Expression-robust 3D face recognition using LBP representation

In this paper, we develop a novel 3D face recognition algorithm based on Local Binary Pattern (LBP) representation under expression varieties. First, to enable the application of LBP representation framework, a special feature-based 3D face division scheme is proposed. Then, the LBP framework for 3D face representation is described, and the facial depth and normal information are extracted and encoded by LBP operator, to weaken the expression effect. For each face region, the statistical histogram is utilized to represent the 3D face, and accordingly three matching strategies are presented to address the recognition task. Finally, We test the proposed 3D face recognition algorithm on BJUT-3D database, achieve encouraging results, and conclude that it is feasible to apply the LBP framework on 3D face recognition.