Abstract
This paper attempts to utilize the basis images of block non-negative matrix factorization (BNMF) to serve as the sparse learning dictionary, which is more suitable for non-negative sparse representation (NSR) because they have non-negative compatibility. Based on BNMF-basis-image dictionary, the NSR features of query facial images can be learnt directly by solving l1-regularized least square problems. The NSR-feature based algorithm is then developed and successfully applied to face recognition. Subsequently, to further enhance the discriminant power of NSR method, this paper also proposes a feature fusion approach via combining NSR-feature with BNMF-feature. The proposed algorithms are tested on ORL and FERET face databases. Experimental results show that the proposed NSR+BNMF method greatly outperforms two single-feature based methods, namely NSR method and BNMF method.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. Proc. NIPS 13, 556–562 (2001)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)
Chen, W.S., Pan, B.B., Fang, B., Li, M., Tang, J.: Incremental Nonnegative Matrix Factorization for Face Recognition. Mathematical Problems in Engineering 2008, Article ID 410674, 17 pages (2008), doi:10.1155/2008/410674
Donoho, D., Tanner, J.: Sparse non-negative solution of underdetermined linear equations by linear programming. Proc. Nat. Acad. Sci. 102(27), 9446–9451 (2005)
Donoho, D.: For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution. Comm. Pure and Applied Math. 59(6), 797–829 (2006)
Bruckstein, A.M., Elad, M., Zibulevsky, M.: On the uniqueness of non-negative sparse solutions to underdetermined systems of equations. IEEE Trans. Inf. Theory 54(11), 4813–4820 (2008)
He, R., Zheng, W.S., Hu, B.G., Kong, X.W.: Two-Stage Non-negative Sparse Representation for Large-Scale Face Recognition. IEEE Transactions on Neural networks and Learning Systems 24(1), 35–46 (2013)
Wright, J., Yang, A.Y., Ganesh, A., Sadtry, S.S., Ma, Y.: Robust Face Recognition via Sparse Representation. IEEE Transactions on Pattern Analysis Machine Intelligence 30(2) (2009)
Kim, S.J., Koh, K., Lustig, M., Boyd, S., Gorinevsky, D.: A method for large-scale l1-regularized least squares. IEEE Journal on Selected Topics in Signal Processing 1(4), 606–617 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Chen, M., Chen, WS., Chen, B., Pan, B. (2013). Non-negative Sparse Representation Based on Block NMF for Face Recognition. In: Sun, Z., Shan, S., Yang, G., Zhou, J., Wang, Y., Yin, Y. (eds) Biometric Recognition. CCBR 2013. Lecture Notes in Computer Science, vol 8232. Springer, Cham. https://doi.org/10.1007/978-3-319-02961-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-02961-0_4
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02960-3
Online ISBN: 978-3-319-02961-0
eBook Packages: Computer ScienceComputer Science (R0)