人脸识别中的光照问题研究
|
摘要
人脸识别研究就是要赋予计算机根据人脸面孔识别人物身份的能力,该研究具有重要的理论价值和巨大的应用前景。经过四十多年的发展,人脸识别研究已经取得了重大进展,但仍存在一些不尽人意的地方,还需要解决光照变化、姿态变化、表情变化等问题。
本文主要关注于人脸识别中的光照问题,分析了光照变化影响人脸识别的原因,概述了人脸识别中光照问题的研究现状,针对目前解决方法中的一些缺点,从图像预处理、提取光照不敏感特征、图像预处理方法与光照不敏感特征结合三个方面对光照问题进行了研究,主要做了如下工作:
1)实验对比分析了分块直方图匹配、分块直方图均衡化和对比度受限直方图均衡化这三种处理效果较好的基于传统图像处理技术的光照预处理方法,结果表明当人脸图像存在阴影时,这三种方法对阴影的削弱能力有限,并且在处理中增强了噪声。
2)基于Retinex理论的光照正则化方法削弱阴影的能力总体上比基于传统图像处理技术的人脸预处理方法好,但这类方法在人脸图像存在较强阴影时,易在阴影边缘处产生光晕现象,光晕现象的产生严重的影响了后续的人脸识别。针对这一问题提出了基于L2范数约束的总变分模型(TVL2)的对数域光照正则化方法LogTVL2,由于TVL2具有较好的边缘保持能力,所提出的LogTVL2方法能较好的削弱光晕现象。从处理效果、处理耗时和识别率三个方面,将LogTVL2与MSR、LogDCT和SQI这三种典型方法进行了实验比较,验证了LogTVL2光照正则化方法的有效性。
3)现有光照预处理方法均没有考虑输入人脸图像的光照情况,而是对它们进行相同的处理。当人脸图像存在较大的光照变化时,现有的光照预处理方法均能在一定程度上削弱光照的变化,提高识别率,但是对于光照比较均匀的人脸图像,这些处理方法却带来了负面影响。针对这一问题,提出了“人脸图像光照质量指数”,人脸图像光照质量指数定义为待测人脸图像的光照估计图像与参考人脸图像的光照估计图像的相似度,参考人脸图像的光照条件是均匀或近似均匀的,通过保留人脸图像离散余弦变换的部分低频系数估计人脸的光照图像。实验结果表明,该方法能较好的定性衡量人脸图像光照不均匀程度。根据输入人脸图像的光照质量指数可以判断该图像是否需要经过预处理,避免预处理方法对光照情况较好的人脸图像带来负面效应。
4)人脸面部对象的轮廓是进行人脸识别的重要特征,并且它对光照具有一定的不敏感性,梯度是刻画这些轮廓的一种重要方式,基于Retinex理论和图像处理的角度,分析比较了对数域梯度、对数域垂直梯度及对数域水平梯度的光照不敏感性,并提出在决策级将三者加权融合,优势互补,提高对光照变化的不敏感性,并通过实验对该方法的有效性进行了验证。
5)结合前面提出的方法,提出了健壮的链式处理方法,首先计算输入人脸图像的光照质量指数,根据计算值确定输入人脸图像是否需要进行光照预处理,若需要,则利用提出的LogTVL2进行光照正则化处理,然后提取梯度方向、梯度幅度特征,然后将梯度方向与梯度幅度特征在决策级别融合,进行识别;若不需要,则直接利用正则化相关进行识别。实验表明LogTVL2光照正则化方法与梯度方向的结合,能较好的提高识别性能,链式处理增强了对光照变化的鲁棒性。
The target of research on face recognition is to endow computer with the ability of identifying people according faces. Face recognition has made great progress after more than forty years of research, but there still exist many unsatisfactory aspects. It needs more research on the problems of illumination variations, pose variations, expression variations and so on.
The dissertation mainly focuses on illumination variations problem in face recognition. We analyze why illumination variations could affect face recognition. An overview of the state-of-the-art of illumination problem in face recognition is given. Research is conducted from three aspects: image preprocessing, extract illumination insensitive features, the combination of image preprocessing and illumination insensitive features. The main work of this dissertation is as follows:
1) Block histogram equalization, block histogram match, and contrast limited adaptive histogram equalization are three illumination preprocessing methods based on traditional image processing techniques. Their performances are better than other methods of the same type. Experiments are conducted in order to compare them. The results show that they do not work well and enhance noise when there are shadows in face image.
