Multi-subregion Face Recognition using Coarse-to-Fine Quad-tree Decomposition
Cuicui Zhang, Xuefeng Liang, Takashi Matsuyama · 2015
One problem of existing appearance-based face recognition methods (e.g. PCA, LDA) is their weak ability of coping with local variations caused by fa-cial expressions, motion deformation, data missing, etc. Multi-subregion fusion methods, which divide the face into a set of subregions, aim at this issue, and were re-ported a better performance. However, it leaves two open questions: 1. what subregions are good partitions on the face, and 2. How to fuse these subregions could achieve the expected performance. In this paper, we ad-dress these two questions and propose a local discrimi-nation driven face partition method based on a coarse-to-fine Quad-tree decomposition. Unlike other multi-subregion approaches relying on prior knowledge, our method partitions the face according to the data prop-erty. Thus, it can adapt to varied databases. Mean-while, our method introduces an optimized solution that fuses selected subregions to reach higher recognition accuracy. The cross-database experiments including one 3D database and three 2D databases demonstrate the efficiency and effectiveness of the proposed method. 1.