Face recognition by wavelet domain associative memory

Author

Zhang, Bai-ling ; Guo, Yan

Author_Institution

Kent Ridge Digital Labs., Singapore

fYear

2001

fDate

2001

Firstpage

481

Lastpage

485

Abstract

We propose a face recognition scheme based on an auto-associative memory (AM) model. Two kinds of AM models are compared, namely, pseudo-inverse memory and radial basis function (RBF) network, and we found that RBF based associative memory is much more efficient. To capture substantial facial features and reduce computational complexity, we use a wavelet transform (WT) to decompose face images and choose the lowest resolution subband coefficients for face representation. Results indicate that the modular scheme yields accurate recognition on the widely used XM2VTS face database and Olivetti Research Laboratory (ORL) face database

Keywords

computational complexity; content-addressable storage; face recognition; feature extraction; image representation; radial basis function networks; wavelet transforms; Olivetti Research Laboratory face database; XM2VTS face database; auto-associative memory model; computational complexity; face image decomposition; face recognition scheme; face representation; facial feature capture; lowest resolution subband coefficients; pseudo-inverse memory; radial basis function network; wavelet domain associative memory; wavelet transform; Associative memory; Computational complexity; Face recognition; Facial features; Image databases; Image resolution; Laboratories; Spatial databases; Wavelet domain; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Multimedia, Video and Speech Processing, 2001. Proceedings of 2001 International Symposium on

Conference_Location

Hong Kong

Print_ISBN

962-85766-2-3

Type

conf

DOI

10.1109/ISIMP.2001.925438

Filename

925438