Infrared face recognition based on co-occurrence histogram of multi-scale local binary patterns

Xie Zhihua; Liu Guodong

Different scales local binary patterns (LBP) extract different micro-structures, which contain important discriminative information for infrared face recognition. To capture the correlation between different scales, a new infrared face recognition method based on multi-scale LBP co-occurrence histogram was proposed in this paper. In traditional multi-scale LBP-based features, correlation in different micro-structures was ignored. To consider such correlation in infrared faces, co-occurrence histogram of multi-scale LBP codes was used to represent the infrared face. Multi-scale LBP co-occurrence histogram not only preserved great invariance to environmental temperature, but also greatly enhanceed the discriminative power of the descriptor as co-occurrence matrix of LBP code well captureed the correlation between different scale micro-structures around the same central point. The experimental results show the recognition rates of infrared face recognition method based on multi-scale LBP co-occurrence histogram can reaches 99.2% under same condition and 91.2% under variable ambient temperatures, outperform that of the classic methods based on LBP and multi-scale LBP histogram.

1. Key Lab of Optic-Electronic and Communication,Jiangxi Sciences and Technology Normal University,Nanchang 330013,China

Received Date: 2014-05-10

Rev Recd Date: 2014-06-12

Publish Date: 2015-01-25

Key words:

Abstract: Different scales local binary patterns (LBP) extract different micro-structures, which contain important discriminative information for infrared face recognition. To capture the correlation between different scales, a new infrared face recognition method based on multi-scale LBP co-occurrence histogram was proposed in this paper. In traditional multi-scale LBP-based features, correlation in different micro-structures was ignored. To consider such correlation in infrared faces, co-occurrence histogram of multi-scale LBP codes was used to represent the infrared face. Multi-scale LBP co-occurrence histogram not only preserved great invariance to environmental temperature, but also greatly enhanceed the discriminative power of the descriptor as co-occurrence matrix of LBP code well captureed the correlation between different scale micro-structures around the same central point. The experimental results show the recognition rates of infrared face recognition method based on multi-scale LBP co-occurrence histogram can reaches 99.2% under same condition and 91.2% under variable ambient temperatures, outperform that of the classic methods based on LBP and multi-scale LBP histogram.

HTML

Reference (43)

[1]	Wu S Q, Li W S, Xie S L. Skin heat transfer model of facial thermograms and its application in face recognition[J]. Pattern Recognition, 2008, 41(8): 2718-2729.
[2]
[3]	Li J, Yu D W, Kuang G. The research on face recognition approaches of infrared imagery [J]. Journal of National University of Defense Technology, 2006, 28(2): 73-76.
[4]
[5]	Wu S Q, Fang Z J, Xie Z H, et al. Recent advances in face recognition[M]. Croatia: IN-TECH press, 2008, 184-206.
[6]
[7]
[8]	Hermosilla G. A comparative study of thermal face recognition methods in unconstrained environments [J]. Pattern Recognition, 2012, 45(7): 2445-2459.
[9]	Li Stan Z, Chu Rufeng, Cai Liaosheng, et al. Illumination invariant face recognition using near-infrared images [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(12): 627-639.
[10]
[11]	Hua S G, Zhou Y, Liu T. PCA+LDA Based thermal infrared imaging face recognition [J]. Pattern Recognition and Artificial Intelligence, 2008, 21(2): 160-164.
[12]
[13]	Ahonen T, Hadid A, Pietikinen M. Face description with local binary patterns: application to face recognition [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2006, 18(12): 2037-2041.
[14]
[15]
[16]	Ojala T, Pietikinen M. Multi-resolution, gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.
[17]
[18]	Zhang Baochang, Shan Shiguang, Gao Wen. Histogram of gabor phase patterns (HGPP): a novel object representation approach for face recognition [J]. IEEE Trans on Image Processing, 2007, 16(1): 57-68.
[19]
[20]	Xie Zhihua, Liu Guodong. Fast infrared face recognition based on local binary pattern [J]. Infrared and Laser Engineering, 2013, 42(12): 3190-3195.
[21]	Liao Shu, Chung Albert C S. Face recognition with salient local gradient orientation binary pattern [C]//In Proceedings of 2009 International Conference on Image Processing (ICIP2009), 2009: 3317-3320.
[22]
[23]	Taskeed Jabid, Md Hasanul Kabir, Oksam Chae. Gender classification using local directional pattern(LDP) [C]// 2010 International Conference on Pattern Recognition (ICPR2010), 2010: 2162-2164.
[24]
[25]	Timo Ojala, Matti Pietikainen, Topi Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2002, 7(7): 971-987.
[26]
[27]	Zheng Yongbin, Shen Chunhua, Hartley Richard. Pyramid center-symmetric local binary/trinary patterns for effective pedestrian detection [C]//In Proceedings of 2010 Asian Conference on Computer Vision (ACCV 2010), 2010: 281-292.
[28]
[29]
[30]	Tan Xiaoyang, Triggs B. Enhanced local texture feature sets for face recognition under difficult lighting conditions [J]. IEEE Transactions on Image Processing, 2010, 19 (6): 1635-1650.
[31]	Fu Xiaofeng, Wei Wei. Facial expression recognition based on advance local binary pattern histogram projection [J]. Pattern Recognition and Artificial Intelligence, 2009, 22(1): 123-128.
[32]
[33]
[34]	Liao S, Law M, Chung C S. Dominant local binary patterns for texture [J]. IEEE Transactions on Image Processing, 2009, 18(5): 1107-1118.
[35]	Song C, Sun Y, Yin B. Adaptively doubly weighted sub-pattern LGBP for eyeglasses-face recognition [J]. Journal of Computational Information Systems, 2010, 6(4): 1135-1142.
[36]
[37]	Heikkila M, Schmid C. Description of interest regions with local binary patterns [J]. Pattern Recogntion, 2009, 42 (3): 425-436.
[38]
[39]	Watanabe T, Ito S, Yokoi K. Co-occurrence histograms of oriented gradients for pedestrian detection [C]//Proc the 3rd IEEE Pacific-Rim Symposium on Image and Video Technology, 2009: 37-47.
[40]
[41]
[42]	Ryusuke Nosaka, Yasuhiro Ohkawa, Kazuhiro Fukui. Feature extraction based on Co-occurrence of adjacent local binary patterns [C]//PSIVT, 2011, LNCS 7088: 82-91.
[43]	Qi Xianbiao, Lu Yi, Chen Shifeng. Spatial co-occurrence of local intensity order for face recognition [C]//2013 IEEE International Conference on Multimedia and Expo Workshops (ICME),2013:1-6.

Infrared face recognition based on co-occurrence histogram of multi-scale local binary patterns

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views