2) Illumination normalization methods based on Retinex theory have better capability of weakening shadows than illumination preprocessing methods based on traditional image processing techniques. When there are heavy shadows in face image, halo effect is produced at the edges of shadows after preprocessing by the existing illumination normalization methods based on Retinex theory. The halo effect could worsen the successive face recognition. To address this problem, an illumination normalization method named LogTVL2 based on Total Variation Model under L2 norm constraint is proposed. Because the TVL2 model has better capability of edge-preserving, the LogTVL2 could weaken halo effect well. In order to validate the performance of LogTVL2, experiments are conducted from three aspects: capability of weakening halo effect, time-consuming and performance of recognition. The LogTVL2 is compared with three representative methods MSR, LogDCT and SQI.
3) At present, all the illumination preprocessing methods treat all face images in the same way without considering the specific illumination conditions. Although most of illumination preprocessing approaches can improve the recognition rate when probe images with large variations in lighting, they may have a bad effect on well-lit face images and lead to a decrease in recognition rate. To address this problem, illumination quality index of face image is proposed. The luminance images of probe face image and reference face image are first estimated. The reference face image is with normal illumination. The similarity score of the two estimated luminance images are calculated by normalized correlation. The similarity score obtained is defined as the illumination quality index of the probe image. Luminance image is estimated by only saving some low-frequency discrete cosine transform coefficients and then conducting inverse transform. Experimental results show that the illumination quality index of face image can measure the degree of uneven illumination of face image well. According to the IQI of input face image, we can decide whether illumination preprocessing should be used on it. This could avoid bringing bad effect on face images with good illumination conditions.
4) The edges of facial objects are important cue for face recognition and are less sensitive to illumination changes. The illumination insensitivity of logarithmic gradient (LG), logarithmic vertical gradient (LVG) and logarithmic horizontal gradient (LHG) are compared based on Retinex theory and image processing techniques. By taking advantages of the LVG, LG and LHG, we fuse them at decision level. Experimental results demonstrate the effectiveness of the proposed method.
5) Combining with the methods proposed above, a robust processing chain is proposed. Firstly the illumination quality index of probe image is calculated. According to the IQI, probe image with approximately normal illumination can be excluded. The excluded probe image needs no illumination normalization and directly step into recognition by normalized correlation. It not only decreases the possibility of misclassification but also saves times. In order to enhance robustness of face recognition to illumination variations, LogTVL2 is conducted on these non-excluded probe images. Then illumination normalized face images are fed to a new fusion algorithm combining gradient direction and magnitude at decision level. This preprocessing chain makes face recognition more reliable under varying illumination.
本文主要关注于人脸识别中的光照问题,分析了光照变化影响人脸识别的原因,概述了人脸识别中光照问题的研究现状,针对目前解决方法中的一些缺点,从图像预处理、提取光照不敏感特征、图像预处理方法与光照不敏感特征结合三个方面对光照问题进行了研究,主要做了如下工作:
1)实验对比分析了分块直方图匹配、分块直方图均衡化和对比度受限直方图均衡化这三种处理效果较好的基于传统图像处理技术的光照预处理方法,结果表明当人脸图像存在阴影时,这三种方法对阴影的削弱能力有限,并且在处理中增强了噪声。
2)基于Retinex理论的光照正则化方法削弱阴影的能力总体上比基于传统图像处理技术的人脸预处理方法好,但这类方法在人脸图像存在较强阴影时,易在阴影边缘处产生光晕现象,光晕现象的产生严重的影响了后续的人脸识别。针对这一问题提出了基于L2范数约束的总变分模型(TVL2)的对数域光照正则化方法LogTVL2,由于TVL2具有较好的边缘保持能力,所提出的LogTVL2方法能较好的削弱光晕现象。从处理效果、处理耗时和识别率三个方面,将LogTVL2与MSR、LogDCT和SQI这三种典型方法进行了实验比较,验证了LogTVL2光照正则化方法的有效性。
3)现有光照预处理方法均没有考虑输入人脸图像的光照情况,而是对它们进行相同的处理。当人脸图像存在较大的光照变化时,现有的光照预处理方法均能在一定程度上削弱光照的变化,提高识别率,但是对于光照比较均匀的人脸图像,这些处理方法却带来了负面影响。针对这一问题,提出了“人脸图像光照质量指数”,人脸图像光照质量指数定义为待测人脸图像的光照估计图像与参考人脸图像的光照估计图像的相似度,参考人脸图像的光照条件是均匀或近似均匀的,通过保留人脸图像离散余弦变换的部分低频系数估计人脸的光照图像。实验结果表明,该方法能较好的定性衡量人脸图像光照不均匀程度。根据输入人脸图像的光照质量指数可以判断该图像是否需要经过预处理,避免预处理方法对光照情况较好的人脸图像带来负面效应。
