Fast recognition using adaptive subdivisions of transformation space

An algorithm, RAST, for solving the bounded error recognition problem efficiently using adaptive subdivisions of transformation space, is presented. The RAST algorithm uses no heuristics and loses no solutions. It is a simple, efficient algorithm combining the ideas of multiresolution matching, Houg...

Full description

Saved in:
Bibliographic Details
Published inProceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 445 - 451
Main Author Breuel, T.M.
Format Conference Proceeding
LanguageEnglish
Published IEEE Comput. Soc. Press 1992
Subjects
Artificial intelligence
Biological system modeling
Clustering algorithms
Contracts
Heuristic algorithms
Image recognition
Laboratories
Object recognition
Polynomials
Solid modeling
Online AccessGet full text

Cover

More Information
Summary:An algorithm, RAST, for solving the bounded error recognition problem efficiently using adaptive subdivisions of transformation space, is presented. The RAST algorithm uses no heuristics and loses no solutions. It is a simple, efficient algorithm combining the ideas of multiresolution matching, Hough transform, search-based recognition, and bounded error recognition. Its performance is better than that of alignment and Hough transform methods, and, as opposed to these methods; RAST finds solutions satisfying simple, well-defined bounded error criteria.< >
ISBN:9780818628559
0818628553
ISSN:1063-6919
DOI:10.1109/CVPR.1992.223152