to the earlier approaches and provides the leading performance in the classification of Columbia-Utrecht database (CUReT) textures imaged under different viewpoints and illumination directions. An approach for learning appearance models for view-based texture recognition using self-organization of feature distributions is also proposed.. It can be used for quickly selecting model histograms and rejecting outliers, thus providing an efficient tool for vision system training, even when the feature data has a large variability.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127135180","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234122
Giuseppe Boccignone, A. Marcelli, Gaetano Somma
We address the problem of how the saccadic behavior of biological observers interacts with either unchanging and suddenly appearing elements in the scene. We show how the optical flow information can be exploited to compute an alerting map, which is then used together with a static conspicuity map to generate gaze shifts.
{"title":"Foveated analysis of video","authors":"Giuseppe Boccignone, A. Marcelli, Gaetano Somma","doi":"10.1109/ICIAP.2003.1234122","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234122","url":null,"abstract":"We address the problem of how the saccadic behavior of biological observers interacts with either unchanging and suddenly appearing elements in the scene. We show how the optical flow information can be exploited to compute an alerting map, which is then used together with a static conspicuity map to generate gaze shifts.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"137 51","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131746926","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 : 2003-09-17DOI: 10.1109/ICIAP.2003.1234054
A. Hanbury, P. Kammerer, Ernestine Zolda
A method for the elimination of cracks in infrared reflectograms is presented. Infrared reflectograms show the underdrawing - the basic concept of the artist drawn on the ground layer - in ancient wood panel paintings. Caused by the different mechanical behaviour of the panel and the covering ground layer during the aging of the painting, cracks appear. Cracks not only disturb the appearance of a painting, but are also a problem for segmenting the lines and strokes of the underdrawing. A method based on mathematical morphology, namely morphological reconstruction with viscosity, is used to eliminate the cracks while keeping as much detail as possible in the brush strokes. A priori information that the cracks are usually thinner than the brush strokes and have a preferred orientation is taken into account.
{"title":"Painting crack elimination using viscous morphological reconstruction","authors":"A. Hanbury, P. Kammerer, Ernestine Zolda","doi":"10.1109/ICIAP.2003.1234054","DOIUrl":"https://doi.org/10.1109/ICIAP.2003.1234054","url":null,"abstract":"A method for the elimination of cracks in infrared reflectograms is presented. Infrared reflectograms show the underdrawing - the basic concept of the artist drawn on the ground layer - in ancient wood panel paintings. Caused by the different mechanical behaviour of the panel and the covering ground layer during the aging of the painting, cracks appear. Cracks not only disturb the appearance of a painting, but are also a problem for segmenting the lines and strokes of the underdrawing. A method based on mathematical morphology, namely morphological reconstruction with viscosity, is used to eliminate the cracks while keeping as much detail as possible in the brush strokes. A priori information that the cracks are usually thinner than the brush strokes and have a preferred orientation is taken into account.","PeriodicalId":218076,"journal":{"name":"12th International Conference on Image Analysis and Processing, 2003.Proceedings.","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131841519","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：