Face Recognition Based on Correlation of Wavelet Transform Images

Author

Zhao, Lihong ; Cai, Yu ; Xu, Xinhe

Author_Institution

Coll. of Inf. Sci. & Eng., Northeastern Univ., Shenyang

Volume

2

fYear

0

fDate

0-0 0

Firstpage

10106

Lastpage

10110

Abstract

Face recognition is a very challenging research topic because variations can be introduced to the pattern of a face by varying pose, lighting, and expression. A new face recognition approach using correlation of wavelet transform images is presented. Using this technique, wavelet transform is applied on images before using images correlation for matching the face representation. The representation used for each face is computed from the mean wavelet transform images and the testing image. The computation time required for recognition is very short. Recognition rate is 98.5% using the ORL database using 5 training images and 5 testing images per person

Keywords

face recognition; wavelet transforms; face pattern; face recognition; image correlation; wavelet transform; Educational institutions; Face recognition; Hidden Markov models; Image databases; Image recognition; Information science; Intelligent control; Pattern recognition; Testing; Wavelet transforms; face recognition; images correlation; template face; wavelet transform;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on

Conference_Location

Dalian

Print_ISBN

1-4244-0332-4

Type

conf

DOI

10.1109/WCICA.2006.1713977

Filename

1713977