DocumentCode
1296109
Title
Object recognition robust under translations, deformations, and changes in background
Author
Würtz, Rolf P.
Author_Institution
Inst. fur Neuroinf., Ruhr-Univ., Bochum, Germany
Volume
19
Issue
7
fYear
1997
fDate
7/1/1997 12:00:00 AM
Firstpage
769
Lastpage
775
Abstract
Recognition systems based on model matching using low level features often fail due to a variation in background. As a solution, I present a system for the recognition of human faces independent of hairstyle. Correspondence maps between an image and a model are established by coarse-fine matching in a Gabor pyramid. These are used for hierarchical recognition
Keywords
face recognition; parallel processing; Gabor pyramid; background change robustness; coarse-fine matching; correspondence maps; deformation robustness; hairstyle; hierarchical recognition; human face recognition; low-level features; model matching; object recognition; translation robustness; Continuous wavelet transforms; Face recognition; Fourier transforms; Frequency; Humans; Image recognition; Image sampling; Kernel; Object recognition; Robustness;
fLanguage
English
Journal_Title
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher
ieee
ISSN
0162-8828
Type
jour
DOI
10.1109/34.598234
Filename
598234
Link To Document