Robust Face Recognition by Using FW-PCA Detecting Occluded Region

Abstract

Abstract:

For the issue that performance of face recognition algorithms is impacted by occlusion, a robust face recognition algorithm by using FW-PCA detecting occluded region is proposed. Firstly, FW-PCA is used to detect occluded region, and occluded region of input images are compared with gallery images. Then, LBP is used to determine the optimal weights and POC is used to get occluded mask. Finally, matching score of each image is calculated, face recognition is finished by nearest neighbor classifier. Experimental results on FRGC2 and UND show that the recognition accuracy can achieve at 99.6%. It has better recognition performance than several advanced recognition algorithms.

Key words: Image processing, Face recognition, Occluded Region Detecting, Fast-Weighted Principal Component Analysis, Phase-Only Correlation, Local Binary Pattern

CLC Number:

TP391.4

QIAO Rui, LI Jing. Robust Face Recognition by Using FW-PCA Detecting Occluded Region[J]. J4, 2015, 32(3): 270-277.

References

[1] 王科俊, 邹国锋. 基于子模式的 Gabor 特征融合的单样本人脸识别[J]. 模式识别与人工智能, 2013, 26(1): 50-56.
[2] Wang S, Zhang D, Liang Y, et al. Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis[C]//Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012: 2216-2223.
[3] Hosoi T, Nagashima S, Kobayashi K, et al. Restoring occluded regions using FW-PCA for face recognition[C]//Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on. IEEE, 2012: 23-30.
[4] 赵海英, 杨一帆, 徐正光. 基于多角度 LBP 特征的三维人脸性别分类[J]. 自动化学报, 2012, 38(9): 1544-1549.
[5] Arjun J S, Nair M S. Robust face recognition technique using Gabor phase pattern and phase only correlation[J]. CSI Transactions on ICT, 2014, 2(2): 85-95.
[6] Passalis G, Perakis P, Theoharis T, et al. Using facial symmetry to handle pose variations in real-world 3D face recognition [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2011, 33(10): 1938-1951.
[7] Li H, Huang D, Lemaire P, et al. Expression robust 3D face recognition via mesh-based histograms of multiple order surface differential quantities[C] Image Processing (ICIP), 2011 18th IEEE International Conference on. IEEE, 2011: 3053-3056.
[8] Liao S, Jain A K, Li S Z. Partial face recognition: Alignment-free approach [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2013, 35(5): 1193-1205.
[9] 文乔龙, 万遂人, 徐双. Fisher准则和正则化水平集方法分割噪声图像 [J]. 计算机研究与发展, 2012, 49(6): 1339-1347.
[10] Jiang Z, Lin Z, Davis L S. Label consistent K-SVD: learning a discriminative dictionary for recognition[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2013, 35(11): 2651-2664.
[11] Jiang Z, Lin Z, Davis L S. Learning a discriminative dictionary for sparse coding via label consistent K-SVD[C] Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011: 1697-1704.
[12] Yang M, Zhang L, Shiu S C K, et al. Gabor feature based robust representation and classification for face recognition with Gabor occlusion dictionary[J]. Pattern Recognition, 2013, 46(7): 1865-1878.
[13] Li X X, Dai D Q, Zhang X F, et al. Structured sparse error coding for face recognition with occlusion[J]. IEEE transactions on image processing: a publication of the IEEE Signal Processing Society, 2013, 22(5): 1889-1900.
[14] Azeem A, Sharif M, Raza M, et al. A survey: face recognition techniques under partial occlusion[J]. Int. Arab J. Inf. Technol., 2014, 11(1): 1-10.
[15] 廖海斌, 陈庆虎, 鄢煜尘. 基于因子分析的实用人脸识别研究[J]. 电子与信息学报, 2011, 33(7): 1611-1617.
[16] Mairal J, Bach F, Ponce J, et al. Online learning for matrix factorization and sparse coding[J]. The Journal of Machine Learning Research, 2010, 28(11): 19-60.
[17] Ocegueda O, Fang T, Shah S K, et al. 3D face discriminant analysis using Gauss-Markov posterior marginals[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2013, 35(3): 728-739.