4)人脸面部对象的轮廓是进行人脸识别的重要特征,并且它对光照具有一定的不敏感性,梯度是刻画这些轮廓的一种重要方式,基于Retinex理论和图像处理的角度,分析比较了对数域梯度、对数域垂直梯度及对数域水平梯度的光照不敏感性,并提出在决策级将三者加权融合,优势互补,提高对光照变化的不敏感性,并通过实验对该方法的有效性进行了验证。
5)结合前面提出的方法,提出了健壮的链式处理方法,首先计算输入人脸图像的光照质量指数,根据计算值确定输入人脸图像是否需要进行光照预处理,若需要,则利用提出的LogTVL2进行光照正则化处理,然后提取梯度方向、梯度幅度特征,然后将梯度方向与梯度幅度特征在决策级别融合,进行识别;若不需要,则直接利用正则化相关进行识别。实验表明LogTVL2光照正则化方法与梯度方向的结合,能较好的提高识别性能,链式处理增强了对光照变化的鲁棒性。
The target of research on face recognition is to endow computer with the ability of identifying people according faces. Face recognition has made great progress after more than forty years of research, but there still exist many unsatisfactory aspects. It needs more research on the problems of illumination variations, pose variations, expression variations and so on.
The dissertation mainly focuses on illumination variations problem in face recognition. We analyze why illumination variations could affect face recognition. An overview of the state-of-the-art of illumination problem in face recognition is given. Research is conducted from three aspects: image preprocessing, extract illumination insensitive features, the combination of image preprocessing and illumination insensitive features. The main work of this dissertation is as follows:
1) Block histogram equalization, block histogram match, and contrast limited adaptive histogram equalization are three illumination preprocessing methods based on traditional image processing techniques. Their performances are better than other methods of the same type. Experiments are conducted in order to compare them. The results show that they do not work well and enhance noise when there are shadows in face image.
2) Illumination normalization methods based on Retinex theory have better capability of weakening shadows than illumination preprocessing methods based on traditional image processing techniques. When there are heavy shadows in face image, halo effect is produced at the edges of shadows after preprocessing by the existing illumination normalization methods based on Retinex theory. The halo effect could worsen the successive face recognition. To address this problem, an illumination normalization method named LogTVL2 based on Total Variation Model under L2 norm constraint is proposed. Because the TVL2 model has better capability of edge-preserving, the LogTVL2 could weaken halo effect well. In order to validate the performance of LogTVL2, experiments are conducted from three aspects: capability of weakening halo effect, time-consuming and performance of recognition. The LogTVL2 is compared with three representative methods MSR, LogDCT and SQI.
3) At present, all the illumination preprocessing methods treat all face images in the same way without considering the specific illumination conditions. Although most of illumination preprocessing approaches can improve the recognition rate when probe images with large variations in lighting, they may have a bad effect on well-lit face images and lead to a decrease in recognition rate. To address this problem, illumination quality index of face image is proposed. The luminance images of probe face image and reference face image are first estimated. The reference face image is with normal illumination. The similarity score of the two estimated luminance images are calculated by normalized correlation. The similarity score obtained is defined as the illumination quality index of the probe image. Luminance image is estimated by only saving some low-frequency discrete cosine transform coefficients and then conducting inverse transform. Experimental results show that the illumination quality index of face image can measure the degree of uneven illumination of face image well. According to the IQI of input face image, we can decide whether illumination preprocessing should be used on it. This could avoid bringing bad effect on face images with good illumination conditions.
4) The edges of facial objects are important cue for face recognition and are less sensitive to illumination changes. The illumination insensitivity of logarithmic gradient (LG), logarithmic vertical gradient (LVG) and logarithmic horizontal gradient (LHG) are compared based on Retinex theory and image processing techniques. By taking advantages of the LVG, LG and LHG, we fuse them at decision level. Experimental results demonstrate the effectiveness of the proposed method.
