Face recognition using modular bilinear discriminant analysis

In this paper, we present a new approach for face recognition, named Modular Bilinear Discriminant Analysis (MBDA). In a first step, a set of experts is created, each one being trained independently on specific face regions using a new supervised technique named Bilinear Discriminant Analysis (BDA). BDA relies on the maximization of a generalized Fisher criterion based on bilinear projections of face image matrices. In a second step, the experts are combined to assign an identity with a confidence measure to each of the query faces. A series of experiments is performed in order to evaluate and compare the effectiveness of MBDA with respect to BDA and to the Modular Eigenspaces method. The experimental results indicate that MBDA is more effective than both BDA and the Modular Eigenspaces approach for face recognition.