Face recognition by elastic bunch graph matching

Author

Wiskott, Laurenz ; Fellous, Jean-Marc ; Krüger, Norbert ; von der Malsburg, Christoph

Author_Institution

Inst. fur Neuroinf., Ruhr-Univ., Bochum, Germany

Volume

1

fYear

1997

fDate

26-29 Oct 1997

Firstpage

129

Abstract

We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled graphs, based on a Gabor wavelet transform. Image graphs of new faces are extracted by an elastic graph matching process and can be compared by a simple similarity function. The system differs from Lades et al. (1993) in three respects. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small set of sample image graphs

Keywords

data structures; face recognition; graph theory; image matching; wavelet transforms; Gabor wavelet transform; data structure; elastic bunch graph matching; elastic graph matching process; face recognition; human faces; image graph extraction; labeled graphs; node positioning; object-adapted graphs; phase information; rotations; sample image graphs; similarity function; Data mining; Data structures; Face recognition; Frequency; Image databases; Image recognition; Integral equations; Kernel; Wavelet coefficients; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1997. Proceedings., International Conference on

Conference_Location

Santa Barbara, CA

Print_ISBN

0-8186-8183-7

Type

conf

DOI

10.1109/ICIP.1997.647401

Filename

647401