DocumentCode
3429417
Title
Face Recognition Using Multiscale Gabor Wavelet
Author
Huang, Lin ; Zhang, Wenjing
Author_Institution
Florida Atlantic Univ., Boca Raton
fYear
2007
fDate
22-24 Aug. 2007
Firstpage
280
Lastpage
283
Abstract
This paper proposes and analyzes multiscale Gabor wavelet and eigenface method for face recognition. The face images are processed by using one-dimensional (1D) filter masks to extract the Gabor features without two-dimensional (2D) Fourier transform. The results of analysis and experiments show that the computational cost and the storage amount of Gabor features in PGE method are significantly lower than the ones in general 2D Gabor wavelet methods with a comparable recognition rate.
Keywords
Gabor filters; eigenvalues and eigenfunctions; face recognition; feature extraction; wavelet transforms; 1D filter masks; Gabor features extraction; face recognition; pyramidal Gabor wavelet eigenface; Computational efficiency; Face recognition; Feature extraction; Filtering; Fourier transforms; Frequency; Gabor filters; Image representation; Wavelet analysis; Wavelet transforms;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications, Computers and Signal Processing, 2007. PacRim 2007. IEEE Pacific Rim Conference on
Conference_Location
Victoria, BC
Print_ISBN
978-1-4244-1189-4
Electronic_ISBN
1-4244-1190-4
Type
conf
DOI
10.1109/PACRIM.2007.4313229
Filename
4313229
Link To Document