Bayesian sample steered discriminative regression for biometric image classification

The flow chart of the proposed BSDR algorithm. Using the method described in Section 3.2, the target response vector for each class k can be computed. Then the linear mapping function for class k can be obtained. With all the wˆk computed, the linear mapping matrix can be obtained by W = [wˆ1, …, wˆK]. For a test sample y, its labeling feature can be extracted by ry = WTy. Classification can be done by NNC with cosine distance.