Learning of Graph Compressed Dictionaries for Sparse Representation Classification

Farshad Nourbakhsh, Eric Granger

Abstract

Despite the limited target data available to design face models in video surveillance applications, many faces of non-target individuals may be captured over multiple cameras in operational environments to improve robustness to variations. This paper focuses on Sparse Representation Classification (SRC) techniques that are suitable for the design of still-to-video FR systems based on under-sampled dictionaries. The limited reference data available during enrolment is complemented by an over-complete external dictionary that is formed with an abundance of faces from non-target individuals. In this paper, the Graph-Compressed Dictionary Learning (GCDL) technique is proposed to learn compact auxiliary dictionaries for SRC. GCDL is based on matrix factorization, and allows to maintain a high level of SRC accuracy with compressed dictionaries because it exploits structural information to represent intra-class variations. Graph compression based on matrix factorization shown to efficiently compress data, and can therefore rapidly construct compact dictionaries. Accuracy and efficiency of the proposed GCDL technique is assessed and compared to reference sparse coding and dictionary learning techniques using images from the CAS-PEAL database. GCDL is shown to provide fast matching and adaptation of compressed dictionaries to new reference faces from the video surveillance environments.

References

  1. Aharon, M., Elad, M., and Bruckstein, A. (2006). The ksvd: An algorithm for designing overcomplete dictionaries for sparse representation. Trans. Signal Processing, 54(11):4311-4322.
  2. Bashbaghi, S., Granger, E., Sabourin, R., and Bilodeau, G. (2014). Watch-list screening using ensembles based on multiple face representations. In International Conference on Pattern Recognition, pages 4489-4494.
  3. Choi, Y. and Szpankowski, W. (2012). Compression of graphical structures: Fundamental limits, algorithms, and experiments. IEEE Trans. on Information Theory, 58(2):620-638.
  4. Deng, W., Hu, J., and Guo, J. (2012). Extended src: Undersampled face recognition via intraclass variant dictionary. IEEE Trans. Pattern Analysis Machine Intelligence, 34(9):1864-1870.
  5. Dewan, M. A. A., Granger, E., Marcialis, G. L., Sabourin, R., and Roli, F. (2016). Adaptive appearance model tracking for still-to-video face recognition. Pattern Recognition, 49:129-151.
  6. Donoho, D. L. and Tsaig, Y. (2008). Fast solution of l1- norm minimization problems when the solution may be sparse. Information Theory, IEEE Transactions on, 54(11):4789-4812.
  7. Elhamifar, E., Sapiro, G., and Vidal, R. (2012). See all by looking at a few: Sparse modeling for finding representative objects. In IEEE Conference on Computer Vision and Pattern Recognition,, pages 1600-1607.
  8. Engan, K., Aase, S. O., and Hakon Husoy, J. (1999). Method of optimal directions for frame design. In International Conference of Acoustics, Speech, and Signal Processing, pages 2443-2446.
  9. Gao, W., Cao, B., Shan, S., Chen, X., Zhou, D., Zhang, X., and Zhao, D. (2008). The cas-peal large-scale chinese face database and baseline evaluations. IEEE Trans. System Man Cybernetics Part A, 38(1):149-161.
  10. Lee, D. D. and Seung, H. S. (2001). Algorithms for nonnegative matrix factorization. In Advances in Neural Information Processing Systems 13, pages 556-562.
  11. Mairal, J., Bach, F., and Ponce, J. (2014). Sparse modeling for image and vision processing. Foundations Trends in Computer Graphics and Vision, 8(2-3):85-283.
  12. Mokhayeri, F., Granger, E., and Bilodeau, G. (2015). Synthetic face generation under various operational conditions in video surveillance. In International Conference on Image Processing.
  13. Navlakha, S., Rastogi, R., and Shrivastava, N. (2008). Graph summarization with bounded error. In International Conference on Management of Data (ACM), pages 419-432.
  14. Nourbakhsh, F. (2015). Algorithms for Graph Compression: Theory and Experiments. PhD thesis, Dipartamento di Scienze Ambientali, Informatica e Statistica, Universitá Ca'Foscari, Venice, Italy.
