Efficient shape matching using shape contexts

descriptionPublicationkeyboard_double_arrow_right Article 01 Nov 2005Publisher:Institute of Electrical and Electronics Engineers (IEEE)Journal:IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 27, pages 1,832-1,837 (issn: 0162-8828,

Copyright policy )

Authors: Greg Mori; Serge J. Belongie; Jitendra Malik;

doi: 10.1109/tpami.2005.220

pmid: 16285381

Efficient shape matching using shape contexts

- Summary
- Subjects
- Metrics

Abstract

We demonstrate that shape contexts can be used to quickly prune a search for similar shapes. We present two algorithms for rapid shape retrieval: representative shape contexts, performing comparisons based on a small number of shape contexts, and shapemes, using vector quantization in the space of shape contexts to obtain prototypical shape pieces.

Related Organizations

University of California, San Diego
United States
Simon Fraser University
Canada
University of California, Berkeley
United States

Keywords

Information Storage and Retrieval, Numerical Analysis, Computer-Assisted, Signal Processing, Computer-Assisted, Image Enhancement, Pattern Recognition, Automated, User-Computer Interface, Imaging, Three-Dimensional, Artificial Intelligence, Subtraction Technique, Image Interpretation, Computer-Assisted, Computer Graphics, Algorithms

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	307
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Top 1%
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Top 0.1%
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Top 10%