Shape contexts enable efficient retrieval of similar shapes
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Shape contexts enable efficient retrieval of similar shapes. / Mori, Greg; Belongie, Serge; Malik, Jitendra.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, 2001, p. I723-I730.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Shape contexts enable efficient retrieval of similar shapes
AU - Mori, Greg
AU - Belongie, Serge
AU - Malik, Jitendra
PY - 2001
Y1 - 2001
N2 - In this work we demonstrate that a recently introduced shape descriptor, the "shape context", can be used to quickly prune a search for similar shapes. Our representation for a shape is a discrete set of n points sampled from its internal and external contours. For each of these points, the shape context is a histogram of the relative positions of the n - 1 remaining points. We present two methods for rapid shape retrieval: one that does comparisons based on a small number of shape contexts and another that uses vector quantization in the space of shape contexts. We verify the discriminative power of these methods with tests on the Columbia (COIL-100) 3D object database and the Snod-grass and Vanderwart line drawings. The shape context-based methods are shown to quickly produce an accurate shortlist of candidates suitable for a more exact matching engine in spite of pose variation and occlusion.
AB - In this work we demonstrate that a recently introduced shape descriptor, the "shape context", can be used to quickly prune a search for similar shapes. Our representation for a shape is a discrete set of n points sampled from its internal and external contours. For each of these points, the shape context is a histogram of the relative positions of the n - 1 remaining points. We present two methods for rapid shape retrieval: one that does comparisons based on a small number of shape contexts and another that uses vector quantization in the space of shape contexts. We verify the discriminative power of these methods with tests on the Columbia (COIL-100) 3D object database and the Snod-grass and Vanderwart line drawings. The shape context-based methods are shown to quickly produce an accurate shortlist of candidates suitable for a more exact matching engine in spite of pose variation and occlusion.
UR - http://www.scopus.com/inward/record.url?scp=0035683817&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:0035683817
VL - 1
SP - I723-I730
JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
SN - 1063-6919
T2 - 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Y2 - 8 December 2001 through 14 December 2001
ER -
ID: 302058751