Abstract
A sparse representation-based classifier has demonstrated potential results in face recognition but meets a small sample problem i.e. number of input images is less than an image dimension. To overcome this issue, dimensionality reduction methods can be employed in a sparse representation framework. Along this direction, sparse representation is often clubbed with the Fisher discriminant criterion. Most of these methods consider a random projection matrix to start with. The performance of dimensionality reduction procedure mostly depends on the projection matrix. In this paper, we show that a better-initialized projection matrix can perform much better than its random counterpart. Further, we are able to reduce the dimension of the projection matrix by half without losing much information. The experiments performed on the Extended Yale B, CMU-PIE and Coil-20 datasets demonstrate the efficacy of the proposed approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, S., Qiao, L., Tan, X.: Sparsity preserving projections with applications to face recognition. Pattern Recogn. 43(1), 331–341 (2010)
Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisher-faces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 711–720 (1997)
Gao, Q., Wang, Q., Huang, Y., Gao, X., Hong, X., Zhang, H.: Dimensionality reduction by integrating sparse representation and fisher criterion and its applications. IEEE Trans. Image Process. 24(12), 5684–5695 (2015)
Tenenbaum, J.B.: Mapping a manifold of perceptual observations. In: Advances in Neural Information Processing Systems, pp. 682–688 (1998)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15(6), 1373–1396 (2003)
He, X., Niyogi, P.: Locality preserving projections. In: Advances in Neural Information Processing Systems, pp. 153–160 (2004)
Gui, J., Sun, Z., Jia, W., Rongxiang, H., Lei, Y., Ji, S.: Discriminant sparse neighborhood preserving embedding for face recognition. Pattern Recogn. 45(8), 2884–2893 (2012)
Yang, M., Zhang, L., Yang, J., Zhang, D.: Robust sparse coding for face recognition. In: CVPR 2011, pp. 625–632. IEEE (2011)
Yang, J., Chu, D., Zhang, L., Xu, Y., Yang, J.: Sparse representation classifier steered discriminative projection with applications to face recognition. IEEE Trans. Neural Netw. Learn. Syst. 24(7), 1023–1035 (2013)
Donoho, D.L., Tsaig, Y.: Fast solution of l1-norm minimization problems when the solution may be sparse. IEEE Trans. Inf. Theory 54(11), 4789–4812 (2008)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Lee, K.-C., Ho, J., Kriegman, D.J.: Acquiring linear subspaces for face recognition under variable lighting. IEEE Trans. Pattern Anal. Mach. Intell. 27(5), 684–698 (2005)
Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression (PIE) database. In: Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition, pp. 53–58. IEEE (2002)
Nene, S.A., Nayar, S.K., Murase, H.: Columbia image object library (coil-20). Department of Computer Science, Columbia University, New York, NY, USA, Technical report CUCS-006-96 (1996)
Zhao, W., Chellappa, R., Jonathon Phillips, P., Rosenfeld, A.: Face recognition: a literature survey. ACM Comput. Surv. (CSUR) 35(4), 399–458 (2003)
Kay, S.M.: Fundamentals of Statistical Signal Processing: Estimation Theory. Prentice-Hall Inc., Upper Saddle River (1993)
Shen, C., Chen, L., Dong, Y., Priebe, C.E.: Sparse representation classification beyond l1 minimization and the subspace assumption. IEEE Trans. Inf. Theory 66(8), 5061–5071 (2020). https://doi.org/10.1109/TIT.2020.2981309
Xu, Y., Cheng, J.: Face recognition algorithm based on correlation coefficient and ensemble-augmented sparsity. IEEE Access 8, 183972–183982 (2020). https://doi.org/10.1109/ACCESS.2020.3028905
Mandal, S., Thavalengal, S., Sao, A.K.: Explicit and implicit employment of edge-related information in super-resolving distant faces for recognition. Pattern Anal. Appl. 19(3), 867–884 (2016). https://doi.org/10.1007/s10044-015-0512-0
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chavda, P., Mandal, S., Mitra, S.K. (2021). Dimensionality Reduction by Consolidated Sparse Representation and Fisher Criterion with Initialization for Recognition. In: Singh, S.K., Roy, P., Raman, B., Nagabhushan, P. (eds) Computer Vision and Image Processing. CVIP 2020. Communications in Computer and Information Science, vol 1378. Springer, Singapore. https://doi.org/10.1007/978-981-16-1103-2_28
Download citation
DOI: https://doi.org/10.1007/978-981-16-1103-2_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1102-5
Online ISBN: 978-981-16-1103-2
eBook Packages: Computer ScienceComputer Science (R0)