This work proposes a multi-spectral face recognition system in an uncontrolled environment, aiming to identify or authenticate identities (people) through their facial images. Face recognition systems in uncontrolled environments have shown impressive performance improvements over recent decades. However, most are limited to the use of a single spectral band in the visible spectrum. The use of multi-spectral images makes it possible to collect information that is not obtainable in the visible spectrum when certain occlusions exist (e.g., fog or plastic materials) and in low- or no-light environments. The proposed work uses the scores obtained by face recognition systems in different spectral bands to make a joint final decision in identification. The evaluation of different methods for each of the components of a face recognition system allowed the most suitable ones for a multi-spectral face recognition system in an uncontrolled environment to be selected. The experimental results, expressed in Rank-1 scores, were 99.5% and 99.6% in the TUFTS multi-spectral database with pose variation and expression variation, respectively, and 100.0% in the CASIA NIR-VIS 2.0 database, indicating that the use of multi-spectral images in an uncontrolled environment is advantageous when compared with the use of single spectral band images.
Keywords: deep neural networks; face recognition; in the wild; multispectral imaging.