5) Combining with the methods proposed above, a robust processing chain is proposed. Firstly the illumination quality index of probe image is calculated. According to the IQI, probe image with approximately normal illumination can be excluded. The excluded probe image needs no illumination normalization and directly step into recognition by normalized correlation. It not only decreases the possibility of misclassification but also saves times. In order to enhance robustness of face recognition to illumination variations, LogTVL2 is conducted on these non-excluded probe images. Then illumination normalized face images are fed to a new fusion algorithm combining gradient direction and magnitude at decision level. This preprocessing chain makes face recognition more reliable under varying illumination.
引文
[1]田捷,杨鑫.生物特征识别技术理论与应用[M].北京:电子工业出版社,2005:23-25.
[2]张志伟.可变光照条件下的人脸识别技术研究[D].河北:河北工业大学博士学位论文,2007:4-5
[3]周激流,张晔.人脸识别理论研究进展[J].计算机辅助设计与图形学学报,1999,11(2):180-184.
[4]山世光.人脸识别中若干关键问题的研究[D].北京:中国科学院计算技术研究所博士学位论文,2004:8-9.
[5]P. J. Phillips, P. Grother, R. Micheals, R. Blackbum, et al.. Face recognition vendor test 2002, http:// www. frvt. org.
[6]Y Adini, Y. Moses, S. Ullman. Face recognition: the problem of compensating for changes in illumination direction [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):721-732.
[7]A. S. Georghiades, P. N. Belhumeur ,D. J. Kriegman. From few to many: illumination cone models for face recognition under variable lighting and pose [J]. IEEE Transaction Pattern Analysis and Machine Intelligence, 2001, 23(6):643-660.
[8]K. C. Lee, J. Ho, D. Kriegman. Acquiring linear subspaces for face recognition under variable lighting. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2005, 27(5):684-698.
[9]M. Turk, A. Pentland. Eigenfaces for recognition [J]. Cognitive Neuroscience, 1991, 3(1): 71-86.
[10]卿来云.人脸识别中的光照问题研究[D].北京:中国科学院计算技术研究所博士学位论文,2005:3-4.
[11]王建国.特征抽取方法研究及其在人脸识别中的应用[D].南京:南京理工大学博士学位论文,2008:2-3.
[12]P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman. Eigenfaces vs. fisherfaces: recognition using class specific linear projection [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 20(7):711-720.
[13]M. S. Bartlett, J. R. Movellan, T. J. Sejnowski. Face recognition by independent component analysis [J].IEEE Transaction on Neural Networks, 2002, 13(6):1450-1464.
[14]J. Yang, D. Zhang, F. Alejandro, et al.. Two-Dimensional PCA: a new approach to appearance-based face representation and recognition [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2004, 26(1):131-137.
[15]X. Wang, X. Tang. A unified framework for subspace face recognition [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2004, 26(9):1222-1228.
[16]A. Shashua. On photometric issue in 3D visual recognition from a single 2D Image [J]. International Journal of Computer Vision, 1997, 21(1):99-122.
[17]A. U. Batur, M. H. Hayes. Linear subspaces for illumination robust face recognition[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, 2:296-301.
[18]P. Belhumeur, D. Kriegman. What is the set of images of an object under all possible illumination conditions[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998, 28(3):245-260.
[19]A. S. Georghiades, P. N. Belhumeur ,D. J. Kriegman. From few to many: illumination cone models for face recognition under variable lighting and pose [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2001, 23(6):643-660.
[20]R. Basri, D. Jacobs. Lambertian reflectance and linear subspaces [J]. IEEE Transaction Pattern Analysis and Machine Intelligence, 2003, 25(2):218-233.
[21]L. Zhang, D. Samaras. Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics [J]. IEEE Transaction Pattern Analysis and Machine Intelligence, 2006, 28(3):351-363.
[22]V. Blanz, T. Vetter. Face recognition based on fitting a 3D morphable model [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003, 25(9):1063-1073.
[23]Y. Gao, M. Leung. Face recognition using line edge map [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002, 24(6):764-779.
[24]S. Wei, S. Lai. Robust face recognition under lighting variations[C].International Conference on Pattern Recognition, 2004, 1:354-357.
[25]T. Zhang, Y. Tang, B. Fang, Z. Shang X. Liu. Face recognition under varying illumination using gradientface [J]. IEEE Transactions on Image Processing, 2009, 18(11):2599-2606.
[26]M. Savvides, B. V. K. Vijaya Kumar , P. K. Khosla. Eigenphases vs. eigenfaces[C].International Conference on Pattern Recognition, 2004, 3:810-813.
