基于局部视觉模型的人脸识别研究
|
摘要
人脸识别技术方兴未艾,是模式识别和机器视觉领域的研究热点,研究内容包括人脸检测和识别、表情识别等。由于人脸识别技术在司法、安全、军事等领域有着广泛的应用前景,受到了研究人员的普遍关注,在近年来更是获得了较大的发展,一系列创新算法不断涌现,也出现了部分接近实用并初步商用化的原型系统。其中,基于局部视觉特征模型的人脸识别方法由于对光照变化等不利因素更为鲁棒的优点逐渐成为主流方法之一。本文在前人的研究基础上,针对人脸识别对光照等干扰因素敏感的问题,从局部特征入手,在图像预处理、特征提取和多特征融合识别三个方面分别进行了探讨,并完成了以下主要工作：
(1)图像预处理是人脸识别的重要前期工作,能够有效减少各种干扰因素,对后期图像识别效果的优劣影响很大。本文对人脸图像的预处理算法中,除了方向、大小等归一化步骤外,重点提出一种针对光照不均图像的预处理方法,即结合Gamma校正、高斯差分(DoG)以及对比度均衡处理为一体。该方法有效降低了光照对人脸的影响,提高了对比度,强化了人脸特征区域,有利于后续的特征提取和识别。
(2)特征提取是人脸识别的核心步骤,本文采用了多种人脸局部视觉特征的提取方法。通过分析传统算法的优缺点之后,本文在传统经典算法基础上,一方面,对LBP纹理特征进行改进,在LBP的差值计算步骤引入Dipole双极比较算子,由此提取不同距离和尺度的更大范围的局部特征,记为ILBP,即改进的LBP算法；之后,再结合Gabor特征的多方向、多尺度等优点,对人脸的Gabor特征图谱提取ILBP特征,并记为ILGBP特征。另一方面,由于实际应用中采集的人脸图像往往受光照变化、角度等因素干扰,而SIFT算法具有平移不变性、旋转不变性、尺度变化不变性等优点,本文又将SIFT特征引入人脸识别当中,用ILGBP特征和SIFT特征共同描述人脸。
(3)基于D-S证据理论和Fisherface方法进行人脸的局部多特征融合识别。鉴于D-S证据理论是基于决策级的融合,本文提出的融合识别算法是在识别过程中,首先运用Fisherface方法分别对ILGBP和SIFT特征分别进行分类识别,得到特征比对的相似度；然后,对这两个相似度,按照D-S证据理论的规则,进行信任度判别,得到最终的判别结果。由于Fisherface的特性,该方法能够有效降低特征维数,并且具有较强的鲁棒性。在MATLAB开发平台上的仿真实验结果显示,本文算法对有遮挡、低光照、侧面等不利情况有较强的识别能力。
Human face recognition technology is still going to be unfolding as a research hotspot of pattern recognition and machine visual territory, which includes the human face detective, face recognition and expression recognition etc. Because the human face recognition technology has extensive application prospect in many domains such as justice, security and military, it has been generally paid close attention to by many researchers. Therefore, the human face recognition technology has achieved great development in recent years. Also, a series of innovation algorithms had been proposed and some preliminary commercial archetype systems had been put into market. Above all the algorithms, the methods based on local visual feature model has gradually become one of the main methods because of its advantages in the recognition for the figures which have great change of illumination or other adverse factors. Based on the previously researches, we try to aim at the robustness of illumination condition and other adverse factors. Start with the local features, we do some discusses in image preprocess, feature extraction and multi-feature fusion recognition. The main tasks we had done in this paper as follows:
(1) Image preprocess is an important previous work of human face recognition. It can decrease all kinds of adverse factors efficiently and seriously influence the face recognition results. In this paper, besides the normalization of orientation, size etc, we principally proposed a preprocess algorithm aims to illumination changes. Our method includes the Gamma regulation, difference of Gaussian and contrast balance. The experiment result shows, our method can decrease the influence of illumination, raise the contrast and strengthen the effective feature areas of human face. Our preprocess methods is effective facilitate the following feature extraction and face recognition.
