Local comprehensive patterns: A novel face feature descriptor

Abstract In this letter, we propose a novel face image feature extraction algorithm using local comprehensive patterns (LCP) for face feature descriptor. The traditional local binary patterns (LBP) and local ternary pattern (LTP) compute the relationship between the referenced pixel and its surrounding neighbor pixels by encoding gray-level difference. The proposed method computes the relationship between the referenced pixel and its neighbors by encoding gray-level difference based on 0°, 45°, 90°, 135°, 180°, 225°, 270°, 315° high orders direction derivatives patterns (DDP) and the direction magnitude patterns (DMP), which can extract more detailed discriminating information. Finally, both the direction derivatives patterns and the direction tendency patterns are respectively exploited to handle the feature fusion. Simulated experiments and comparisons on subsets of ORL and Yale B face databases under ideal condition, different illumination condition, different facial expression and partial occlusion show that the proposed algorithm is an outstanding method better than the LBP, the local derivative patterns, and the LTP.