Pub Date : 1992-06-15DOI: 10.1109/CVPR.1992.223265
J. Dolan, E. Riseman
A computational framework for computing curvilinear structure on the edge data of images is presented. The method is symbolic, operating on geometric entities/tokens. It is also constructive, hierarchical, parallel, and locally distributed. Computation proceeds independently at each token and at each stage interleaves the discovery of structure with its careful description. The process yields a hierarchy of descriptions at multiple scales. These multiscale descriptions provide efficient feature indexing both for the grouping process itself as well as for subsequent recognition processes. Experimental results are presented to demonstrate the effectiveness of the approach with respect to curvilinear structure, and its application to more general grouping problems is discussed.<>
{"title":"Computing curvilinear structure by token-based grouping","authors":"J. Dolan, E. Riseman","doi":"10.1109/CVPR.1992.223265","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223265","url":null,"abstract":"A computational framework for computing curvilinear structure on the edge data of images is presented. The method is symbolic, operating on geometric entities/tokens. It is also constructive, hierarchical, parallel, and locally distributed. Computation proceeds independently at each token and at each stage interleaves the discovery of structure with its careful description. The process yields a hierarchy of descriptions at multiple scales. These multiscale descriptions provide efficient feature indexing both for the grouping process itself as well as for subsequent recognition processes. Experimental results are presented to demonstrate the effectiveness of the approach with respect to curvilinear structure, and its application to more general grouping problems is discussed.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124794144","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223240
J. Vlontzos, D. Geiger
A Markov random field (MRF) formulation for the problem of optical flow computation is studied. An adaptive window matching scheme is used to obtain a good measure of the correlation between the two images. A confidence measure for each match is also used. Thus, the input to the system is the adaptive correlation and the corresponding confidence. The MRF model is then used to estimate the velocity field and the velocity discontinuities. The problem of occlusions is addressed, and a relationship between occlusions and motion discontinuities is established.<>
{"title":"A MRF approach to optical flow estimation","authors":"J. Vlontzos, D. Geiger","doi":"10.1109/CVPR.1992.223240","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223240","url":null,"abstract":"A Markov random field (MRF) formulation for the problem of optical flow computation is studied. An adaptive window matching scheme is used to obtain a good measure of the correlation between the two images. A confidence measure for each match is also used. Thus, the input to the system is the adaptive correlation and the corresponding confidence. The MRF model is then used to estimate the velocity field and the velocity discontinuities. The problem of occlusions is addressed, and a relationship between occlusions and motion discontinuities is established.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115928566","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223124
T. Kanungo, R. Haralick
Restricted domains, which are a restricted class of 2-D shapes, are defined. It is proved that any restricted domain can be decomposed as n-fold dilations of thirteen basis structuring elements and hence can be represented in a thirteen-dimensional space. This thirteen-dimensional space is spanned by the thirteen basis structuring elements comprising of lines, triangles, and a rhombus. It is shown that there is a linear transformation from this thirteen-dimensional space to an eight-dimensional space wherein a restricted domain is represented in terms of its side lengths. Furthermore, the decomposition in general is not unique, and all the decompositions can be constructed by finding the homogeneous solutions of the transformation and adding it to a particular solution. An algorithm for finding all possible decompositions is provided.<>
{"title":"Morphological decomposition of restricted domains: a vector space solution","authors":"T. Kanungo, R. Haralick","doi":"10.1109/CVPR.1992.223124","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223124","url":null,"abstract":"Restricted domains, which are a restricted class of 2-D shapes, are defined. It is proved that any restricted domain can be decomposed as n-fold dilations of thirteen basis structuring elements and hence can be represented in a thirteen-dimensional space. This thirteen-dimensional space is spanned by the thirteen basis structuring elements comprising of lines, triangles, and a rhombus. It is shown that there is a linear transformation from this thirteen-dimensional space to an eight-dimensional space wherein a restricted domain is represented in terms of its side lengths. Furthermore, the decomposition in general is not unique, and all the decompositions can be constructed by finding the homogeneous solutions of the transformation and adding it to a particular solution. An algorithm for finding all possible decompositions is provided.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115024385","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223248
