Fast pattern recognition using gradient-descent search in an image pyramid

Author

MacLean, James ; Tsotsos, John

Author_Institution

Dept. of Comput. Sci., Toronto Univ., Ont., Canada

Volume

2

fYear

2000

fDate

2000

Firstpage

873

Abstract

A new technique for fast pattern recognition using normalized grey-scale correlation (NGC) is described. While NGC has traditionally been slow due to computational intensity issues, the introduction of both a pyramid structure and a local estimate of the correlation surface gradient allows for recognition in 10-50 ms using modest microcomputer hardware. The algorithm is designed to analyze the target off-line prior to starting the search. Issues surrounding determining an appropriate depth for the pyramid representation and performing sub-pixel localization of the target instance are discussed. The speed and robustness of the method makes it attractive for industrial applications

Keywords

computational complexity; gradient methods; image recognition; image representation; microcomputer applications; search problems; 10 to 50 ms; NGC; computational intensity; correlation surface gradient; fast pattern recognition; gradient-descent search; image pyramid; industrial applications; normalized grey-scale correlation; pyramid representation depth; sub-pixel localization; target analysis; target instance; Algorithm design and analysis; Cameras; Computer science; Hardware; Image recognition; Manufacturing industries; Microcomputers; Pattern matching; Pattern recognition; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2000. Proceedings. 15th International Conference on

Conference_Location

Barcelona

ISSN

1051-4651

Print_ISBN

0-7695-0750-6

Type

conf

DOI

10.1109/ICPR.2000.906213

Filename

906213