2D Face recognition on IV² database by Steerable pyramid and LDA

Abstract : In this communication, we investigate the 2D Face recognition problem by combining two different methods: an appearance-based projective method : Linear Discriminant Analysis (LDA); and a multiresolution one: Steerable Pyramid (SP). Many fusion strategies have been elaborated and tested on IV² database including challenging variability such as pose, expression, illumination and quality. Results of proposed method were then compared to those related to five algorithms submitted in the first evaluation campaign on 2D face recognition using IV² database. Proposed algorithm is always among the two best ones.