W. Niblack, Phillip B. Gibbons, D. Capson
An algorithm for generating skeletons of objects in a binary image is described. The algorithm produces a well-centered skeleton with the same simple connectivity as the object, and it allows the object to be either exactly or approximately (to within a known, user-selectable error) reconstructed. Its connectivity and reconstructability properties can be rigorously proved. For approximate reconstruction, the skeleton can also be (almost always) thin and is insensitive to border noise without image prefiltering or skeleton post-pruning, while maintaining the precise error bounds for reconstruction. Because of these properties, its robustness to rotation, pleasing visual appearance, and flexibility, it is well suited for such applications as data compression, image analysis, character recognition, and circuit board inspection.<>
{"title":"Generating connected skeletons for exact and approximate reconstruction","authors":"W. Niblack, Phillip B. Gibbons, D. Capson","doi":"10.1109/CVPR.1992.223248","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223248","url":null,"abstract":"An algorithm for generating skeletons of objects in a binary image is described. The algorithm produces a well-centered skeleton with the same simple connectivity as the object, and it allows the object to be either exactly or approximately (to within a known, user-selectable error) reconstructed. Its connectivity and reconstructability properties can be rigorously proved. For approximate reconstruction, the skeleton can also be (almost always) thin and is insensitive to border noise without image prefiltering or skeleton post-pruning, while maintaining the precise error bounds for reconstruction. Because of these properties, its robustness to rotation, pleasing visual appearance, and flexibility, it is well suited for such applications as data compression, image analysis, character recognition, and circuit board inspection.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115087815","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223205
Mou-Yen Chen, A. Kundu, Jian Zhou
A complete scheme for totally unconstrained handwritten word recognition based on a single contextual hidden Markov model (HMM) is proposed. The scheme includes a morphology- and heuristics-based segmentation algorithm and a modified Viterbi algorithm that searches the (l+1)st globally best path based on the previous l best paths. The results of detailed experiments for which the overall recognition rate is up to 89.4% are reported.<>
{"title":"Off-line handwritten word recognition (HWR) using a single contextual hidden Markov model","authors":"Mou-Yen Chen, A. Kundu, Jian Zhou","doi":"10.1109/CVPR.1992.223205","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223205","url":null,"abstract":"A complete scheme for totally unconstrained handwritten word recognition based on a single contextual hidden Markov model (HMM) is proposed. The scheme includes a morphology- and heuristics-based segmentation algorithm and a modified Viterbi algorithm that searches the (l+1)st globally best path based on the previous l best paths. The results of detailed experiments for which the overall recognition rate is up to 89.4% are reported.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128939316","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223140
S. Nadabar, Anil K. Jain
A scheme for the estimation of the Markov random field (MRF) line process parameters that uses geometric CAD models of the objects in the scene is presented. The models are used to generate synthetic images of the objects from random viewpoints. The edge maps computed from the synthesized images are used as training samples to estimate the line process parameters using a least squares method. It is shown that this parameter estimation method is useful for detecting edges in range as well as intensity images.<>
{"title":"Parameter estimation in MRF line process models","authors":"S. Nadabar, Anil K. Jain","doi":"10.1109/CVPR.1992.223140","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223140","url":null,"abstract":"A scheme for the estimation of the Markov random field (MRF) line process parameters that uses geometric CAD models of the objects in the scene is presented. The models are used to generate synthetic images of the objects from random viewpoints. The edge maps computed from the synthesized images are used as training samples to estimate the line process parameters using a least squares method. It is shown that this parameter estimation method is useful for detecting edges in range as well as intensity images.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127956117","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223234
J. Hervé, Y. Aloimonos
An active approach to the integration of shape from x modules-here shape from shading and shape from texture-is proposed. The question of what constitutes a good motion for the active observer is addressed. Generally, the role of the visual system is to provide depth information to an autonomous robot; a trajectory module will then interpret it to determine a motion for the robot, which in turn will affect the visual information received. It is suggested that the motion can also be chosen so as to improve the performance of the visual system.<>
