Face recognition based on Wavelet and Fourier transform

Author

Lihong, Zhao ; Yanan, Tian ; Xili, Zhang

Author_Institution

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

fYear

2008

fDate

2-4 July 2008

Firstpage

4225

Lastpage

4229

Abstract

Processing of the face image in the transform domain can remove the noise by the change of illumination and camera. So a method presented in this paper is based on wavelet and Fourier transform. Facial features are obtained by combining discrete wavelet transform with Fourier transform. And they are classified by the Nearest-Neighbor classifier with the similarity metric of Euclidean distance and correlation coefficient. Experiments are made in ORL and YALE face image databases. The experimental results show that the proposed method is simple, fast and effective for the face recognition.

Keywords

Fourier transforms; discrete wavelet transforms; face recognition; pattern classification; Euclidean distance; Fourier transform; correlation coefficient; discrete wavelet transform; face image processing; face recognition; facial features; nearest neighbor classifier; similarity metric; transform domain; Cameras; Discrete Fourier transforms; Discrete transforms; Discrete wavelet transforms; Euclidean distance; Face recognition; Facial features; Fourier transforms; Image databases; Lighting; Fourier transform; face recognition; spectrofaces; wavelet transform;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference, 2008. CCDC 2008. Chinese

Conference_Location

Yantai, Shandong

Print_ISBN

978-1-4244-1733-9

Electronic_ISBN

978-1-4244-1734-6

Type

conf

DOI

10.1109/CCDC.2008.4598125

Filename

4598125