Membership degree fusion of DCT and LGBPH based face recognition approach for single sample problem
Xiaowei Liu, Jin-Quan Xiong, Zhihua Xie · 2013
For single sample face recognition, the approaches based on statistical learning are always suffering from the generalizability problem because of small samples. This paper proposes a novel non-statistics features extraction approach based on fusion of global and local features. The global and low frequency features are obtained by low frequency coefficients of discrete cosine transform (DCT). The local and high frequency features are extracted by LGBPH. To integrate the global and local features, the final recognition can be achieved by parallel integration of classification results of the global and local features. The membership degree is defined to integrate local classifier and global classifier. The experimental results on ORL face databases show that the global face and local information can be integrated well after membership degree fusion by global and local features, and this improves the performance of single sample face recognition. Meanwhile, the proposed single sample face recognition method outperforms the methods based on DCT+LDA, LGBPH or traditional fusion.