TY - CONF
T1 - Determining the similarity of deformable shapes
AU - Basri, Ronen
AU - Costa, Luiz
AU - Geiger, Davi
AU - Jacobs, David
N1 - Funding Information:
The authors would like to thank Warren Smith for several helpful suggestions. The vision group at the Weizmann Institute is supported in part by the Israeli Ministry of Science, Grant No. 8504. R. Basri is an incumbent of Arye Dissentshik Career Development Chair at the Weizmann Institute. D. Geiger was supported by AFOSR under F 49620-96-1-0159 and F 49620-96-1-0028 and a CAREER award from the NSF.
PY - 1995
Y1 - 1995
N2 - We study how to measure the degree of similarity between two image contours. We propose an approach for comparing contours that takes into account deformations in object shape, the articulation of parts, and variations in the shape and size of portions of objects. Our method uses dynamic programming to compute the minimum cost of bringing one shape into the other via local deformations. Using this as a starting point, we investigate the properties that such a cost function should have to model human performance and to perform usefully in a computer vision system. We suggest novel conditions on this cost function that help capture the part-based nature of objects without requiring any explicit decomposition of shapes into their parts. We then suggest several possible cost functions based on different physical models of contours, and describe experiments with these costs.
AB - We study how to measure the degree of similarity between two image contours. We propose an approach for comparing contours that takes into account deformations in object shape, the articulation of parts, and variations in the shape and size of portions of objects. Our method uses dynamic programming to compute the minimum cost of bringing one shape into the other via local deformations. Using this as a starting point, we investigate the properties that such a cost function should have to model human performance and to perform usefully in a computer vision system. We suggest novel conditions on this cost function that help capture the part-based nature of objects without requiring any explicit decomposition of shapes into their parts. We then suggest several possible cost functions based on different physical models of contours, and describe experiments with these costs.
UR - http://www.scopus.com/inward/record.url?scp=0029234786&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029234786&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0029234786
SP - 135
EP - 143
T2 - Proceedings of the Workshop on Physics-Based Modeling in Computer Vision
Y2 - 18 June 1995 through 19 June 1995
ER -