Arbitrary illumination conditions for facial identification

Author

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

Author_Institution

Univ. de Las Palmas de Gran Canaria, Las Palmas

fYear

2007

fDate

8-11 Oct. 2007

Firstpage

93

Lastpage

98

Abstract

This paper presents a simple, robust and novel for errors detection in biometric system which is applied to the Olivetti Research Laboratory (ORL) Face and Yale Databases. We have used as parameterisation different transformed dominions by James L. Wyman, et al. (2002), and a support vector machine (SVM) by Anil K. Jain, et al. (2004) as classifier. This system has been adjusted with our experiments for obtaining an false identification rate (FIR) of 0%, with a success rate of 90.8% a rejected samples rate of 9.2%.

Keywords

biometrics (access control); face recognition; support vector machines; biometric system; facial identification; illumination condition; parameterisation different transformed dominion; support vector machine; Biometrics; Face detection; Face recognition; Image databases; Lighting; Neural networks; Principal component analysis; Robustness; Support vector machine classification; Support vector machines; Biometric identification; classification system; facial recognition; neural network (NN); support vector machines (SVM);

fLanguage

English

Publisher

ieee

Conference_Titel

Security Technology, 2007 41st Annual IEEE International Carnahan Conference on

Conference_Location

Ottawa, Ont.

Print_ISBN

978-1-4244-1129-0

Type

conf

DOI

10.1109/CCST.2007.4373474

Filename

4373474