盛剑会;范春年;

• 1:中原工学院计算机学院
• 2:南京信息工程大学计算机与软件学院

摘要(Abstract)：

为了消除光照变化对人脸识别的影响,提出了一种新的基于小波的光照归一化算法。首先对人脸图像进行三级小波分解,获取低频和高频系数;接着对低频成分直方图均衡化,减弱光照的影响,同时对高频成分阈值去噪,再放大高频以增强图像边缘;最后进行逆小波变换,得到归一化后的人脸图像。在Yale B人脸库上的实验结果表明:本文方法可有效减弱光照变化对人脸识别的影响,显著地提高了人脸识别系统的识别率。

关键词(KeyWords)： 人脸识别;光照;小波分析;光照归一化;直方图均衡化;去噪;朗伯光照模型;YaleB人脸库

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金资助项目(60723003)

作者(Authors): 盛剑会;范春年;

参考文献(References)：

• [1]Zhao W.Face Recognition:A Literature Survey[J].ACM ComputingSurveys,2003,35(4):399–458.
• [2]Phillips P J,W T Scruggs.FRVT 2006 and ICE 2006 Large-ScaleExperimental Results[J].IEEE Transactions on Pattern Analysis andMachine Intelligence,2010,32(5):831-846.
• [3]Adini Y,Y Moses,S Ullman.Face Recognition:The Problem ofCompensating for Changes in Illumination Direction[J].IEEETransactions on Pattern Analysis and Machine Intelligence,1997,19(7):721-732.
• [4]Shan S.Illumination normalization for robust face recognition againstvarying lighting conditions[C]//.In Proceedings of the IEEEInternational Workshop on Analysis and Modeling of Faces andGestures(AMFG’03).Washington DC.USA:IEEE Computer Society,2003:157-164.
• [5]Du S,R Ward.Wavelet-based illumination normalization for facerecognition[C]//.In IEEE International Conference on ImageProcessing(ICIP 2005).Washington DC.USA:IEEE Computer Society2005:954-957.
• [6]Belhumeur P N,D J Kriegman.What is the set of images of an objectunder all possible illumination conditions[J].International Journal ofComputer Vision,1998,28(3):245-260.
• [7]Georghiade A S,P N Belhumeur.From Few to Many:Illumination ConeModels for Face Recognition Under Variable Lighting and Pose[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(6):643-660.
• [8]Basri R.,D W Jacobs.Lambertian reflectance and linear subspaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(2):218-233.
• [9]滕云,贺春林,汤永斌.基于相频特性的具有光照鲁棒的人脸识别研究[J].计算机科学,2010(08):290-293.
• [10]Shashua A,T Riklin-Raviv.The Quotient Image:Class-BasedRe-Rendering and Recognition with Varying Illuminations[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2001,23(2):129-139.
• [11]Jobson D J,Z Rahman,G A Woodell.A multiscale retinex for bridgingthe gap between color images and the human observation of scenes[J].IEEE Transactions on Image Processing,1997,6(7):965-976.
• [12]Chen T.Total variation models for variable lighting face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(9):1 519-1 524.
• [13]Gross R,V Brajovic.An Image Preprocessing Algorithm forIllumination Invariant Face Recognition[C]//.in Audio-andVideo-Based Biometric Person Authentication.Guildford,UK:Springer,2003:10-18.
• [14]Zhang T P.Face Recognition Under Varying Illumination UsingGradientfaces[J].IEEE Transactions on Image Processing,2009,18(11):2 599-2 606.
• [15]章毓晋.图像工程(上册)图像处理:第2版[M].北京:清华大学出版社,2006.
• [16]Feng G C,P C Yuen,D Q Dai.Human face recognition using PCA onwavelet subband[J].Journal of Electronic Imaging,2000,9(2):226-233.
• [17]陈武凡.小波分析及其在图像处理中的应用[M].北京:科学出版社,2002.
• [18]Donoho D L.De-noising by Soft-thresholding[J].IEEE Transaction onInformation Theory,1995,41(3):613-627.
• [19]Sim T,S Baker,M Bsat.The CMU pose,illumination,and expressiondatabase[J].IEEE Transactions on Pattern Analysis and MachineIntelligence,2003,25(12):1 615-1 618.
• [20]P J Phillips,H Wechsler,P J Rauss,et al.The FERET Database andEvaluation Procedure for Face Recognition Algorithms[J].Image andVision Computing,1998,16(5):295-306.