A wavelet-based method for multispectral face recognition

Yufeng Zheng; Chaoyang Zhang; Zhaoxian Zhou

doi:10.1117/12.919264

10 May 2012 A wavelet-based method for multispectral face recognition

Yufeng Zheng, Chaoyang Zhang, Zhaoxian Zhou

Proceedings Volume 8401, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X; 840105 (2012) https://doi.org/10.1117/12.919264
Event: SPIE Defense, Security, and Sensing, 2012, Baltimore, Maryland, United States

Abstract

A wavelet-based method is proposed for multispectral face recognition in this paper. Gabor wavelet transform is a common tool for orientation analysis of a 2D image; whereas Hamming distance is an efficient distance measurement for face identification. Specifically, at each frequency band, an index number representing the strongest orientational response is selected, and then encoded in binary format to favor the Hamming distance calculation. Multiband orientation bit codes are then organized into a face pattern byte (FPB) by using order statistics. With the FPB, Hamming distances are calculated and compared to achieve face identification. The FPB algorithm was initially created using thermal images, while the EBGM method was originated with visible images. When two or more spectral images from the same subject are available, the identification accuracy and reliability can be enhanced using score fusion. We compare the identification performance of applying five recognition algorithms to the three-band (visible, near infrared, thermal) face images, and explore the fusion performance of combing the multiple scores from three recognition algorithms and from three-band face images, respectively. The experimental results show that the FPB is the best recognition algorithm, the HMM yields the best fusion result, and the thermal dataset results in the best fusion performance compared to other two datasets.

Citation Download Citation

Yufeng Zheng, Chaoyang Zhang, and Zhaoxian Zhou "A wavelet-based method for multispectral face recognition", Proc. SPIE 8401, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X, 840105 (10 May 2012); https://doi.org/10.1117/12.919264

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available