Face recognition using adaptive local ternary patterns method

LBP based feature descriptors have gotten encouraging performance in image recognition. As the improved versions of LBP, Local Ternary Pattern (LTP) and Center-symmetric LBP (CS-LBP) have been successfully applied to image recognition and matching. Both use a threshold to address the noise. However, it is difficult to manually set a suitable threshold in LTP and CS-LBP. Here, we propose an adaptive local feature descriptor for face recognition. First, inspired by Weber's Law, we introduce an adaptive Local Ternary Pattern (ALTP) feature descriptor based on an automatic strategy selecting the threshold for LTP; Second, based on ALTP, we further propose a center-symmetric adaptive local ternary pattern (CS-ALTP) feature description method for face recognition. CS-ALTP improves CS-LBP from two aspects: (1) An automatic threshold is proposed based on Weber's law; (2) double channel patterns are exploited to extract more discriminative information. The experiments on ORL and FERET face databases show that ALTP and CS-ALTP have good and robust recognition performance.