Block independent component analysis for face recognition
块独立成分分析的人脸识别

This paper presented a subspace algorithm called Block Independent Component Analysis (B-ICA) for face recognition. Unlike the traditional ICA, in which the whole face image is transformed into a vector before calculating the independent components (ICs), B-ICA partitions the facial images into blocks and stretches the block to a vector, which is taken as the training vector. Since the dimensionality of the training vector in B-ICA is much smaller than that in traditional ICA, it can reduce the face recognition error caused by the dilemma in ICA, i.e. the number of available training samples is greatly less than that of the dimension of training vector. Extensive experiments are performed on the well-known Yale and AR databases to validate the proposed method and the experimental results show that the B-ICA achieves higher recognition accuracy than ICA and other existing subspace methods.