(2) Feature extraction is the key task of human face recognition. In this paper, we decide to extract multifarious local visual features of human face. After the analysis of the advantages and disadvantages of traditional algorithms, we do some improvement in LBP texture features firstly based on previously method. The improved LBP (ILBP) feature means that we propose a Dipole compare operator instead the simple difference operation of middle pixel and the 8 pixels border upon. The ILBP algorithm can extract the local features of bigger area in different orientations and scales. And then, we take the advantages of Gabor feature: multi-orientation and multi-scale. Based on this method, we extract the ILBP features on the figures which had already been extracted the Gabor features. We call it ILGBP feature.
In another hand, the human faces we get from the practical use condition always influenced by the changes of illumination, scales and other adverse factors. Yet, the SIFT algorithm has the advantages of translation invariance, rotational invariance and scale transform invariance. Therefore, we use both the ILGBP feature and SIFT feature to describe a human face.
(3) We use a method that based on D-S evidence theory and Fisherface algorithm to do the human face recognition based on multi-feature fusion. Because the D-S evidence theory is a method of inosculation on the level of strategic decision, in our method, we use the Fisherface algorithm to do the face recognition on ILGBP feature and SIFT feature respectively firstly. After the Fisherface feature contrast, we will get two similarity values which could be transformed to trust values use the regulations of D-S evidence theory. At last, we can successfully get the recognize results by the means of trust values. Because of the property of Fisherface algorithm, our method can decrease the feature dimension efficiently. What's more, it has stronger robustness.
The experiment results in MATLAB have told that our method has strong recognized capacity for the low-quality human faces.
(1)图像预处理是人脸识别的重要前期工作,能够有效减少各种干扰因素,对后期图像识别效果的优劣影响很大。本文对人脸图像的预处理算法中,除了方向、大小等归一化步骤外,重点提出一种针对光照不均图像的预处理方法,即结合Gamma校正、高斯差分(DoG)以及对比度均衡处理为一体。该方法有效降低了光照对人脸的影响,提高了对比度,强化了人脸特征区域,有利于后续的特征提取和识别。
(2)特征提取是人脸识别的核心步骤,本文采用了多种人脸局部视觉特征的提取方法。通过分析传统算法的优缺点之后,本文在传统经典算法基础上,一方面,对LBP纹理特征进行改进,在LBP的差值计算步骤引入Dipole双极比较算子,由此提取不同距离和尺度的更大范围的局部特征,记为ILBP,即改进的LBP算法；之后,再结合Gabor特征的多方向、多尺度等优点,对人脸的Gabor特征图谱提取ILBP特征,并记为ILGBP特征。另一方面,由于实际应用中采集的人脸图像往往受光照变化、角度等因素干扰,而SIFT算法具有平移不变性、旋转不变性、尺度变化不变性等优点,本文又将SIFT特征引入人脸识别当中,用ILGBP特征和SIFT特征共同描述人脸。
(3)基于D-S证据理论和Fisherface方法进行人脸的局部多特征融合识别。鉴于D-S证据理论是基于决策级的融合,本文提出的融合识别算法是在识别过程中,首先运用Fisherface方法分别对ILGBP和SIFT特征分别进行分类识别,得到特征比对的相似度；然后,对这两个相似度,按照D-S证据理论的规则,进行信任度判别,得到最终的判别结果。由于Fisherface的特性,该方法能够有效降低特征维数,并且具有较强的鲁棒性。在MATLAB开发平台上的仿真实验结果显示,本文算法对有遮挡、低光照、侧面等不利情况有较强的识别能力。
Human face recognition technology is still going to be unfolding as a research hotspot of pattern recognition and machine visual territory, which includes the human face detective, face recognition and expression recognition etc. Because the human face recognition technology has extensive application prospect in many domains such as justice, security and military, it has been generally paid close attention to by many researchers. Therefore, the human face recognition technology has achieved great development in recent years. Also, a series of innovation algorithms had been proposed and some preliminary commercial archetype systems had been put into market. Above all the algorithms, the methods based on local visual feature model has gradually become one of the main methods because of its advantages in the recognition for the figures which have great change of illumination or other adverse factors. Based on the previously researches, we try to aim at the robustness of illumination condition and other adverse factors. Start with the local features, we do some discusses in image preprocess, feature extraction and multi-feature fusion recognition. The main tasks we had done in this paper as follows:
(1) Image preprocess is an important previous work of human face recognition. It can decrease all kinds of adverse factors efficiently and seriously influence the face recognition results. In this paper, besides the normalization of orientation, size etc, we principally proposed a preprocess algorithm aims to illumination changes. Our method includes the Gamma regulation, difference of Gaussian and contrast balance. The experiment result shows, our method can decrease the influence of illumination, raise the contrast and strengthen the effective feature areas of human face. Our preprocess methods is effective facilitate the following feature extraction and face recognition.
