Multi-modal face recognition

In this paper, we exploit the multi-modal face recognition capability by a comparative study on 8 fusion methods in the score level, including Sum, Product, Max, Min, Decision Template (DT), Dempster-Shafer Rule (DS), Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) methods. Our experiments are based on the CASIA 3D Face Database and can be divided into two modes: verification and classification. Major conclusions are: (1) 2D modality can achieves similar performance as to 3D modality, and fusion scheme can substantially improve the recognition performance; (2) Product rule gives the best recognition performance in the simple fusion methods without training stage; (3) There is no guarantee that the complicated fusion methods with training stage will achieve better recognition performance than the simple fusion methods, and it is important to select the most suitable model for fusion according to the tasks.