Title: Infrared face recognition based on LBP co-occurrence matrix and partial least squares

Authors: Zhihua Xie; Guodong Liu

Addresses: Key Lab of Optic-Electronic and Communication, Jiangxi Sciences and Technology Normal University, Nanchang, China ' Key Lab of Optic-Electronic and Communication, Jiangxi Sciences and Technology Normal University, Nanchang, China

Abstract: Infrared face recognition, being light-independent, and not vulnerable to facial skin, expressions and posture, can avoid or limit the drawbacks of face recognition in visible light. This paper proposes an infrared face recognition method based on Local Binary Pattern (LBP) co-occurrence matrix. In traditional LBP-based features such as LBP histogram, space locations information, which is an important feature for recognition, is discarded. Considering such spatial relations in infrared faces, we introduce co-occurrence matrix of LBP codes, instead of histogram, to obtain more discriminative representation for location features. To cope with the high dimensions of LBP co-occurrence matrix, the final classifier formulates Partial Least Squares (PLS) regression for accurate classification. The experimental results show combination of LBP co-occurrence matrix and PLS achieve better infrared face recognition performance compared to state-of-the-art approaches.

Keywords: LBP; local binary pattern; grey co-occurrence matrix; PLS; partial least squares; infrared face recognition; IR face recognition; biometrics; facial recognition.

DOI: 10.1504/IJWMC.2015.066758

International Journal of Wireless and Mobile Computing, 2015 Vol.8 No.1, pp.90 - 94

Received: 17 Jul 2014
Accepted: 22 Aug 2014
Published online: 04 Jan 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article