Efficient shape matching using shape contexts
Research output: Contribution to journal › Journal article › Research › peer-review
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.
Original language | English |
---|---|
Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 27 |
Issue number | 11 |
Pages (from-to) | 1832-1837 |
Number of pages | 6 |
ISSN | 0162-8828 |
DOIs | |
Publication status | Published - Nov 2005 |
Externally published | Yes |
Bibliographical note
Funding Information:
Portions of this paper appeared in previous publications [35], [33]. Greg Mori was supported by grants from NSERC (RGPIN-312230) and the SFU President’s Research Fund. Serge Belongie was supported by US National Science Foundation CAREER #0448615, The Alfred P. Sloan Research Fellowship, and through subcontracts B542001 and B547328 under the auspices of the US Department of Energy by the Lawrence Livermore National Laboratory under contract No. W-7405-ENG-48. The authors thank the anonymous reviewers for their useful suggestions.
- Object recognition, Optical character recognition, Shape
Research areas
ID: 302054912