Advertisement

Face Recognition Based on Representation with Reject Option

  • Min Wang
  • Yuyao Wang
  • Jinrong Cui
  • Shu Liu
  • Yuan Tian
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 238)

Abstract

In this paper, we proposed a method for face recognition with reject option. First, by setting a threshold, we use sparse representation (SR) method to find out candidates who should be rejected, and choose their nearest neighbors in the training set based on contribution in SR. Then we extract the Locally Adaptive Regression Kernels (LARK) feature of each candidate sample and its neighbors respectively. At last, we determine whether a candidate should be rejected via calculating the matrix cosine similarity measure. A number of experiments show that combining with sparse and LARK representation can obtain good performs for rejection.

Keywords

Sparse representation Lark feature Reject option 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Zhang, D., Song, F., Xu, Y., Liang, Z.: Advanced Pattern Recognition Technologies with Applications to Biometrics. Medical Information Science Reference (2009)Google Scholar
  2. 2.
    Xu, Y., Zhong, A., Yang, J., Zhang, D.: LPP Solution Schemes for Use with Face Recognition. Pattern Recognition 43, 4165–4176 (2010)CrossRefzbMATHGoogle Scholar
  3. 3.
    Xu, Y., Zhang, D., Yang, J.Y.: A Feature Extraction Method for Use with Bimodal Biometrics. Pattern Recognition 43, 1106–1115 (2010)CrossRefzbMATHGoogle Scholar
  4. 4.
    Wang, J., You, J., Li, Q., Xu, Y.: Orthogonal Discriminant Vector for Face Recognition Across Pose. Pattern Recognition 45, 4069–4079 (2012)CrossRefzbMATHGoogle Scholar
  5. 5.
    Xu, Y., Zhu, X., Li, Z., Liu, G., Lu, Y., Liu, H.: Using the Original and ’Symmetrical Face’ Training Samples to Perform Representation Based Two-step Face Recognition. Pattern Recognition 46, 1151–1158 (2013)CrossRefGoogle Scholar
  6. 6.
    Landgrebe, T.C.W., Tax, D.M.J., Paclłk, P., et al.: The Interaction Between Classification and Reject Performance for Distance-based Reject-option Classifiers. Pattern Recognition Letters 27, 908–917 (2006)CrossRefGoogle Scholar
  7. 7.
    Eickeler, S., Jabs, M., Rigoll, G.: Comparison of Confidence Measures for Face Recognition. In: 4th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 257–262. IEEE (2000)Google Scholar
  8. 8.
    Suutala, J., Roning, J.: Methods for Person Identification on a Pressure-sensitive Floor: Experiments with Multiple Cclassifiers and Rreject Option. Information Fusion 9, 21–40 (2008)CrossRefGoogle Scholar
  9. 9.
    Kim, C., Choi, C.H.: Image Covariance-based Subspace Method for Face Recognition. Pattern Recognition 40, 1592–1604 (2007)CrossRefzbMATHGoogle Scholar
  10. 10.
    Chen, J.C., Shi, S.Y., Lien, J.J.: Face Recognition and Unseen Subject Rejection in Margin-enhanced Space. In: International Conference on System Science and Engineering (ICSSE), pp. 631–636. IEEE (2010)Google Scholar
  11. 11.
    Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust Face Recognition via Sparse Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 31, 210–227 (2009)CrossRefGoogle Scholar
  12. 12.
    Karimi, M.M., Soltanian-Zadeh, H.: Face Recognition: A Sparse Representation-based Classification using Independent Component Analysis. In: 6th International Symposium on Telecommunications (IST), pp. 1170–1174. IEEE (2012)Google Scholar
  13. 13.
    Xu, Y., Zhang, D., Yang, J., Yang, J.Y.: A Two-phase Test Sample Sparse Representation Method for Uuse with Face Rrecognition. IEEE Transactions on Circuits and Systems for Video Technology 21, 1255–1262 (2011)CrossRefGoogle Scholar
  14. 14.
    Wagner, A., Wright, J., Ganesh, A., Zhou, Z., Mobahi, H., Ma, Y.: Toward a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 34, 372–386 (2012)CrossRefGoogle Scholar
  15. 15.
    Donoho, D.L.: For Most Large Underdetermined Systems of Linear Equations the Minimal l1-norm Ssolution is Also the Sparsest Solution. Communications on Pure and Applied Mathematics 59, 797–829 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Seo, H.J., Milanfar, P.: Face Verification Using the Lark Representation. IEEE Transactions on Information Forensics and Security 6, 1275–1286 (2011)CrossRefGoogle Scholar
  17. 17.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Min Wang
    • 1
  • Yuyao Wang
    • 1
  • Jinrong Cui
    • 1
  • Shu Liu
    • 1
  • Yuan Tian
    • 2
  1. 1.Bio-Computing Research Center, Shenzhen Graduate SchoolHarbin Institute of TechnologyHarbinChina
  2. 2.Industrial Engineering Department, Shenzhen Graduate SchoolTsinghua UniversityBeijingChina

Personalised recommendations