Shape contexts enable efficient retrieval of similar shapes
G. Mori, S. Belongie, and J. Malik. Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings
of the 2001 IEEE Computer Society Conf. on, 1, page I----723----I----730 vol.1. (2001)
DOI: 10.1109/CVPR.2001.990547
Abstract
In this paper 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 Snodgrass 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.
%0 Conference Paper
%1 Mori2001
%A Mori, G
%A Belongie, S
%A Malik, J
%B Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings
of the 2001 IEEE Computer Society Conf. on
%D 2001
%K 3D Columbia context, contexts, database,image descriptor, discriminative engine, exact histogram, image matching object occlusion, pose power, quantisation quantization, recognition, retrieval, shape shapes similar variation, vector
%P I----723----I----730 vol.1
%R 10.1109/CVPR.2001.990547
%T Shape contexts enable efficient retrieval of similar shapes
%V 1
%X In this paper 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 Snodgrass 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.
@inproceedings{Mori2001,
abstract = { In this paper 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 Snodgrass 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.},
added-at = {2013-09-29T14:16:50.000+0200},
author = {Mori, G and Belongie, S and Malik, J},
biburl = {https://www.bibsonomy.org/bibtex/29b3e9932255e6bc1fefc2d990008b737/guillem.palou},
booktitle = {Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings
of the 2001 IEEE Computer Society Conf. on},
doi = {10.1109/CVPR.2001.990547},
interhash = {d0bf0bddbd77230c3a8329feaf45716c},
intrahash = {9b3e9932255e6bc1fefc2d990008b737},
issn = {1063-6919},
keywords = {3D Columbia context, contexts, database,image descriptor, discriminative engine, exact histogram, image matching object occlusion, pose power, quantisation quantization, recognition, retrieval, shape shapes similar variation, vector},
pages = {I----723----I----730 vol.1},
timestamp = {2013-09-29T14:16:50.000+0200},
title = {{Shape contexts enable efficient retrieval of similar shapes}},
volume = 1,
year = 2001
}