Automatic Parameter Determination Based on a Modified Discriminant Criterion for Face Recognition

This paper presents an Automatical Parameter Determination (APD) approach for face recognition. A modified discriminant criterion is first proposed via consideration of both Euclidean structure and the manifold structure in the face pattern space. Two parameter-formulae are derived by maximizing the discriminant index. The update equations are then obtained to automatically determine the optimal parameters and the optimal projection matrix. The proposed ADP algorithm is evaluated on the ORL face database. Compared with some state of the art approaches, the experimental results demonstrate that the proposed method gives better performance.