Local Region Partitioning for Disguised Face Recognition Using Non-negative Sparse Coding

  • Khoa Dang DangEmail author
  • Thai Hoang Le
Conference paper
Part of the Studies in Computational Intelligence book series (SCI, volume 457)


In this paper, three initializing methods for the Non-negative Sparse Coding are proposed for the disguised face recognition task in two scenarios: sunglasses or scarves. They aim to overcome previous sparse coding methods’ difficulty, which is the requirement for a comprehensive training set. This means spending much more effort for collecting images and matching, which is not practical in many real world applications. To build a training set from a limited database containing one neutral facial images per person, a number of training images are derived from one image in the database using one of the three following partitioning methods: (1) grid-based partitioning, (2) horizontal partitioning and (3) geometric partitioning. Experiment results will show that these initialization methods facilitate Non-negative sparse coding algorithm to converge much faster compared to previous methods. Furthermore, trained features are more localized and more distinct. This leads to faster recognition time with comparable recognition results.


Occluded face recognition non-negative sparse coding local region features 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Olshausen, B., Field, D.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. J. Nature 381, 607–609 (1996)CrossRefGoogle Scholar
  2. 2.
    Bhavin, S., Levine, M.: Face recognition using localized features based on non-negative sparse coding. J. Machine Vision and Application 18, 107–122 (2007)CrossRefGoogle Scholar
  3. 3.
    Lee, D., Seung, S.: Algorithms for non-negative matrix factorization. In: 13th Advances in Neural Information Processing Systems, pp. 556–562. MIT Press (2000)Google Scholar
  4. 4.
    ISO/IEC JTC1 SC17 WG3/TF1 for ICAO-NTWG: History, interoperability and implementation, Machine readable travel documents. International Civil Aviation Organization (2007)Google Scholar
  5. 5.
    Le, T., Truong, H., Dang, K., Duong, D.: Using Genetic Algorithms to Find Reliable Set of Coefficients for Face Recognition. J. Information Technologies and Communications (JITC) 1(6(26), 124–133 (2011)Google Scholar
  6. 6.
    Wright, J., Yang, A., Ganesh, A., Sastry, S., Ma, Y.: Robust face recognition via sparse representation. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 210–227. IEEE Press, Washington, DC (2009)Google Scholar
  7. 7.
    Martinez, M., Benavente, R.: The AR face database,
  8. 8.
    Nguyen, M., Le, Q., Pham, V., Tran, T., Le, B.: Multi-scale Sparse Representation for Robust Face Recognition. In: 3rd International Conference on Knowledge and Systems Engineering, Hanoi, Vietnam, pp. 195–199 (2011)Google Scholar
  9. 9.
    Yang, M., Zhang, L., Yang, J., Zhang, D.: Robust sparse coding for face recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 625–632. IEEE Press (2011)Google Scholar
  10. 10.
    Elhamifar, E., Vidal, R.: Robust Classification using Structured Sparse Representation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1873–1879. IEEE Press (2011)Google Scholar
  11. 11.
    Huang, K., Aviyente, S.: Sparse representation for signal classification. In: Advances in Neural Information Processing Systems (2006)Google Scholar
  12. 12.
    Hoyer, P.: Probabilistic Models of Early Vision. Ph.D. Thesis. Helsinki University of Technology (2002)Google Scholar
  13. 13.
    Hoyer, P.: Non-Negative Sparse Coding. In: 7th IEEE Workshop on Neural Networks for Signal Processing, pp. 557–565. IEEE Press (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.University of Science, Vietnam National UniversityHo Chi Minh CityVietnam

Personalised recommendations