Abstract: In order to overcome the defects that the face recognition accuracy can be greatly reduced in the uncontrolled environments such as the change of illumination, occlusion, and posture, etc, an uniform local binary pattern ＆ sparse representation face recognition algorithm based on Gabor phase and amplitude was proposed. In the proposed algorithm, the Gabor phase and amplitude images of a face image are obtained via Gabor filter, then uniform local binary histogram is extracted via block, finally the test image can be classified as the existing class via sparse representation. The experimental results based on AR face database show that the proposed algorithm has the highest face recognition accuracy in the existing uncontrolled environments comparison with the SRC（sparse representation-based classifier） face recognition algorithm, and face segmentation recognition algorithm based on LBP and SRC.