  15. Nourbakhsh, F., Bulò, S. R., and Pelillo, M. (2015). A matrix factorization approach to graph compression with partial information. International Journal of Machine Learning & Cybernetics, 6(4):523-536.
  16. Olshausen, B. A. and Field, D. J. (1996). Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381:607-609.
  17. Ramírez, I., Sprechmann, P., and Sapiro, G. (2010). Classification and clustering via dictionary learning with structured incoherence and shared features. In IEEE Conference on Computer Vision and Pattern Recognition, pages 3501-3508.
  18. Shafiee, S., Kamangar, F., Athitsos, V., and Huang, J. (2013). The role of dictionary learning on sparse representation-based classification. In International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 7813, pages 47:1-47:8.
  19. Sperotto, A. and Pelillo, M. (2007). Szemerédis regularity lemma and its applications to pairwise clustering and segmentation. In International Conference of Energy Minimization Methods in Computer Vision and Pattern Recognition, volume 4679 of Lecture Notes in Computer Science, pages 13-27.
  20. Su, Y., Shan, S., Chen, X., and Gao, W. (2010). Adaptive generic learning for face recognition from a single sample per person. In International Conference on Computer Vision and Pattern Recognition, pages 2699-2706.
  21. Szemerédi, E. (1978). Regular partitions of graphs. In Problèmes combinatoires et thorie des graphes, pages 399-401.
  22. Tan, X., Chen, S., hua Zhou, Z., and Zhang, F. (2006). Face recognition from a single image per person: A survey. International Journal of Pattern Recognition, 39:1725-1745.
  23. Tillmann, A. M. (2015). On the computational intractability of exact and approximate dictionary learning. IEEE Signal Processing Letter, 22(1):45-49.
  24. Toivonen, H., Zhou, F., Hartikainen, A., and Hinkka, A. (2011). Compression of weighted graphs. In International Conference on Knowledge Discovery and Data Mining (ACM), pages 965-973.
  25. Wei, C. and Wang, Y. F. (2015). Undersampled face recognition via robust auxiliary dictionary learning. IEEE Transactions on Image Processing, 24(6):1722-1734.
  26. Wright, J., Yang, A. Y., Ganesh, A., Sastry, S. S., and Ma, Y. (2009). Robust face recognition via sparse representation. IEEE Trans. Pattern Analysis Machine Intelligence, 31(2):210-227.
  27. Yang, A. Y., Ganesh, A., Zhou, Z., Sastry, S., and Ma, Y. (2010a). Fast l1-minimization algorithms for robust face recognition: A review. International Conference on Image Processing, pages 1849-1852.
  28. Yang, M., Van, L., and Zhang, L. (2013). Sparse variation dictionary learning for face recognition with a single training sample per person. In International Conference on Computer Vision, pages 689-696.
  29. Yang, M., Zhang, L., Feng, X., and Zhang, D. (2011a). Fisher discrimination dictionary learning for sparse representation. In International Conference on Computer Vision, pages 543-550.
  30. Yang, M., Zhang, L., Yang, J., and Zhang, D. (2010b). Metaface learning for sparse representation based face recognition. In International Conference on Image Processing,, pages 1601-1604.
  31. Yang, M., Zhang, L., Yang, J., and Zhang, D. (2011b). Robust sparse coding for face recognition. In International Conference on Computer Vision and Pattern Recognition, pages 625-632.
Download


Paper Citation


in Harvard Style

Nourbakhsh F. and Granger E. (2016). Learning of Graph Compressed Dictionaries for Sparse Representation Classification . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 309-316. DOI: 10.5220/0005710403090316


in Bibtex Style

@conference{icpram16,
author={Farshad Nourbakhsh and Eric Granger},
title={Learning of Graph Compressed Dictionaries for Sparse Representation Classification},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={309-316},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005710403090316},
isbn={978-989-758-173-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Learning of Graph Compressed Dictionaries for Sparse Representation Classification
SN - 978-989-758-173-1
AU - Nourbakhsh F.
AU - Granger E.
PY - 2016
SP - 309
EP - 316
DO - 10.5220/0005710403090316