Both class information of face subjects and color information of face images are very important cues for recognition. In this paper, a novel class dependent color face recognition approach based on block diagonal discriminant NMF is proposed. The approach employs block diagonal matrix to encode color information of face images simultaneously. Block diagonal constraint is imposed on discriminant NMF algorithm to construct feature extraction approach, which fuses class and color information at the same time into the extracted facial features. To improve learning efficiency of the algorithm, 3D active deformable model is exploited to generate virtual face images. Experimental results on CVL and CMU PIE face databases verify the effectiveness of the proposed approach.