(2) Feature extraction is the key task of human face recognition. In this paper, we decide to extract multifarious local visual features of human face. After the analysis of the advantages and disadvantages of traditional algorithms, we do some improvement in LBP texture features firstly based on previously method. The improved LBP (ILBP) feature means that we propose a Dipole compare operator instead the simple difference operation of middle pixel and the 8 pixels border upon. The ILBP algorithm can extract the local features of bigger area in different orientations and scales. And then, we take the advantages of Gabor feature: multi-orientation and multi-scale. Based on this method, we extract the ILBP features on the figures which had already been extracted the Gabor features. We call it ILGBP feature.
In another hand, the human faces we get from the practical use condition always influenced by the changes of illumination, scales and other adverse factors. Yet, the SIFT algorithm has the advantages of translation invariance, rotational invariance and scale transform invariance. Therefore, we use both the ILGBP feature and SIFT feature to describe a human face.
(3) We use a method that based on D-S evidence theory and Fisherface algorithm to do the human face recognition based on multi-feature fusion. Because the D-S evidence theory is a method of inosculation on the level of strategic decision, in our method, we use the Fisherface algorithm to do the face recognition on ILGBP feature and SIFT feature respectively firstly. After the Fisherface feature contrast, we will get two similarity values which could be transformed to trust values use the regulations of D-S evidence theory. At last, we can successfully get the recognize results by the means of trust values. Because of the property of Fisherface algorithm, our method can decrease the feature dimension efficiently. What's more, it has stronger robustness.
The experiment results in MATLAB have told that our method has strong recognized capacity for the low-quality human faces.
引文
[1]张敏贵,潘泉,张洪才,张绍武.多生物特征识别[J].信息与控制,2002,31(6)：524-528.
[2]廖频.基于统一概率模型的人脸识别技术[D]:[学位论文].北京：中国科学院研究生院,2003.
[3]山世光.人脸识别中若干关键问题的研究[D]:[学位论文].北京：中国科学院研究生院,2004.
[4]Viola P, Jones M, Rapid object detection using a boosted cascade of simple features[C]. In:Proc. Of Conf. on Computer Vision and Pattern Recognition,2001, (1):511-518.
[5]Viola P, Jones M, Robust real time object detection[R]. Technical Report:Compaq Cambridge Research Laboratory,2001.
[6]H. Chan & W. W. Bledsoe, A man-machine facial recognition system:some preliminary results, Technical report, Panoramic Research Inc., California,1965.
[7]SIROVICH L, KIRBY M. Low-dimensional procedure for the characterization of human faces [J], Opt. Soc. Am. A,1987,4(3):519-524.
[8]PENTLAND A, MOGHADDAM B, STARNER T. View-based and Modular Eigen spaces for Face Recognition[C]. IEEE Conference on Computer Vision & Pattern Recognition, Seattle, WA, USA,1994,84-91.
[9]ZHAO L, YANG Y H. Theoretical analysis of illumination in PCA-based vision system [J]. Pattern Recognition,1999,32(4):547-564.