[27]唱轶钲,山世光,高文,曹波,杨鹏. Gabor特征判别分析人脸识别方法的误配准鲁棒性分析[J].计算机工程与应用,2005,28(5):56-59.
[28]山世光,高文,唱铁钲,曹波,陈熙霖.人脸识别中的“误配准灾难”问题研究[J].计算机学报,2005,28(5):782-790.
[29]Ahone, T. Hadid, A. Pietikainen. Face recognition with local binary patterns[C]. Proceedings of the European Conference on Computer Vision, 2004: 469-481.
[30]B. Zhang. Histogram of Gabor Phase Patterns: A novel object representation approach for face recognition [J]. IEEE Transactions on Image Processing, 2007, 16(1):57-68.
[31]张文超,山世光,张洪明等.基于局部Gabor变化直方图序列的人脸描述与识别[J].软件学报, 2006 ,17 (12) :2508 - 2517.
[32]阮秋琦.数字图像处理[M].北京:电子工业出版社,2005:58-60.
[33]S. Shan, W. Gao, B. Cao,D. Zhao. Illumination normalization for robust face recognition against varying illumination conditions[C]. IEEE workshop on Analysis and Modeling of Faces and Gestures, 2003:157-164.
[34]M. Savvides, B. V. K. Vijaya Kumar. Illumination Normalization Using Logarithm Transforms for face recognition [J].Audio and video based biometric person authentication lecture notes in Computer Science, 2003, 2688:549-556.
[35]X. Feng, Y. Wang, Y. Gao. A framework of local illumination normalization for face recognition [J]. 2007 IEEE International Workshop on Anti-counterfeiting, Security, Identification, 2007:199-203.
[36]X. Xie, K. Lam. An efficient illumination normalization method for face recognition [J]. Pattern Recognition Letters, 2006, 27(6):609-617.
[37]S. Du, R. K. Ward. Adaptive region-based imaged enhancement method for robust face recognition under variable illumination conditions [J]. IEEE Transaction on Circuits and Systems for Video Technology, 2010, 20(9):1165-1175.
[38]E. H. Land, J. J. Mccann. Lightness and Retinex theory [J]. Journal of the Optical Society of America, 1971, 61(1):1-11.
[39]D. J. Jobson, Z. Rahman, G. A. Woodel. A multiscale Retinex for bridging the gap between color images and the human observation of scenes [J]. IEEE Transaction on Image Processing, 1997, 6(7):965-976.
[40]R. Gross, V. Brajovic. An image pre-processing algorithm for illumination invariant face recognition[C].Proceedings of Fourth International Conference Audio and Video Based Biometric Person Authentication, 2003:10-18.
[41]H. Wang, S. Li ,Y. Wang. Generalized quotient image [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2004, 2:498-505.
[42]王海涛,刘俊,王阳生.自商图像[J].计算机工程, 2005,31(18):178-215.
[43]T. Chen, W. Yin, X. Zhou, D. Comaniciu, T. S. Huang. Total variation models for variable lighting face recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(9):1519-1524.
[44]庄连生.复杂光照条件下人脸识别关键算法研究[D].安徽:中国科学技术大学博士学位论文,2006:29-31.
[45]W. Chen, M. J. Er, S. Wu. Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain [J]. IEEE Transaction System, Man, and Cybernetics-Part B, 2006, 36(2):458-466.
[46]Y. Z. Goh, B.J. Andrew, K. O. Michael. Wavelet based illumination invariant preprocessing in face recognition[C]. Congress on Image and Signal Processing, 2008, 3:421-425.
[47]Z. Lian, M.J.Er. Illumination normalization for face recognition in transformed domain [J]. Electronics Letter, 2010, 46(15):1060-1061.
[48]P. J. Phillips, H. Wechsler, P. Rauss. The FERET database and evaluation procedure for face recognition algorithm [J]. Image and Vision Computing, 1998, 16(5):295-306.
[49]张晓华,山世光,曹波,高文,周德龙,赵得斌. CAS-PEAL大规模中国人脸图像数据库及其基本测评介绍[J].计算机辅助设计与图形学报,2005,17(1):9-17.
[50]T. Sim, S. Baker, M. Bsat. The CMU pose, illumination, and expression database [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(12):1615-1618.
[51]安高云.复杂条件人脸识别中若干关键问题的研究[D].北京:北京交通大学博士学位论文,2008:101-104.
