The LBP Integrating Neighbor Pixels on Face Recognition

Abstract:

The traditional LBP only considers the difference between the center pixel and the neighbor pixels. In order to use the relationship of the center pixel and neighbor pixels, a manipulative texture method B_LBP is proposed in this paper, which integrates the grayscale intensity of neighbor pixels into traditional LBP. The method keeps the local structure information of original images and enhances the identification ability. LDA (Linear discriminate analysis) is used to reduce the dimensionality of the original data. The experiments are conducted on Yale B and CMU PIE face databases with B_LBP, LEP and LBP. The results show that the B_LBP is superior to the traditional LBP and LEP.

• Periodical: Advanced Materials Research (Volumes 756-759)
• Pages: 3835-3840
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.756-759.3835
• Online since: September 2013
• Authors: Wei Sheng Li, Long Chen
• Keywords: B_LBP, Center Pixel, Face Recognition, LBP, LEP, Neighbor Pixels

References

[1] T. Ojala, M. Pietikainen, and D. Harwood, A Comparative Study of Texture Measures with Classification Based on Feature Distributions, Pattern Recognition, 1996, 29: 51-59.

DOI: 10.1016/0031-3203(95)00067-4

[2] T. Ahonen, A. Hadid and M. Pietikäinen, Face Description with Local Binary Patterns: Application to Face Recognition, IEEE Trans, on PAMI, 2006, 28(12): 2037-(2041).

DOI: 10.1109/tpami.2006.244

[3] T. Ojala, M. Pietikainen, T. Maenpaa, Multi resolution Gray-seals and Rotation Invariant Texture Classification with Local Binary Pattern, IEEE Trans. on PAMI, 2002, 24(7): 971-987.

DOI: 10.1109/tpami.2002.1017623

[4] X. Tan, P. Triggs, Enhanced Local Texture Feature Sets for Face Recognition under Difficult Lighting Conditions, IEEE Trans. on Image Processing, 2010, 19(6): 1635-1650.

DOI: 10.1109/tip.2010.2042645

[5] L. Jianjun, Based on Gabor wavelets and CS -LBP face feature extraction algorithm research, Chongqing, Chongqing university (2010).

[6] F. Xiaofeng, Base on the binary model of face recognition and expression recognition research, Hangzhou, Zhejiang University (2008).

[7] H. Jiaxiang, The algorithm multi-direction LBP to apply in the face recognition, Xiameng, Xiameng University (2009).

[8] L. Z. Stan and K. Jain. Handbook of Face Recognition. Springer. (2005).

[9] T. Sim, S. Baker, M Bsat, The CMU pose, illumination, and expression (PIE) database. IEEE Int. Conf. Automatic Face and Gesture Recognition, 46-51. 200.

DOI: 10.1109/afgr.2002.1004130

[10] X. Junbi, J. Cuicui Based on PCA and R - continuous matching affinity algorithm. Computer applications and software, 27(11): 270 - 271, 293．(2010).

[11] T. Theodorelee, L. Jingjiao. Pattern recognition. Electronic industry press. (2006).