[10]GOTTUMUKKAL R, ASARI V K. An improved face recognition technique based on modular PCA approach [J]. Pattern Recognition Letters,2004,25:429-436.
[11]YANG M H, AHUJAN, KRIEGMAN D. Face recognition using kernel Eigen faces [C]. Proc. IEEE Conference on Image Processing. Vancouver, BC, Canada,2000,1:37-40.
[12]ZHANG JIANYANG, FRANGI D, YANG JING YU AF.Two-dimensional PCA:A new approach to appearance-based face representation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(1):131-137.
[13]CHEN SONGCAN, ZHANG DAOQIANG, ZHOU ZHIHUA. Enhanced (PC)2A for face recognition with one training image per person [J], Pattern Recognition Letters,2004, 25:1173-1181.
[14]PUJOL A, VITRIA J, LUMBRERAS F, eta. Topological principal component analysis for face encoding and recognition [J], Pattern Recognition Letters,2001,22:769-776.
[15]TAN K, CHEN S. Adaptively weighted sub-pattern PCA for face recognition [J], Neurocomputing,2005,64:505-511.
[16]BELHUMEUR P N, PHESPANHA J, KRIEGMAN D J. Eigenfaces.vs.Fisherfaces: Recognition using class specific linear projection [J], IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[17]SHAN SHIGUANG, CAO BO, GAO WEN, ZHAO DEBIN. Extended fisher face for face recognition from a single example image per person [C]. Proceedings of IEEE International Symposium on Circuits and Systems,2002,2:81-84.
[18]杨竹青,李勇,胡德文.独立成分分析综述[J].自动化学报,2002,28(5)：762-772.
[19]BARTLETT M S, SEJNOWSKI T J. Independent components of face images: representation for face recognition[C]. Proceedings of the 4th Annual Journal Symposium on Neural Computation,1997.
[20]DENIZ O, CASTRILLON M., HERNANDEZ M. Face recognition using independent component analysis and support vector machines [J]. Pattern Recognition Letters,2003, 24:2153-2157.
[21]YANG JIAN, GAO XIUMEI, ZHANG DAVID,etal. Kernel ICA:An alternative formulation and its application to face recognition [J]. Pattern Recognition,2005, 38:1784-1787.
[22]CHENG JIAN, LIN QINGSHAN, LU HANQING, etal. Ensemble learning for independent component analysis[J]. Pattern Recognition,2006,39:81-88.
[23]FORTLTNA J, CAPSON D. Improved support vector classification using.PC A and ICA feature space modification[J]. Pattern Recognition,2004,37:117-119.
[24]KIM T K,KIM H, HWANG W, etal. Independent component analysis in a local facial residue space for face recognition[J]. Pattern Recognition,2004,37(9):1873-1885.
[25]M.Lades, J.C.Vorbruggen, J.Buhmann, etal. Distortion invariant object recognition in the dynamic link architecture [J]. IEEE Transaction Computer,1993, (42):300-311
[26]T. Ojala, M. Pietikainen, T. Maenpa. Multi-resolution Gray-scale and Rotation Invariant Texture Classification with Local Binary Patterns[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[27]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,2006,12：2508-2517.
[28]孟昕.基于局部模式的人脸识别方法研究[D]：[学位论文].哈尔滨：哈尔滨工业大学,2006.
[29]KOHONEN T. Self-organization and associative memory. Berlin:Springer,1988.
[30]DEMERS D, COTTRELL G W. Nonlinear Dimensionality Reduction [A].In Advances in Neural Information Processing Systems[C]. San Matea, CA:Morgan Kaufmann,1993, 580-587.
[31]LAWRENCE S, GILES C L, TSOI A C. Face Recognition:A Convolution Neural-Network Approach [J]. IEEE Transaction on Neural Networks,1997,8(1):93-113.
[32]LIN S H, KUNG S Y, LINL J. Face recognition/detection by probabilistic decision-based neural network [J]. IEEE Transaction on Neural Networks,1997,8(1):114-132.
[33]RANGANATH S, ARUM K. Face recognition using transform features and neural networks [J]. Pattern Recognition,1997,30(10):1615-1622.
