An Ensemble Method of Global and Local Representation for Face Recognition
Zhiyong Zeng · 2018
To aim at the challenge of face recognition to uncontrolled situations, an ensemble method of global and local representation for face recognition is presented in this paper.shearlets transform is firstly employed to decompose a image into subimages.Then directional information is utilized along with conventional scaling and translation parameters, global feature of a face image is extracted by principle component analysis.Thirdly, local feature of a face image is extracted by a deep convolutional neural network.Finally, an ensemble of global and local feature is performed by weighted score.Experimental results on two challenge face databases show that the proposed method achieved higher face recognition accuracy than art-ofthe-state methods.Hence, the ensemble of global and local feature is more potential features for the design of efficient face recognition system.