Learning Hierarchical Representations for Face Recognition using Deep Belief Network Embedded with Softmax Regress and Multiple Neural Networks

Abstract

In face recognition and classification, feature extraction and classification based on insufficient labeled data is a well-known challenging problem. In this paper, a novel semi-supervised learning algorithm named deep belief network embedded with Softmax regress (DBNESR) is proposed to address this problem. DBNESR first learns hierarchical representations of feature by deep learning and then makes more efficient classification with Softmax regress. At the same time we design many kinds of classifiers based on supervised learning: BP, HBPNNs, RBF, HRBFNNs, SVM and multiple classification decision fusion classifier——hybrid HBPNNs-HRBFNNs-SVM classifier. The conducted experiments validate: Firstly, the proposed semi-supervised deep learning algorithm DBNESR is optimal for face recognition with the highest and most stable recognition rates; Second, the semi-supervised learning algorithm has better effect than all supervised learning algorithms; Third, hybrid neural networks has better effect than single neural network.