Best wavelength selection for Gabor wavelet using GA for EBGM algorithm

Author

Sigari, Mohamad Hoseyn

Author_Institution

Ferdowsi Univ. of Mashad, Mashad

fYear

2007

fDate

28-29 Dec. 2007

Firstpage

35

Lastpage

39

Abstract

In this paper a new method for optimization of elastic bunch graph matching (EBGM) algorithm in frontal face recognition is presented. In EBGM algorithm, some pre-determined wavelength of Gabor wavelet is used to extract features from face image. For optimization of EBGM algorithm, genetic algorithm (GA) is used to select the best wavelengths of Gabor wavelet. For evaluation, algorithm has been tested on 300 classes of FERET face database. In training phase, only one image per class is trained. The recognition rate of optimized EBGM is about 91%. Also the optimized EBGM can run 1.5 times faster than original EBGM.

Keywords

face recognition; feature extraction; genetic algorithms; graph theory; image matching; wavelet transforms; EBGM algorithm; Gabor wavelet; best wavelength selection; elastic bunch graph matching; feature extraction; frontal face recognition; genetic algorithm; optimization; Biometrics; Face recognition; Feature extraction; Genetic algorithms; Humans; Image databases; Image recognition; Independent component analysis; Principal component analysis; Spatial databases; Elastic Bunch Graph Matching (EBGM); Face Recognition; Gabor Wavelet; Genetic Algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Vision, 2007. ICMV 2007. International Conference on

Conference_Location

Islamabad

Print_ISBN

978-1-4244-1624-0

Electronic_ISBN

978-1-4244-1625-7

Type

conf

DOI

10.1109/ICMV.2007.4469269

Filename

4469269