Abstract:
Biometric authentication based on face recognition acquired enormous attention due to its non-intrusive nature of image capture. Recently, with the advancement in sensor technology, face recognition based on Multi-spectral imaging has gained lot of popularity due to its potential of capturing discrete spatio-spectral images across the electro- magnetic spectrum. Our contribution here is to study empirically, the extensive comparative performance analysis of 22 photometric illumina- tion normalization techniques for robust Multi-spectral face recognition. To evaluate this study, we developed a Multi-spectral imaging sensor that can capture Multi-spectral facial images across nine different spec- tral band in the wavelength range from 530nm to 1000nm. With the developed sensor we captured Multi-spectral facial database for 231 in- dividuals, which will be made available in the public domain for the researcher community. Further, quantitative experimental performance analysis in the form of identification rate at rank 1, was conducted on 22 photometric normalization techniques using four state-of-the-art face recognition algorithms. The performance analysis indicates outstanding results with utmost all of the photometric normalization techniques for six spectral bands such as 650nm, 710nm, 770nm, 830nm, 890nm, 950nm.
