Determining the similarity of deformable shapes

Ronen Basri, Luiz Costa, Davi Geiger, David Jacobs

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publicationProc Workshop Phys Based Model Computer Vision
Editors Anon
PublisherIEEE
Pages135-143
Number of pages9
StatePublished - 1995
EventProceedings of the Workshop on Physics-Based Modeling in Computer Vision - Cambridge, MA, USA
Duration: Jun 18 1995Jun 19 1995

Other

OtherProceedings of the Workshop on Physics-Based Modeling in Computer Vision
CityCambridge, MA, USA
Period6/18/956/19/95

Fingerprint

Cost functions
Dynamic programming
Computer vision
Costs
Decomposition
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Basri, R., Costa, L., Geiger, D., & Jacobs, D. (1995). Determining the similarity of deformable shapes. In Anon (Ed.), Proc Workshop Phys Based Model Computer Vision (pp. 135-143). IEEE.

Determining the similarity of deformable shapes. / Basri, Ronen; Costa, Luiz; Geiger, Davi; Jacobs, David.

Proc Workshop Phys Based Model Computer Vision. ed. / Anon. IEEE, 1995. p. 135-143.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Basri, R, Costa, L, Geiger, D & Jacobs, D 1995, Determining the similarity of deformable shapes. in Anon (ed.), Proc Workshop Phys Based Model Computer Vision. IEEE, pp. 135-143, Proceedings of the Workshop on Physics-Based Modeling in Computer Vision, Cambridge, MA, USA, 6/18/95.
Basri R, Costa L, Geiger D, Jacobs D. Determining the similarity of deformable shapes. In Anon, editor, Proc Workshop Phys Based Model Computer Vision. IEEE. 1995. p. 135-143
Basri, Ronen ; Costa, Luiz ; Geiger, Davi ; Jacobs, David. / Determining the similarity of deformable shapes. Proc Workshop Phys Based Model Computer Vision. editor / Anon. IEEE, 1995. pp. 135-143
@inproceedings{052c227e4c1f47a6a5e200e92111a89d,
title = "Determining the similarity of deformable shapes",
abstract = "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.",
author = "Ronen Basri and Luiz Costa and Davi Geiger and David Jacobs",
year = "1995",
language = "English (US)",
pages = "135--143",
editor = "Anon",
booktitle = "Proc Workshop Phys Based Model Computer Vision",
publisher = "IEEE",

}

TY - GEN

T1 - Determining the similarity of deformable shapes

AU - Basri, Ronen

AU - Costa, Luiz

AU - Geiger, Davi

AU - Jacobs, David

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 - Conference contribution

SP - 135

EP - 143

BT - Proc Workshop Phys Based Model Computer Vision

A2 - Anon, null

PB - IEEE

ER -