Face recognition based on center-symmetric gradient magnitude and phase pattern

被引：0

作者：

Yang, Hui-Xian ^{[1
]}

Zhai, Yun-Long ^{[1
]}

Cai, Yong-Yong ^{[1
]}

Feng, Jun-Peng ^{[1
]}

Li, Qiu-Qiu ^{[1
]}

机构：

[1] School of Physics and Optoelectronics, Xiangtan University, Xiangtan

来源：

Guangdianzi Jiguang/Journal of Optoelectronics Laser | 2015年 / 26卷 / 05期

关键词：

Center-symmetric gradient magnitude and phase pattern (CSGMP); Center-symmetric local directional pattern (CSLDP); Face recognition; Nearest neighbor classifier; Single sample;

D O I：

10.16136/j.joel.2015.05.0588

中图分类号：

学科分类号：

摘要：

To overcome the limitations of traditional face recognition methods for single sample, a novel method of face recognition based on center-symmetric gradient magnitude and phase pattern (CSGMP) is proposed. Firstly, gradient magnitude maps and phase maps of a face image are calculated. Secondly, a new operator named center-symmetric local directional pattern (CSLDP) is proposed to encode the gradient magnitude, and gradient phase is quantized into eight regions, then the proposed CSGMP is the combination of the binary codes of phase and CSLDP of magnitude. Finally, CSGMP feature maps are divided into several blocks, and the concatenated histogram calculated over all blocks is utilized as the feature descriptor of face recognition. The recognition is performed by using the nearest neighbor classifier. Experimental results on YALE and AR face databases validate that the CSGMP algorithm is an outstanding method for single sample face recognition under different illumination conditions, different facial expression conditions and partial occlusion conditions. ©, 2015, Board of Optronics Lasers. All right reserved.

引用

页码：969 / 977

页数：8

共 18 条

[1] Wang W.-Q., Zhang X.-Y., Cao C.-Q., Et al., Scale invariant face recognition from single sample, Journal of Image and Graphics, 17, 3, pp. 380-386, (2012)
[2] Chen Y.-M., Chiang J.-H., Fusing multiple features for fourier mellin-based face recognition with single example image per person, Neurocomputing, 73, 16-18, pp. 3089-3096, (2010)
[3] Yang X.-K., Yue X.-Q., Ji Q.-B., Based on HOG and DMMA for face recognition with single training sample per person, Application Research of Computers, 32, 2, pp. 627-634, (2015)
[4] Wang K.-J., Zou G.-F., A sub-pattern gabor features fusion method for single sample face recognition, PR & AI, 26, 1, pp. 50-56, (2013)
[5] Li W.-H., Chen L., Gong W.-G., Fast facial descriptor extraction for single image based face recognition, Journal of Optoelectronics·Laser, 25, 3, pp. 558-564, (2014)
[6] Vu N.S., Exploring patterns of gradient orientations and magnitudes for face recognition, IEEE Transactions on Information Forensics and Security, 8, 2, pp. 295-304, (2013)
[7] Gao T., Feng X.L., Lu H., A novel face feature descriptor using adaptively weighted extended LBP pyramid, Optik, 124, 23, pp. 6286-6291, (2013)
[8] Jabid T., Kabir M.H., Chae O., Local directional pattern (LDP) for face recognition, Proc. of International Conference on Consumer Electronics, pp. 329-330, (2010)
[9] Zhang T.-P., Tang Y.-Y., Fang B., Et al., Face recognition under varying illumination using gradientfaces, IEEE Transactions on Image Processing, 18, 11, pp. 2599-2606, (2009)
[10] Chen X., Zhang J.-S., Illumination robust single sample face recognition using multi-directional orthogonal gradient phase faces, Neurocomputing, 74, 14, pp. 2291-2298, (2011)

← 1 2 →