Abstract
Face occlusion is one of the most challenging problems for robust face recognition. Nonnegative matrix factorization (NMF) has been widely used in local feature extraction for computer vision. However, standard NMF is not robust to occlusion. In this paper, we propose a robust discriminative representation learning method under nonnegative patch alignment, which can take account of the geometric structure and discriminative information simultaneously. Specifically, we utilize linear reconstruction coefficients to characterize local geometric structure and maximize the pairwise fisher distance to improve the separability of different classes. The reconstruction errors are measured with weighted distance, and the weights for each pixel are learned adaptively with our proposed update rule. Experimental results on two benchmark datasets demonstrate the learned representation is more discriminative and robust than most of the existing methods in occluded face recognition.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ekenel, H.K., Stiefelhagen, R.: Why Is facial occlusion a challenging problem? In: Tistarelli, M., Nixon, M.S. (eds.) ICB 2009. LNCS, vol. 5558, pp. 299–308. Springer, Heidelberg (2009)
Belhumeur, P.N., Hespanha, J.P., Kriegman, D.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. TPAMI 19(7), 711–720 (1997)
Turk, M., Pentland, A.: Face recognition using eigenfaces. In: CVPR, pp. 586–591. IEEE (1991)
Tan, X., Chen, S., Zhou, Z.H., Zhang, F.: Recognizing partially occluded, expression variant faces from single training image per person with som and soft k-nn ensemble. TNN 16(4), 875–886 (2005)
Li, S.Z., Hou, X.W., Zhang, H.J., Cheng, Q.S.: Learning spatially localized, parts-based representation. In: CVPR, pp. 1–6. IEEE (2001)
Jia, H., Martinez, A.M.: Support vector machines in face recognition with occlusions. In: CVPR, pp. 136–141. IEEE (2009)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nat. 401(6755), 788–791 (1999)
Huang, J., Nie, F., Huang, H., Ding, C.: Robust manifold nonnegative matrix factorization. ACM TKDD 8(3), 11 (2014)
Guan, N., Tao, D., Luo, Z., Shawe-Taylor, J.: Mahnmf: manhattan non-negative matrix factorization. Mach. Learn. 1(5), 11–43 (2012)
Sandler, R., Lindenbaum, M.: Nonnegative matrix factorization with earth mover’s distance metric for image analysis. TPAMI 33(8), 1590–1602 (2011)
Du, L., Li, X., Shen, Y.: Robust nonnegative matrix factorization via half-quadratic minimization. In: ICDM, pp. 201–210. IEEE (2012)
Cai, D., He, X., Han, J., Huang, T.: Graph regularized nonnegative matrix factorization for data representation. TPAMI 33(8), 1548–1560 (2011)
Yang, J., Yang, S., Fu, Y., Li, X., Huang, T.: Non-negative graph embedding. In: CVPR, pp. 1–8. IEEE (2008)
Guan, N., Tao, D., Luo, Z., Yuan, B.: Non-negative patch alignment framework. TNN 22(8), 1218–1230 (2011)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Sci. 290(5500), 2323–2326 (2000)
Loog, M., Duin, R.P.W., Haeb-Umbach, R.: Multiclass linear dimension reduction by weighted pairwise fisher criteria. TPAMI 23(7), 762–766 (2001)
Yang, M., Zhang, L., Yang, J., Zhang, D.: Regularized robust coding for face recognition. TIP 22(5), 1753–1766 (2013)
Kong, D., Ding, C., Huang, H.: Robust nonnegative matrix factorization using l21-norm. In: Proceedings of the 20th International Conference on Information and Knowledge Management, pp. 673–682. ACM (2011)
Acknowledgements
This work is supported in part by the National Natural Science Foundation of China (No.61402122), the 2014 Ph.D. Recruitment Program of Guizhou Normal University and the Outstanding Innovation Talents of Science and Technology Award Scheme of education department in Guizhou Province (Qianjiao KY word [2015]487).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ou, W., Li, G., Yu, S., Xie, G., Ren, F., Tang, Y. (2015). Robust Discriminative Nonnegative Patch Alignment for Occluded Face Recognition. In: Arik, S., Huang, T., Lai, W., Liu, Q. (eds) Neural Information Processing. ICONIP 2015. Lecture Notes in Computer Science(), vol 9492. Springer, Cham. https://doi.org/10.1007/978-3-319-26561-2_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-26561-2_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26560-5
Online ISBN: 978-3-319-26561-2
eBook Packages: Computer ScienceComputer Science (R0)