3D local derivative pattern for hyperspectral face recognition

Jie Liang, Jun Zhou, Yongsheng Gao
2015 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
Traditional 2D face recognition has been studied for many years and has achieved huge success. Nonetheless, there is high demand to explore unrevealed information other than structure and texture in spatial domain in the faces. Hyperspectral imaging meets such requirements by providing additional spectrum information on objects, in completion to the traditional spatial features extracted in 2D images. In this paper, we propose a novel 3D high-order texture pattern descriptor for hyperspectral
more » ... ce recognition, which effectively exploit both spatial and spectral features in hyperspectral images. Based on the local derivative pattern, our method encodes the hyperspectral faces with multi-directional derivatives and binarization function in spatial-spectral space. Then a spatialspectral feature descriptor is generated by applying a 3D histogram on the derivative pattern, which can be used to convert hyperspectral face images into vectorized representations. Compared to traditional face recognition methods, our method is able to describe the distinctive micro-patterns which integrate the potential spatial and spectral information in faces. Experiments on the real hyperspectral face databases prove that our method has outperformed several state-of-theart hyperspectral face recognition approaches.
doi:10.1109/fg.2015.7163115 dblp:conf/fgr/LiangZG15 fatcat:qyl464k6tveszapvpgag3bweau