[52]S. M. Pizer, E. P. Amburn, et al.. Adaptive histogram equalization and its variations [J]. Computer Vision, Graphics, and Image Processing, 1987, 39(3):355-368.
[53]J.B. Zimmerman, S.M. Pizer, E.V. Stab, et al.. Contrast limited adaptive histogram equalization [J]. Graphics Gems, 1994: 474-485.
[54]L. Rudin, S. Osher, E. Fatemi. Nonlinear total variation based noise removal algorithms [J]. Physica D: Nonlinear Phenomenon, 1992, 60:259-268.
[55]A. Chambolle. An algorithm for total variation minimization and application [J]. Journal of Mathematical Imaging and Vision, 2004, 20(1):89-97.
[56]庄连生,龙飞,庄镇泉,李斌.基于全变分模型的光照处理算法[J].电路与系统学报,2008,13(5):103-106.
[57]H. Sellahewa ,S.A. Jassim. Image-quality-based adaptive face recognition [J]. IEEE Transactions on Instrumentation and Measurement, 2010, 59(4):805-813.
[58]O. Arandjelovic, R. Cipolla. A methodology for rapid illumination-invariant face recognition using processing filters [J]. Computer Vision and Image Understanding, 2009, 113(2):159-171.
[59]X. Wang, X. Tang. Unified subspace analysis for face recognition[C].Ninth IEEE International Conference on Computer Vision, 2003,1:679-686.
[60]H. Han, S. Shan, L. Qing, X. Chen, W. Gao. Lighting aware preprocessing for face recognition across varying illumination[C]. European Conference on Computer Vision, 2010:308-321.
[61]阮秋琦.数字图像处理学[M].北京:电子工业出版社,2001:82-84.
[62]J. Kittler, M. Hatef, R. Duin, J. Matas. On combining classifiers [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(3):226-239.
[63]X. Tan, B. Triggs. Enhanced local texture feature sets for face recognition under difficult lighting conditions [J]. IEEE Transactions on Image Processing, 2010, 19(6):1635-1650.
[64]A. Jain, K. Nandakumar, A. Ross. Score normalization in multi-modal biometrics systems [J]. IEEE Transactions on Pattern Recognition, 2005, 38(12):2270-2285.
[65]H. Chen, P. Belhumeur, D. Jacobs. In search of illumination invariants [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2000, 1:254-261.
[66]R. Gopalan, D. Jacobs. Comparing and combining lighting insensitive approaches for face recognition [J]. Computer Vision and Image Understanding, 2010, 114(1):135-145.
[2]张志伟.可变光照条件下的人脸识别技术研究[D].河北:河北工业大学博士学位论文,2007:4-5
[3]周激流,张晔.人脸识别理论研究进展[J].计算机辅助设计与图形学学报,1999,11(2):180-184.
[4]山世光.人脸识别中若干关键问题的研究[D].北京:中国科学院计算技术研究所博士学位论文,2004:8-9.
[5]P. J. Phillips, P. Grother, R. Micheals, R. Blackbum, et al.. Face recognition vendor test 2002, http:// www. frvt. org.
[6]Y Adini, Y. Moses, S. Ullman. Face recognition: the problem of compensating for changes in illumination direction [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):721-732.
[7]A. S. Georghiades, P. N. Belhumeur ,D. J. Kriegman. From few to many: illumination cone models for face recognition under variable lighting and pose [J]. IEEE Transaction Pattern Analysis and Machine Intelligence, 2001, 23(6):643-660.
[8]K. C. Lee, J. Ho, D. Kriegman. Acquiring linear subspaces for face recognition under variable lighting. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2005, 27(5):684-698.
[9]M. Turk, A. Pentland. Eigenfaces for recognition [J]. Cognitive Neuroscience, 1991, 3(1): 71-86.
[10]卿来云.人脸识别中的光照问题研究[D].北京:中国科学院计算技术研究所博士学位论文,2005:3-4.
[11]王建国.特征抽取方法研究及其在人脸识别中的应用[D].南京:南京理工大学博士学位论文,2008:2-3.
[12]P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman. Eigenfaces vs. fisherfaces: recognition using class specific linear projection [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 20(7):711-720.
[13]M. S. Bartlett, J. R. Movellan, T. J. Sejnowski. Face recognition by independent component analysis [J].IEEE Transaction on Neural Networks, 2002, 13(6):1450-1464.
