An LBP-based multi-scale illumination preprocessing method for face recognition
- 89 Downloads
It is one of the major challenges for face recognition to minimize the disadvantage of illumination variations of face images in different scenarios. Local Binary Pattern (LBP) has been proved to be successful for face recognition. However, it is still very rare to take LBP as an illumination preprocessing approach. In this paper, we propose a new LBP-based multi-scale illumination preprocessing method. This method mainly includes three aspects: threshold adjustment, multi-scale addition and symmetry restoration/neighborhood replacement. Our experiment results show that the proposed method performs better than the existing LBP-based methods at the point of illumination preprocessing. Moreover, compared with some face image preprocessing methods, such as histogram equalization, Gamma transformation, Retinex, and simplified LBP operator, our method can effectively improve the robustness for face recognition against illumination variation, and achieve higher recognition rate.
Key wordsFace recognition Illumination preprocessing Local Binary Pattern (LBP)
Unable to display preview. Download preview PDF.
- O. Lahdenoja, M. Laiho, and A. Paasio. Reducing the feature vector length in local binary patten based face recognition. Proceedings of IEEE International Conference on Image Processing (ICIP’2005), Genoa, Italy, September 11–14, 2005, Vol.2, 914–917.Google Scholar
- S. C. Liao, X. X. Zhu, Z. Lei, L. Zhang, and S. Z. Li. Learning multi-scale block local binary patterns for face recognition. Proceedings of IAPR/IEEE International Conference on Biometrics (ICB’ 2007), Seoul, Korea, August 27–29, 2007, 828–837.Google Scholar
- M. Sebastien, R. Yann, and H. Guillaume. On the recent use of local binary patterns for face authentication. International Journal on Image and Video Processing, Special Issue on Facial Image Processing, 2007(2007)1, 1–9.Google Scholar
- Y. G. Huang, Y. H. Wang, and T. N. Tan. Combining statistics of geometrical and correlative features for 3D face recognition. Proceedings of the 17th British Machine Vision Conference (BMVC’ 2006), Edinburgh, UK, September 4–7, 2006, 879–888.Google Scholar
- G. Zhang, X. Huang, S. Z. Li, Y. Wang, and X. Wu. Boosting local binary pattern (LBP)-based face recognition. Proceedings of the 5th Chinese Conference on Biometric Recognition (SINOBIOMETRICS’ 2004), Guangzhou, China, December 13–15, 2004, 179–186.Google Scholar
- G. Heusch, Y. Rodriguez, and S. Marcel. Local binary patterns as an image preprocessing for face authentication. Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FG’2006), Southampton, UK, April 10–12, 2006, 9–14.Google Scholar
- Qian Tao and Raymond Veldhuis. Illumination normalization based on simplified local binary patterns for face verification system. Proceedings of Biometrics Symposium 2007, Baltimore, Maryland, USA, September 11–13, 2007, 1–7.Google Scholar