GB(2D)2 PCA-based convolutional network for face recognition

Min Jiang; Ruru Lu; Jun Kong; Xiao-Jun Wu; Hongtao Huo; Xiaofeng Wang

doi:10.1117/1.JEI.26.2.023001

1 March 2017 GB(2D)² PCA-based convolutional network for face recognition

Min Jiang, Ruru Lu, Jun Kong, Xiao-Jun Wu, Hongtao Huo, Xiaofeng Wang

Author Affiliations +

Journal of Electronic Imaging, Vol. 26, Issue 2, 023001 (March 2017). https://doi.org/10.1117/1.JEI.26.2.023001

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 (2D)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.

Citation Download Citation

Min Jiang, Ruru Lu, Jun Kong, Xiao-Jun Wu, Hongtao Huo, and Xiaofeng Wang "GB(2D)² PCA-based convolutional network for face recognition," Journal of Electronic Imaging 26(2), 023001 (1 March 2017). https://doi.org/10.1117/1.JEI.26.2.023001

Received: 11 July 2016; Accepted: 7 February 2017; Published: 1 March 2017

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available