[14]J. Yang, D. Zhang, F. Alejandro, et al.. Two-Dimensional PCA: a new approach to appearance-based face representation and recognition [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2004, 26(1):131-137.
[15]X. Wang, X. Tang. A unified framework for subspace face recognition [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2004, 26(9):1222-1228.
[16]A. Shashua. On photometric issue in 3D visual recognition from a single 2D Image [J]. International Journal of Computer Vision, 1997, 21(1):99-122.
[17]A. U. Batur, M. H. Hayes. Linear subspaces for illumination robust face recognition[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, 2:296-301.
[18]P. Belhumeur, D. Kriegman. What is the set of images of an object under all possible illumination conditions[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998, 28(3):245-260.
[19]A. S. Georghiades, P. N. Belhumeur ,D. J. Kriegman. From few to many: illumination cone models for face recognition under variable lighting and pose [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2001, 23(6):643-660.
[20]R. Basri, D. Jacobs. Lambertian reflectance and linear subspaces [J]. IEEE Transaction Pattern Analysis and Machine Intelligence, 2003, 25(2):218-233.
[21]L. Zhang, D. Samaras. Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics [J]. IEEE Transaction Pattern Analysis and Machine Intelligence, 2006, 28(3):351-363.
[22]V. Blanz, T. Vetter. Face recognition based on fitting a 3D morphable model [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003, 25(9):1063-1073.
[23]Y. Gao, M. Leung. Face recognition using line edge map [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002, 24(6):764-779.
[24]S. Wei, S. Lai. Robust face recognition under lighting variations[C].International Conference on Pattern Recognition, 2004, 1:354-357.
[25]T. Zhang, Y. Tang, B. Fang, Z. Shang X. Liu. Face recognition under varying illumination using gradientface [J]. IEEE Transactions on Image Processing, 2009, 18(11):2599-2606.
[26]M. Savvides, B. V. K. Vijaya Kumar , P. K. Khosla. Eigenphases vs. eigenfaces[C].International Conference on Pattern Recognition, 2004, 3:810-813.
[27]唱轶钲,山世光,高文,曹波,杨鹏. Gabor特征判别分析人脸识别方法的误配准鲁棒性分析[J].计算机工程与应用,2005,28(5):56-59.
[28]山世光,高文,唱铁钲,曹波,陈熙霖.人脸识别中的“误配准灾难”问题研究[J].计算机学报,2005,28(5):782-790.
[29]Ahone, T. Hadid, A. Pietikainen. Face recognition with local binary patterns[C]. Proceedings of the European Conference on Computer Vision, 2004: 469-481.
[30]B. Zhang. Histogram of Gabor Phase Patterns: A novel object representation approach for face recognition [J]. IEEE Transactions on Image Processing, 2007, 16(1):57-68.
[31]张文超,山世光,张洪明等.基于局部Gabor变化直方图序列的人脸描述与识别[J].软件学报, 2006 ,17 (12) :2508 - 2517.
[32]阮秋琦.数字图像处理[M].北京:电子工业出版社,2005:58-60.
[33]S. Shan, W. Gao, B. Cao,D. Zhao. Illumination normalization for robust face recognition against varying illumination conditions[C]. IEEE workshop on Analysis and Modeling of Faces and Gestures, 2003:157-164.
[34]M. Savvides, B. V. K. Vijaya Kumar. Illumination Normalization Using Logarithm Transforms for face recognition [J].Audio and video based biometric person authentication lecture notes in Computer Science, 2003, 2688:549-556.
[35]X. Feng, Y. Wang, Y. Gao. A framework of local illumination normalization for face recognition [J]. 2007 IEEE International Workshop on Anti-counterfeiting, Security, Identification, 2007:199-203.
[36]X. Xie, K. Lam. An efficient illumination normalization method for face recognition [J]. Pattern Recognition Letters, 2006, 27(6):609-617.
[37]S. Du, R. K. Ward. Adaptive region-based imaged enhancement method for robust face recognition under variable illumination conditions [J]. IEEE Transaction on Circuits and Systems for Video Technology, 2010, 20(9):1165-1175.
[38]E. H. Land, J. J. Mccann. Lightness and Retinex theory [J]. Journal of the Optical Society of America, 1971, 61(1):1-11.
[39]D. J. Jobson, Z. Rahman, G. A. Woodel. A multiscale Retinex for bridging the gap between color images and the human observation of scenes [J]. IEEE Transaction on Image Processing, 1997, 6(7):965-976.
