Multi-spectral information regarding face recognition

Author

Ticay-Rivas, Jaime R. ; Pozo-Baños, Marcos Del ; Travieso, Carlos M. ; Alonso, Jesús B. ; Ferrer, Miguel A.

Author_Institution

Signal & Commun. Dept., Univ. of Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain

fYear

2011

fDate

18-21 Oct. 2011

Firstpage

1

Lastpage

9

Abstract

Recently, hyper-spectral facial image capturing techniques have opened a new door for creating innovative techniques aiming to improve these systems features. In our work, we have developed a verification approach based on Principal Component Analysis, and doing channel fusion (data fusion), in particular 5, 13, 14, 16, 24, 33, and 34 channels, reaching an Equal Error Rate of 97.37%; showing a good behavior of the kind of images.

Keywords

computer vision; face recognition; image fusion; principal component analysis; channel fusion; computer vision; data fusion; equal error rate; face recognition; hyper-spectral facial image capturing techniques; innovative techniques; multispectral information; principal component analysis; verification approach; Databases; Discrete cosine transforms; Discrete wavelet transforms; Face; Feature extraction; Principal component analysis; Support vector machines; Face Verification; Hyper-spectral Face Image; Pattern Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Security Technology (ICCST), 2011 IEEE International Carnahan Conference on

Conference_Location

Barcelona

ISSN

1071-6572

Print_ISBN

978-1-4577-0902-9

Type

conf

DOI

10.1109/CCST.2011.6095933

Filename

6095933