光照变化条件下人脸识别方法研究

系统仿真学报 ›› 2016, Vol. 28 ›› Issue (3): 689-695.

光照变化条件下人脸识别方法研究

孔锐, 张冰

暨南大学电气信息学院, 广东珠海 519070

收稿日期:2014-08-27 修回日期:2015-07-09 发布日期:2020-07-02
作者简介:孔锐(1964-),男,合肥,博士,副教授,研究方向为图像处理、模式识别;张冰(1965-),女,苏州,高工,研究方向为图像处理。
基金资助:
广东省学科建设专项资金项目-科技创新(2013KJCX0023);珠海市公共技术服务平台科技项目(2013D0501990013)

Research on Face Recognition Method Under Uncontrolled Illumination Variation

Kong Rui, Zhang Bing

College of Electrical and Information, Jinan University, Zhuhai 519070, China

Received:2014-08-27 Revised:2015-07-09 Published:2020-07-02

摘要/Abstract

摘要： 提出了一种在变化光照条件下,具有高识别率和快速的人脸识别新算法。新算法利用韦伯局部描述算子对人脸图像进行预处理,经预处理后的图像在对光照变化具有鲁莽性,采用改进的线性判别分析算法进行特征提取,利用最近邻分类器进行分类识别。新算法分别在Yale、The Extended Yale Database B人脸库进行测试,并与一些经典的方法进行比较,实验结果显示,新算法可以获得较高的识别率,尤其是在光照变化比较大的情况下,新算法更具优势,同时,新算法的速度快,完全满足变化光照条件下的人脸识别实时性的要求。

关键词: 韦伯法则, 特征提取, 人脸识别, 线性判别分析

Abstract: A new face recognition algorithm is proposed with high recognition rate under uncontrolled illumination conditions. The new algorithm process face images in advance using Weber local descriptor, which means that the processed image is insensitive to illumination changing. An improved linear discriminant analysis algorithm is adopt for feature extracting, finally, nearest neighbor classifier based on Euclidean distance is applied to classify. The new algorithm is tested on Yale and The Extended Yale Database B face database respectively, in comparison with classic face recognition algorithms, the performance of the proposed method is superior to other's under uncontrolled illumination variation and the speed of the proposed method can fully meet the requirements of real-time face recognition.

Key words: weber's law, feature extracting, face recognition, fisher linear discriminant analysis

中图分类号:

TP391.41

孔锐, 张冰. 光照变化条件下人脸识别方法研究[J]. 系统仿真学报, 2016, 28(3): 689-695.

Kong Rui, Zhang Bing. Research on Face Recognition Method Under Uncontrolled Illumination Variation[J]. Journal of System Simulation, 2016, 28(3): 689-695.

参考文献

[1] B Becker, E Ortiz.Evaluation of face recognition techniques for application to Facebook[C]// IEEE International Conference, Automatic Face Gesture Recognition. USA: IEEE, 2008: 1-6.
[2] S M Pizer, E P Amburn.Adaptive histogram equalization and its variations[J]. Computer Vision Graphics & Image Processing (S0734-189X), 1987, 39(3): 355-368.
[3] Savvides M, Kumar V.Illumination normalization using logarithm transforms for face authentication[C]// Proceedings IAPR AVBPA. Guildford, UK: Springer Berlin Heidelberg, 2003, 2688: 549-556.
[4] Neelamma K Patil, Vasudha S, Lokesh R Boregowda.A Novel Method for Illumination Normalization for Performance Improvement of Face Recognition System[C]//2013 International Symposium on Electronic System Design. Singapore: IEEE, 2013: 148-152.
[5] L E Castillo, L A Cament, F J Galdames, et al.Illumination normalization method using Kolmogorov- Nagumo-based statistics for face recognition[J]. Electronics Letters (S0013-5194), 2014, 50(13): 940-942.
[6] J Ruiz-del-Solar, J Quinteros. Illumination compensation and normalization in eigenspace-based face recognition: A comparative study of different pre-processing approaches[J]. Pattern Recognition Letter (S0167-8655), 2008, 29(14): 1966-1979.
[7] Swarup Ku Dandpat, Sukadev Meher.Quality Based Illumination Compensation for Face Recognition[C]// 2011 International Conference on Image Information Processing (ICIIP 2011). Himachal Pradesh, INDIA: IEEE, 2011: 1-4.
[8] Chia-Po Wei, Chih-Fan Chen, Yu-Chiang Frank Wang. Robust Face Recognition with Structurally Incoherent Low-Rank Matrix Decomposition[J]. IEEE Transactions on Image Processing(S1057-7149), 2014, 23(8): 3294-3307.
[9] S Hitesh Babu, Shreyas H R, K Manikantan, et al. Face Recognition using Active Illumination Equalization and Mirror Image Superposition as Pre-processing techniques[C]// 2014 Fifth International Conference on Signals and Image Processing. Bangalore, India: IEEE, 2014: 96-101.
[10] Kuo-Chin Fan, Tsung-Yung Hung.A Novel Local Pattern Descriptor-local Vector Pattern in High-Order Derivative Space for Face Recognition[J]. IEEE Transactions on Image Processing(S1057-7149), 2014, 23(7): 2877-2891.
[11] Shan Du, Mohamed Shehata, Wael Badawy.A Novel Algorithm for Illumination Invariant DCT-based Face Recognition[C]// 2012, 25th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE). USA: IEEE, 2012.
[12] A Wagner, J Wright, A Ganesh, et al.Toward a practical face recognition system: Robust alignment and illumination by sparse representation[J]. IEEE Transaction Pattern Analysis Machine Intelligence (S0162-8828), 2012, 34(2): 372-386.
[13] Biao Wang, Weifeng Li, Wenming Yang, et al.Illumination Normalization Based on Weber’s Law With Application to Face Recognition[J]. IEEE Signal Processing Letters (S1070-9908), 2011, 18(8): 462-465.
[14] Yang J, Yang J Y.Why can LDA be performed in PCA transformed space?[J]. Pattern Recognition (S0031-3203), 2003, 36(2): 563-566.
[15] 章毓晋. 基于子空间的人脸识别[M]. 北京: 清华大学出版社, 2009: 82-88.
[16] J Chen, S Shan, C He, et al.WLD: A robust local image descriptor[J]. IEEE Transaction Pattern Analysis Machine Intelligence(S0162-8828), 2010, 32(9): 1705-1720.