Decision fusion for block linear regression classification based on confidence index

We consider the problem of recognizing human faces with varying expression and illumination, and a novel confidence index based block linear regression classification method is proposed. Our approach divides images into blocks, and each block is identified using the linear regression classifier separately. We develop a confidence index model to measure the recognition confidence of each block, and the final decision is achieved by aggregating individual results with the designed Bayesian decision fusion algorithm. The performances of our approach and conventional algorithms are evaluated under conditions of varying expression and illumination using benchmark databases, improvements demonstrate the proposed approach is robustness to both expression and illumination variations.