Abstract
This paper presents a novel method called sparse representation based classification via fusion variant dictionary (FSRC) for single-sample face recognition. There are two points to be highlighted in our method: (1) A specific preprocessing step is introduced to help the gray level of the testing sample distributed uniformly. (2) A fusion variant dictionary is proposed including two parts: the first part is an intra-class variant term, which can help represent the moderate illuminations, expressions and disguises; the second part is a noise term, which can help remove the common noise (caused by pixel noise, severe illumination or our preprocessing step) in testing samples. Extensive experiments on public face databases demonstrate advantages of the proposed method over the state-of-the-art methods, especially in dealing with image corruption and severe illumination.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Deng, W., Hu, J., Guo, J.: Extended src: Undersampled face recognition via intraclass variant dictionary. IEEE PAMI 34, 1864–1870 (2012)
Deng, W., Hu, J., Guo, J.: In defense of sparsity based face recognition. In: CVPR (2013)
Yang, M., Gool, L.V., Zhang, L.: Sparse variation dictionary learning for face recognition with a single training sample per person. In: ICCV (2013)
Zhuang, L., Yang, A., Zhou, Z., Sastry, S., Ma, Y.: Single-sample face recognition with image corruption and misalignment via sparse illumination transfer. In: CVPR (2013)
Wright, J., Yang, A., Ganesh, A., Sastry, S., Ma, Y.: Robust face recognition via sparse re-presentation. IEEE PAMI 31, 210–227 (2009)
Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: Multi-pie. Image and Vision Computing 28, 807–813 (2010)
http://picasa.google.com/ (accessed May 23, 2014)
http://face.com/ (accessed May 23, 2014)
http://cn.faceplusplus.com/uc/ (accessed May 23, 2014)
Lin, Z., et al.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv:1009.5055v2
Bertsekas, D.P.: Nonlinear programming. Athena Scientific (2004)
Cands, E., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? Journal of the ACM 58(3), Article 11 (2011)
Yang, A., Ganesh, A., Sastry, S., Ma, Y.: Fast l1-minimization algorithms and an application in robust face recognition: A review. In: ICIP (2010)
Yang, A., Ganesh, A., Zhou, Z., Sastry, S., Ma, Y.: Fast l1-minimization algorithms for robust face recognition. arXiv:1007.3753v4 (2012)
Tan, X., Triggs, B.: Enhanced local texture feature sets for face recognition under difficult lighting conditions. TIP (2010)
Lee, K., Ho, J., Driegman, D.: Acquiring linear subspaces for face recognition under variable lighting. IEEE PAMI 27(5), 684–698 (2005)
Georghiades, Belhumeur, P., Kriegman, D.: From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE PAMI 23(6), 643–660 (2001)
Yang, J., Zhang, L., Xu, Y., Yang, J.: Beyond sparsity: the role of l1-optimizer in pattern classification. Pattern Recognition 45, 1104–1118 (2012)
Gonzalez, R., Woods, R.: Digital image processing. Pearson Prentice Hall (2007)
Martinez, A., Benavente, R.: The AR face database, CVC Technical Report (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tai, Y., Yang, J., Qian, J., Chen, Y. (2014). Single-Sample Face Recognition via Fusion Variant Dictionary. In: Li, S., Liu, C., Wang, Y. (eds) Pattern Recognition. CCPR 2014. Communications in Computer and Information Science, vol 484. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45643-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-662-45643-9_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45642-2
Online ISBN: 978-3-662-45643-9
eBook Packages: Computer ScienceComputer Science (R0)