Face Recognition Based on Features of Triple Descriptors

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Recently, texture descriptors and object detection descriptors have been used widely in face recognition due to their discriminative ability and fast implementation. In this paper, we investigate the efficiency of face recognition based on image blocking and a combination of triple descriptors, LBP, LTP, and HOG.  The method is applied to Color Feret dataset and AT&T along with four classifiers to measure the accuracy rate. The experimental results show a better recognition rate on AT&T and stable performance on both datasets.



  • Keywords

    Classification; face recognition; Histogram of the Oriented Gradient; Local Binary Pattern; Local Ternary Pattern

  • References

      [1] T. Ojala, M. Pietika¨inen, and T. Ma¨enpa¨a¨, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971-987, July 2002.

      [2] Ojala, T., M. Pietikäinen, and D. Harwood, “A Comparative Study of Texture Measures with Classification Based on Feature Distributions,” Pattern Recognition 29, 1996, pp.51-59.

      [3] T. Ahonen, A. Hadid, and M. Pietikainen. Face recognition with local binary patterns. ECCV, 469–481, 2004.

      [4] S. Nikan, M. Ahmadi, “Human face recognition under occlusion using LBP and entropy weighted voting,” in International Conf. on Pattern Recognition (ICPR12), Tsukuba, November 2012, pp. 1699-1702.

      [5] Soodeh Nikan, Majid Ahmadi, “Local gradient-based illumination invariant face recognition using local phase quantisation and multi-resolution local binary pattern fusion”, The Institution of Engineering and Technology (IET), vol. 9, Issue no.1, pp. 12–21, 2014.

      [6] X. Tan and B. Triggs, “Enhanced local texture feature sets for face recognition under difficult lighting conditions,” IEEE Transactions on Image Processing, vol. 19, pp. 1635-1650, June 2010.

      [7] N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2005, pp. 886–893.

      [8] Kang Wang , Zhenxue Chen, Q.M. Jonathan Wu, Chengyun Liu, “Illumination and pose variable face recognition via adaptively weighted ULBP_MHOG and WSRC” Signal Processing: Image Communication 58 (2017) 175–186

      [9] P.J. Phillips, H. Moon, P.J. Rauss, S. Rizvi, “The FERET evaluation methodology for face recognition algorithms,” IEEE Trans. Pattern Anal. Mach. Intell., 22, pp. 1090–1104, October 2000.

      [10] ORL and Yale face databases. [Online]. Available: http://www.face-rec.org/databases/

      [11] Zhang H and Xu S (2016), “The Face Recognition Algorithms Based on Weighted LTP” in Journal of Image and Graphics, Vol. 4, No. 1.

      [12] O. Rama Devi, L.S.S.Reddy, E.V.Prasad, “ Face Recognition Using Fused Spatial Patterns”, International Journal of Advanced Trends in Computer Science and Engineering, Vol. 4, No. 2, pp. 15-21, Mar 2015.




Article ID: 27854
DOI: 10.14419/ijet.v7i4.16.27854

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.