Matching shapes

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Matching shapes. / Belongie, Serge; Malik, Jitendra; Puzicha, Jan.

In: Proceedings of the IEEE International Conference on Computer Vision, Vol. 1, 2001, p. 454-461.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Belongie, S, Malik, J & Puzicha, J 2001, 'Matching shapes', Proceedings of the IEEE International Conference on Computer Vision, vol. 1, pp. 454-461. https://doi.org/10.1109/ICCV.2001.937552

APA

Belongie, S., Malik, J., & Puzicha, J. (2001). Matching shapes. Proceedings of the IEEE International Conference on Computer Vision, 1, 454-461. https://doi.org/10.1109/ICCV.2001.937552

Vancouver

Belongie S, Malik J, Puzicha J. Matching shapes. Proceedings of the IEEE International Conference on Computer Vision. 2001;1:454-461. https://doi.org/10.1109/ICCV.2001.937552

Author

Belongie, Serge ; Malik, Jitendra ; Puzicha, Jan. / Matching shapes. In: Proceedings of the IEEE International Conference on Computer Vision. 2001 ; Vol. 1. pp. 454-461.

Bibtex

@article{f7d2e36395dc4c1e9e5baffb4e530ca6,
title = "Matching shapes",
abstract = "We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by (1) solving for correspondences between points on the two shapes, (2) using the correspondences to estimate an aligning transform. In order to solve the correspondence problem, we attach a descriptor, the shape context, to each point. The shape context at a reference point captures the distribution of the remaining points relative to it, thus offering a globally discriminative characterization. Corresponding points on two similar shapes will have similar shape contexts, enabling us to solve for correspondences as an optimal assignment problem. Given the point correspondences, we estimate the transformation that best aligns the two shapes; regularized thin-plate splines provide a flexible class of transformation maps for this purpose. Dissimilarity between two shapes is computed as a sum of matching errors between corresponding points, together with a term measuring the magnitude of the aligning transform. We treat recognition in a nearest-neighbor classification framework. Results are presented for silhouettes, trademarks, handwritten digits and the COIL dataset.",
author = "Serge Belongie and Jitendra Malik and Jan Puzicha",
year = "2001",
doi = "10.1109/ICCV.2001.937552",
language = "English",
volume = "1",
pages = "454--461",
journal = "Proceedings of the IEEE International Conference on Computer Vision",
issn = "1550-5499",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - Matching shapes

AU - Belongie, Serge

AU - Malik, Jitendra

AU - Puzicha, Jan

PY - 2001

Y1 - 2001

N2 - We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by (1) solving for correspondences between points on the two shapes, (2) using the correspondences to estimate an aligning transform. In order to solve the correspondence problem, we attach a descriptor, the shape context, to each point. The shape context at a reference point captures the distribution of the remaining points relative to it, thus offering a globally discriminative characterization. Corresponding points on two similar shapes will have similar shape contexts, enabling us to solve for correspondences as an optimal assignment problem. Given the point correspondences, we estimate the transformation that best aligns the two shapes; regularized thin-plate splines provide a flexible class of transformation maps for this purpose. Dissimilarity between two shapes is computed as a sum of matching errors between corresponding points, together with a term measuring the magnitude of the aligning transform. We treat recognition in a nearest-neighbor classification framework. Results are presented for silhouettes, trademarks, handwritten digits and the COIL dataset.

AB - We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by (1) solving for correspondences between points on the two shapes, (2) using the correspondences to estimate an aligning transform. In order to solve the correspondence problem, we attach a descriptor, the shape context, to each point. The shape context at a reference point captures the distribution of the remaining points relative to it, thus offering a globally discriminative characterization. Corresponding points on two similar shapes will have similar shape contexts, enabling us to solve for correspondences as an optimal assignment problem. Given the point correspondences, we estimate the transformation that best aligns the two shapes; regularized thin-plate splines provide a flexible class of transformation maps for this purpose. Dissimilarity between two shapes is computed as a sum of matching errors between corresponding points, together with a term measuring the magnitude of the aligning transform. We treat recognition in a nearest-neighbor classification framework. Results are presented for silhouettes, trademarks, handwritten digits and the COIL dataset.

UR - http://www.scopus.com/inward/record.url?scp=0034850567&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2001.937552

DO - 10.1109/ICCV.2001.937552

M3 - Journal article

AN - SCOPUS:0034850567

VL - 1

SP - 454

EP - 461

JO - Proceedings of the IEEE International Conference on Computer Vision

JF - Proceedings of the IEEE International Conference on Computer Vision

SN - 1550-5499

ER -

ID: 302059339