{"title":"Exploratory active vision: theory","authors":"J. Hervé, Y. Aloimonos","doi":"10.1109/CVPR.1992.223234","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223234","url":null,"abstract":"An active approach to the integration of shape from x modules-here shape from shading and shape from texture-is proposed. The question of what constitutes a good motion for the active observer is addressed. Generally, the role of the visual system is to provide depth information to an autonomous robot; a trajectory module will then interpret it to determine a motion for the robot, which in turn will affect the visual information received. It is suggested that the motion can also be chosen so as to improve the performance of the visual system.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131100753","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223200
P. Sajda, L. Finkel
The problems of object segmentation and binding are addressed within a biologically based network model capable of determining depth from occlusion. In particular, the authors discuss two subprocesses most relevant to segmentation and binding: contour binding and figure direction. They propose that these two subprocesses have intrinsic constraints that allow several underdetermined problems in occlusion processing and object segmentation to be uniquely solved. Simulations that demonstrate the role these subprocesses play in discriminating objects and stratifying them in depth are reported. The network is tested on illusory stimuli, with the network's response indicating the existence of robust psychological properties in the system.<>
{"title":"Object segmentation and binding within a biologically-based neural network model of depth-from-occlusion","authors":"P. Sajda, L. Finkel","doi":"10.1109/CVPR.1992.223200","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223200","url":null,"abstract":"The problems of object segmentation and binding are addressed within a biologically based network model capable of determining depth from occlusion. In particular, the authors discuss two subprocesses most relevant to segmentation and binding: contour binding and figure direction. They propose that these two subprocesses have intrinsic constraints that allow several underdetermined problems in occlusion processing and object segmentation to be uniquely solved. Simulations that demonstrate the role these subprocesses play in discriminating objects and stratifying them in depth are reported. The network is tested on illusory stimuli, with the network's response indicating the existence of robust psychological properties in the system.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129793518","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223160
J. Mundy, J. Noble, Constantinos Marinos, V.-D. Nguyen, Aaron J. Heller, J. Farley, A. T. Tran
The concepts and design issues that provide the basis for the I/sup 2/F (image interpretation foundations) system are described. The I/sup 2/F system combines object-oriented design for machine vision software and constraint-based geometric modeling into a flexible and effective system for automatic template-guided visual inspection. Object-oriented design for 2-D geometry-based image analysis is discussed, and results from processing experimental X-ray data are presented.<>
{"title":"An object-oriented approach to template guided visual inspection","authors":"J. Mundy, J. Noble, Constantinos Marinos, V.-D. Nguyen, Aaron J. Heller, J. Farley, A. T. Tran","doi":"10.1109/CVPR.1992.223160","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223160","url":null,"abstract":"The concepts and design issues that provide the basis for the I/sup 2/F (image interpretation foundations) system are described. The I/sup 2/F system combines object-oriented design for machine vision software and constraint-based geometric modeling into a flexible and effective system for automatic template-guided visual inspection. Object-oriented design for 2-D geometry-based image analysis is discussed, and results from processing experimental X-ray data are presented.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126464555","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223221
H. Beyer
A basic review of the bundle adjustment with self-calibration is given. The mathematical model, parameter estimation, and quality analysis of calibration and positioning are covered. The calibration procedure, hardware, and testfield of an accuracy investigation with off-the-shelf CCD (charge-coupled device) camera, lens, and frame grabber are described. A relative accuracy in object space of 1 part in 30000 and an accuracy of 1/45 in image space were verified by independent measurements with theodolites.<>
{"title":"Accurate calibration of CCD-cameras","authors":"H. Beyer","doi":"10.1109/CVPR.1992.223221","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223221","url":null,"abstract":"A basic review of the bundle adjustment with self-calibration is given. The mathematical model, parameter estimation, and quality analysis of calibration and positioning are covered. The calibration procedure, hardware, and testfield of an accuracy investigation with off-the-shelf CCD (charge-coupled device) camera, lens, and frame grabber are described. A relative accuracy in object space of 1 part in 30000 and an accuracy of 1/45 in image space were verified by independent measurements with theodolites.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123128563","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：