Face recognition based on multi-level histogram sequence center-symmetric local binary pattern and fisherface
Xiaoyu Xu, Li Ping Su, Lan Liu · 2017
The high dimension and large computational complexity are shortcomings of feature extraction in multi-level histogram sequence local binary pattern (M-HSLBP). In order to overcome those problems, a face recognition algorithm based on the combination of multi-level histogram sequence center-symmetric local binary pattern (M-HCSLBP) and Fisherface is proposed in this paper. First, CS-LBP algorithm is employed on face images, then utilizing multi-level feature extraction, the corresponding histogram features are obtained. Next, feature reduction was conducted by Fisherface algorithm. Finally, the nearest neighbor classifier was used for classification and recognition. Experiments are implemented on ORL, Yale and GT face databases to compare the recognition rate of ten algorithms, which show that the proposed algorithm has the highest recognition rate and the best robustness.