Robust Face Detection Using Multi-Block Local Gradient Patterns and Extreme Learning Machine

Part of the Adaptation, Learning, and Optimization book series (ALO, volume 16)


A novel multi-block local gradient patterns (MB-LGP) based face detection method was proposed in this article. The MB-LGP operators extract face features in the way similar to local gradient patterns (LGP) however, the gradient of pixels in LGP was replaced by the counterparts of square image areas in MB-LGP. We have proved that the MB-LGP has most of the advantages of LGP and moreover with a stronger discriminant power and better robustness against noise. In the classification part, the extreme learning machine was introduced in the last stage in the proposed cascade classifier in order to speed up training process and increase classification accuracy. As was shown in experiments using the CMU\(+\)MIT database the new method possesses high detection rate.


Face detection Multi-block local gradient patterns (MB-LGP) Extreme learning machine (ELM) 


  1. 1.
    T. Ojala, M. Pietikainen, T. Maenpaa, Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 7(13), 971–987 (2002)CrossRefGoogle Scholar
  2. 2.
    H. Jin, Q. Liu, H. Lu et al., Face detection using improved LBP under bayesian framework. Proceedings of Third International Conference on Image and Graphics. IEEE, pp. 306–309 (2004)Google Scholar
  3. 3.
    X. Tan, B. Triggs, Enhanced local texture feature sets for face recognition under difficult lighting conditions. Analysis and Modeling of Faces and Gestures (Springer, Berlin, 2007), pp. 168–182Google Scholar
  4. 4.
    S. Liao, S. Chung, Face recognition by using elongated local binary patterns with average maximum distance gradient magnitude. Computer Vision-ACCV 2007 (Springer, Berlin, 2007), pp. 672–679Google Scholar
  5. 5.
    G. Zhao, M. Pietikainen, Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 915–928 (2007)CrossRefGoogle Scholar
  6. 6.
    L. Paulhac, P. Makris, Y. Ramel, Comparison between 2D and 3D local binary pattern methods for characterisation of three-dimensional textures. Image Analysis and Recognition (Springer, Berlin, 2008), pp. 670–679Google Scholar
  7. 7.
    Jun. B, Kim. D, Robust face detection using local gradient patterns and evidence accumulation. Pattern Recogn. 45(9), 3304–3316 (2012)Google Scholar
  8. 8.
    P. Viola, M. Jones, Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001. IEEE, 1: I-511-I-518, vol. 1 (2001)Google Scholar
  9. 9.
    M. Jones, P.Viola, Fast multi-view face detection. Mitsubishi Electric Research Lab, 2012. TR-20003-96, vol. 3 (2003)Google Scholar
  10. 10.
    J. Xu, Y. Dou, Z. Pang, A reconfigurable architecture for rotation invariant multi-view face detection based on a novel two-stage boosting method. EURASIP J. Adv. Sig. Process. 2009, 54 (2009)Google Scholar
  11. 11.
    R. Xiao, L. Zhu, H.J. Zhang, Boosting chain learning for object detection. Proceedings of Ninth IEEE International Conference on Computer Vision. IEEE, pp. 709–715 (2003)Google Scholar
  12. 12.
    J. Friedman, T. Hastie, R. Tibshirani, Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Ann. Stat. 28(2), 337–407 (2000)CrossRefMATHMathSciNetGoogle Scholar
  13. 13.
    S.Z. Li, Z.Q. Zhang, Floatboost learning and statistical face detection. IEEE Trans. Pattern Anal. Mach. Intell. 26(9), 1112–1123 (2004)CrossRefGoogle Scholar
  14. 14.
    K. Zeng, Y. Tang, F. Liu, Parallization of Adaboost algorithm through hybrid MPI/openMP and transactional memory. 19th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP). IEEE, pp. 94–100 (2011)Google Scholar
  15. 15.
    Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme learning machine: a new learning scheme of feedforward neural networks. Proceedings of IEEE International Joint Conference on Neural Networks. IEEE, vol. 2, pp. 985–990 (2004)Google Scholar
  16. 16.
    H.A. Rowley, S. Baluja, T. Kanade, Neural network-based face detection. IEEE Trans. Pattern Anal. Mach. Intell. 20(1), 23–38 (1998)CrossRefGoogle Scholar
  17. 17.
    G.B. Huang, H. Zhou, X. Ding et al., Extreme learning machine for regression and multiclass classification. IEEE Trans. Syst. Man Cybern. Part B Cybern. 20(1), 23–38 (1998)Google Scholar
  18. 18.
    Y.W. Li, E. Zhu, R.Y. Chen et al., A vehicle classification approach based on edge orientation histograms. J. Comput. Inf. Syst. 8(16), 6979–6989 (2012)MathSciNetGoogle Scholar
  19. 19.
    R. Zabih, J. Woodfill, Non-parametric local transforms for computing visual correspondence. Computer VisionECCV’94 (Springer, Berlin, 1994), pp. 151–158Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.College of ComputerNational University of Defense TechnologyChangshaChina
  2. 2.State Key Laboratory of High Performance ComputingNational University of Defense TechnologyChangshaChina

Personalised recommendations