A new fusion framework for multispectral face recognition in the texture space

In this work, we introduce a new fusion framework for multispectral face recognition in the textures space. Active and passive infrared imaging modalities are used and comparison with visible face recognition is performed. The proposed texture space is based on the use of LBP (Local Binary Pattern) and LTP (Local Ternary Pattern) techniques. Also, a new adaptive texture descriptor is presented. This last descriptor called LATP (Local Adaptive Ternary Pattern) is less sensitive to noise in near uniform regions and permit to overcome some of the limitations of LBP and LTP descriptors. The obtained multispectral data are fused using a multi-scale fusion scheme in order to get interesting face characteristics. The obtained results are promising and show an increase in recognition performance when texture channels are fused in a multi-scale fusion scheme.