[40]R. Gross, V. Brajovic. An image pre-processing algorithm for illumination invariant face recognition[C].Proceedings of Fourth International Conference Audio and Video Based Biometric Person Authentication, 2003:10-18.
[41]H. Wang, S. Li ,Y. Wang. Generalized quotient image [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2004, 2:498-505.
[42]王海涛,刘俊,王阳生.自商图像[J].计算机工程, 2005,31(18):178-215.
[43]T. Chen, W. Yin, X. Zhou, D. Comaniciu, T. S. Huang. Total variation models for variable lighting face recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(9):1519-1524.
[44]庄连生.复杂光照条件下人脸识别关键算法研究[D].安徽:中国科学技术大学博士学位论文,2006:29-31.
[45]W. Chen, M. J. Er, S. Wu. Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain [J]. IEEE Transaction System, Man, and Cybernetics-Part B, 2006, 36(2):458-466.
[46]Y. Z. Goh, B.J. Andrew, K. O. Michael. Wavelet based illumination invariant preprocessing in face recognition[C]. Congress on Image and Signal Processing, 2008, 3:421-425.
[47]Z. Lian, M.J.Er. Illumination normalization for face recognition in transformed domain [J]. Electronics Letter, 2010, 46(15):1060-1061.
[48]P. J. Phillips, H. Wechsler, P. Rauss. The FERET database and evaluation procedure for face recognition algorithm [J]. Image and Vision Computing, 1998, 16(5):295-306.
[49]张晓华,山世光,曹波,高文,周德龙,赵得斌. CAS-PEAL大规模中国人脸图像数据库及其基本测评介绍[J].计算机辅助设计与图形学报,2005,17(1):9-17.
[50]T. Sim, S. Baker, M. Bsat. The CMU pose, illumination, and expression database [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(12):1615-1618.
[51]安高云.复杂条件人脸识别中若干关键问题的研究[D].北京:北京交通大学博士学位论文,2008:101-104.
[52]S. M. Pizer, E. P. Amburn, et al.. Adaptive histogram equalization and its variations [J]. Computer Vision, Graphics, and Image Processing, 1987, 39(3):355-368.
[53]J.B. Zimmerman, S.M. Pizer, E.V. Stab, et al.. Contrast limited adaptive histogram equalization [J]. Graphics Gems, 1994: 474-485.
[54]L. Rudin, S. Osher, E. Fatemi. Nonlinear total variation based noise removal algorithms [J]. Physica D: Nonlinear Phenomenon, 1992, 60:259-268.
[55]A. Chambolle. An algorithm for total variation minimization and application [J]. Journal of Mathematical Imaging and Vision, 2004, 20(1):89-97.
[56]庄连生,龙飞,庄镇泉,李斌.基于全变分模型的光照处理算法[J].电路与系统学报,2008,13(5):103-106.
[57]H. Sellahewa ,S.A. Jassim. Image-quality-based adaptive face recognition [J]. IEEE Transactions on Instrumentation and Measurement, 2010, 59(4):805-813.
[58]O. Arandjelovic, R. Cipolla. A methodology for rapid illumination-invariant face recognition using processing filters [J]. Computer Vision and Image Understanding, 2009, 113(2):159-171.
[59]X. Wang, X. Tang. Unified subspace analysis for face recognition[C].Ninth IEEE International Conference on Computer Vision, 2003,1:679-686.
[60]H. Han, S. Shan, L. Qing, X. Chen, W. Gao. Lighting aware preprocessing for face recognition across varying illumination[C]. European Conference on Computer Vision, 2010:308-321.
[61]阮秋琦.数字图像处理学[M].北京:电子工业出版社,2001:82-84.
[62]J. Kittler, M. Hatef, R. Duin, J. Matas. On combining classifiers [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(3):226-239.
[63]X. Tan, B. Triggs. Enhanced local texture feature sets for face recognition under difficult lighting conditions [J]. IEEE Transactions on Image Processing, 2010, 19(6):1635-1650.
[64]A. Jain, K. Nandakumar, A. Ross. Score normalization in multi-modal biometrics systems [J]. IEEE Transactions on Pattern Recognition, 2005, 38(12):2270-2285.
[65]H. Chen, P. Belhumeur, D. Jacobs. In search of illumination invariants [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2000, 1:254-261.
[66]R. Gopalan, D. Jacobs. Comparing and combining lighting insensitive approaches for face recognition [J]. Computer Vision and Image Understanding, 2010, 114(1):135-145.