Share Email Print

Journal of Electronic Imaging

GB(2D)2 PCA-based convolutional network for face recognition
Author(s): Min Jiang; Ruru Lu; Jun Kong; Xiao-Jun Wu; Hongtao Huo; Xiaofeng Wang
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Face recognition is a challenging task in computer vision. Numerous efforts have been made to design low-level hand-crafted features for face recognition. Low-level hand-crafted features highly depend on prior knowledge, which is difficult to obtain without learning new domain knowledge. Recently, ConvNets have generated great attention for their ability of feature learning and achieved state-of-the-art results on many computer vision tasks. However, typical ConvNets are trained by a gradient descent method in supervised mode, which results in high computational complexity. To solve this problem, an efficient unsupervised deep learning network is proposed for face recognition in this paper, which combines both 2-D Gabor filters and ( 2 D ) 2 PCA to learn the multistage convolutional filters. To speed up the calculation, the learned high-dimensional features are further encoded using short binary hashes. Finally, the obtained output features are trained using LinearSVM. Extensive experimental results on several facial benchmark databases show that the proposed network can obtain competitive performance and robust distortion-tolerance for face recognition.

Paper Details

Date Published: 1 March 2017
PDF: 14 pages
J. Electron. Imag. 26(2) 023001 doi: 10.1117/1.JEI.26.2.023001
Published in: Journal of Electronic Imaging Volume 26, Issue 2
Show Author Affiliations
Min Jiang, Jiangnan Univ. (China)
Ruru Lu, Jiangnan Univ. (China)
Jun Kong, Jiangnan Univ. (China)
Xinjiang Univ. (China)
Xiao-Jun Wu, Jiangnan Univ. (China)
Hongtao Huo, Chinese People's Public Security Univ. (China)
Xiaofeng Wang, Jiangnan Univ. (China)

© SPIE. Terms of Use
Back to Top