基于鲁棒的局部二值模式人脸识别算法
A Novel Face Recognition Algorithm Based on Robust Local Binary Pattern
DOI: 10.12677/CSA.2013.38060, PDF,  被引量    科研立项经费支持
作者: 程雷鸣, 其木苏荣：北京信息科技大学，北京；靳 薇：北京市新技术应用研究所，北京
关键词: 人脸识别；鲁棒的局部二值模式；Robust函数；马氏距离；Face Recognition; Robust Local Binary Pattern; Robust Function; Mahalanobis Distance
摘要: 本文针对LBP算法特征包含outlier和维度过高的问题提出了一种基于鲁棒的局部二值模式(RobustLBP)的快速有效的人脸识别算法。RobustLBP算法的思想是在LBP算法的基础上加上一个Robust函数除去outlier达到降维的目的。首先通过计算LBP特征各个维度和中心元素的马氏距离作为Robust函数的输入，使得Robust函数收敛估算出重要信息。然后利用这些信息求出变换矩阵除去原始LBP特征的outlier。最后比对降维后特征间的卡方距离实现人脸识别。在FERET、CAS-PEAL-R1、LFW人脸数据库上的实验证明本文提出方法在是人脸识别上具有优越性。
Abstract: This paper is aimed at solving the problems that LBP feature contains outlier and the dimension of LBP fea- ture is too high, and a fast and effective face recognition algorithm based on Robust Local Binary Pattern is proposed. The main idea of RobustLBP is setting a Robust function on the basis of original LBP. First, it calculates the Maha- lanobis distance between the mean vector and every dimension as the argument of Robust function and estimates a set of important information by making Robust function convergence. Then, it obtains a transformation matrix which is used to reject outlier of original feature by using the information. Lastly, it compares the Chi-square distance among the features after reducing dimension in order to complete face recognition. Extensive experiments on FERET, CAS- PEAL-R1 and LFW face databases validate the effectiveness of face recognition.
文章引用：程雷鸣, 其木苏荣, 靳薇. 基于鲁棒的局部二值模式人脸识别算法[J]. 计算机科学与应用, 2013, 3(8): 344-348. https://dx.doi.org/10.12677/CSA.2013.38060

参考文献

[1] Ojala, T., Pietikäinen, M. and Harwood, D. (1994) Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. Proceedings of the 12th IAPR International Conference on Pattern Recognition (ICPR 1994), 1, pp. 582-585.
[2] Lei, Z., Pietikäinen, M. and Li, S.Z. (2013) Learning discrimi- nant face descriptor. TPAMI, p. 112.
[3] Cao, Z., Yin, Q., Tang, X. and Sun, J. (2010) Face recognition with learning-based descriptor. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, 13-18 June 2010, pp. 2707-2714.
[4] Lei, Z., Yi, D. and Li, S.Z. (2012) Discriminant image filter learning forface recognition with local binary pattern like repre- sentation. 2012 IEEE Conference on Biometrics Compendium, Computer Vision and Pattern Recognition (CVPR), Providence, 16-21 June 2012, pp. 2512-2517.
[5] Pietikäinen, M., Hadid, A., Zhao, G. and Ahonen, T. (2011) Com- puter vision using local binary patterns. Springer, New York.
[6] Zhang, W., Shan, S., Gao, W. and Zhang, H. (2005) Local gabor binary patternhistogram sequence (lgbphs): A novel non-statis- tical model for facerepresentation and recognition. 10th IEEE International Conference on Computer Vision, 1, pp. 786-791.
[7] Maturana, D., Mery, D. and Soto, A. (2011) Learning discrimi- native local binary patterns for face recognition. 2011 IEEE In- ternational Conference on Automatic Face & Gesture Recogni- tion and Workshops, Santa Barbara, 21-25 March 2011, pp. 470- 475.
[8] Maturana, D., Mery, D. and Soto, A. (2010) Face recognition with decisiontree-based local binary patterns,” Computer Vision ACCV, 6495, pp. 618-629.
[9] Meng, X., Shan, S., Chen, X. and Gao, W. (2006) Local visual primitives (lvp) for face modelling and recognition. 18th Inter- national Conference on Pattern Recognition, 2, pp. 536-539.
[10] Zhang, B., Shan, S., Chen, X. and Gao, W. (2007) Histogram of gaborphase patterns (hgpp): A novel object representation ap- proach for facerecognition. IEEE T-IP, 16, pp. 57-68.
[11] Xie, S., Shan, S., Chen, X., Meng, X. and Gao, W. (2009) Learned local ga-borpatterns for face representation and recogni- tion. Signal Processing, 89, pp. 2333-2344.
[12] Ahonen, T., Hadid, A. and Pietikainen, M. (2006) Face descrip- tion with localbinary patterns: Application to face recognition. IEEE T-PAMI, 28, pp. 2037-2041.