Open Access Open Access  Restricted Access Subscription Access

A Fusion Face Recognition Approach Based on 7-Layer Deep Learning Neural Network


Affiliations
1 College of Computer Science and Information Engineering, Tianjin University of Science & Technology, No. 1038, DaGu Road, HeXi District, Tianjin 300222, China
 

This paper presents a method for recognizing human faces with facial expression. In the proposed approach, a motion history image (MHI) is employed to get the features in an expressive face. The face can be seen as a kind of physiological characteristic of a human and the expressions are behavioral characteristics. We fused the 2D images of a face and MHIs which were generated from the same face's image sequences with expression. Then the fusion features were used to feed a 7-layer deep learning neural network. The previous 6 layers of the whole network can be seen as an autoencoder network which can reduce the dimension of the fusion features. The last layer of the network can be seen as a softmax regression; we used it to get the identification decision. Experimental results demonstrated that our proposed method performs favorably against several state-of-the-art methods.
User
Notifications
Font Size

Abstract Views: 71

PDF Views: 0




  • A Fusion Face Recognition Approach Based on 7-Layer Deep Learning Neural Network

Abstract Views: 71  |  PDF Views: 0

Authors

Jianzheng Liu
College of Computer Science and Information Engineering, Tianjin University of Science & Technology, No. 1038, DaGu Road, HeXi District, Tianjin 300222, China
Chunlin Fang
College of Computer Science and Information Engineering, Tianjin University of Science & Technology, No. 1038, DaGu Road, HeXi District, Tianjin 300222, China
Chao Wu
College of Computer Science and Information Engineering, Tianjin University of Science & Technology, No. 1038, DaGu Road, HeXi District, Tianjin 300222, China

Abstract


This paper presents a method for recognizing human faces with facial expression. In the proposed approach, a motion history image (MHI) is employed to get the features in an expressive face. The face can be seen as a kind of physiological characteristic of a human and the expressions are behavioral characteristics. We fused the 2D images of a face and MHIs which were generated from the same face's image sequences with expression. Then the fusion features were used to feed a 7-layer deep learning neural network. The previous 6 layers of the whole network can be seen as an autoencoder network which can reduce the dimension of the fusion features. The last layer of the network can be seen as a softmax regression; we used it to get the identification decision. Experimental results demonstrated that our proposed method performs favorably against several state-of-the-art methods.