Share Email Print
cover

Proceedings Paper

A wavelet-based method for multispectral face recognition
Author(s): Yufeng Zheng; Chaoyang Zhang; Zhaoxian Zhou
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 10 May 2012
PDF: 12 pages
Proc. SPIE 8401, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X, 840105 (10 May 2012); doi: 10.1117/12.919264
Show Author Affiliations
Yufeng Zheng, Alcorn State Univ. (United States)
Chaoyang Zhang, Univ. of Southern Mississippi (United States)
Zhaoxian Zhou, Univ. of Southern Mississippi (United States)


Published in SPIE Proceedings Vol. 8401:
Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering X
Harold Szu, Editor(s)

© SPIE. Terms of Use
Back to Top