Facial identification using transformed domain by SVM

Author

Travieso, Carlos M. ; Alonso, Jestis B. ; Ferrer, Miguel A.

Author_Institution

Dpto. de Senales y Comunicaciones, Univ. de Las Palmas de Gran Canada Campus de, Las Palmas de Gran Canaria, Spain

fYear

2004

fDate

11-14 Oct. 2004

Firstpage

321

Lastpage

324

Abstract

In this paper, we propose a facial biometric identification system, using transformed domains such as discrete cosine transforms (DCT), fast Fourier transforms (FFT) and discrete wavelets transforms (DWT). As novel classifier system has been utilized a support vector machines (SVM) (Burges, 1998), and in addition, the way of computing transformed coefficients. With the above system, it has been obtained a simple and robust system with good results, upper to 98% with the ORL face database (400 images) from Olivetti Research Laboratory.

Keywords

discrete cosine transforms; discrete wavelet transforms; face recognition; fast Fourier transforms; support vector machines; ORL face database; Olivetti Research Laboratory; classifier system; discrete cosine transforms; discrete wavelets transforms; facial biometric identification system; facial identification; fast Fourier transforms; support vector machines; transformed domain; Biometrics; Discrete Fourier transforms; Discrete cosine transforms; Discrete wavelet transforms; Fast Fourier transforms; Image databases; Robustness; Support vector machine classification; Support vector machines; Wavelet domain;

fLanguage

English

Publisher

ieee

Conference_Titel

Security Technology, 2004. 38th Annual 2004 International Carnahan Conference on

Print_ISBN

0-7803-8506-3

Type

conf

DOI

10.1109/CCST.2004.1405412

Filename

1405412