[34]LEE S Y, HAM Y K, PARK R H. Recognition of human front faces using knowledge-based feature extraction and neurofuzzy algorithm [J]. Pattern Recognition,1996, 29(11):1863-1876.
[35]IGUTTA S, WECHSLER H. Face Recognition Using Hybrid Classifiers [J].Pattern Recognition,1997,30(4):539-553.
[36]RABINER L.A tutorial on hidden Markov models and selected application in speed recognition[C].In Proceedings of the IEEE,1989,77(2):257-286.
[37]SAMARIA F. Face recognition using hidden Markov model [M]. Cambridge, University of Cambridge,1994.
[38]NEFIAN A. A hidden Markov model-based approach for face detection and recognition[M].Georgia, Georgia Institute of Technology,1999.
[39]OTHMAN H, ABOULNASR T. A separable low complexity 2D HMM with application to face recognition[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2003, 25(10),1229-1238.
[40]LADES M, VORBRUGGEN J C, J.BUHMANN V, etal. Distortion invariant object recognition in the dynamic link architecture[J]. IEEE Transaction on Computers,1993, 42(3):300-311.
[41]WISKOTT L, FELLOWS J, KRUGER N, etal. Face recognition by elastic bunch graph matching[R]. Internal Report 96-08, Ruhr University, Bochum, Germany,1996.
[42]中国科学院自动化研究所.生物识别与安全技术研究中心[EB/OL]. http://www. sinobiometrics. com.
[43]ZIOU D, TABBONE S. Edge detection techniques-An overview[J].International Journal of Pattern Recognition and Image Analysis,1998,8(4):537-559.
[44]SONKA M, HLAVAC V, BOYLE R. Image processing analysis and machine vision(2nd edition)[M]. PWS Publishing,1998.
[45]朱加涛.基于二值边缘图像的眼睛定位和人脸识别[D]:[学位论文].杭州：浙江大学,2004.
[46]LEE S Y, HAM Y K, HPARK R. Recognition of human resonate faces using knowledge-based refuter extraction and neuro-ufzyz algorithm[J]. Pattern Recognition,1996, 29(11):1863-1876.
[47]徐红侠.基于Gabor小波和局部二值模式的人脸表情识别[D]：[学位论文],南京：南京理工大学,2008.
[48]陈金如.人脸图像分析与识别方法研究[D]：[学位论文],北京：清华大学,2001.
[49]T. Ojala, M. Pietikainen, D. Harwood. A Comparative Study of Texture Measure with Classification based on Featured Algorithms [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,22(10):1090-1104,2000.
[50]T. Ojala, M.Pietikainen, T. Maenpaa. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns [J]. IEEE Transaction Pattern Analysis and Machine Intelligence,24(7):971-987,2002.
[51]Benjamin J Balas, Pawan Sinha. Region-based representations for face recognition[J]. ACM Transactions on Applied Perception,2006,3(4):354-375.
[52]Daugman J G.. Uncertainty Relation for Resolution in Space, Spatial Frequency, and Orientation Optimized by Two-Dimensional Visual Cortical Filters[J]. Optical Soc. Amer, 1985,2(7):160-169.
[53]张文超,山世光,张洪明,陈杰,陈熙霖,高文.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.
[54]David G L. Distinctive Image Feature from Scale-invariant Interest Points[J]. International Journal of Computer Vision,2004,60(2):91-110.
[55]Q.S.Sun, S.G Zeng, Y Liu, et al. A new method of feature fusion and its application in image recognition [J]. Pattern Recognition,2005,38(12):2437-2448.
[56]Gunatilaka A H, Baertlein B A. Feature-level and decision-level fusion of non-coincidently sampled sensors for land mine detection [JJ. IEEE Transactions on Pattern Analysis and Machine Vision,2001,23(6):577-589.
[57]王成波.计算机人脸识别技术的研究[D]：[学位论文].大连：大连理工大学,2005.
[2]廖频.基于统一概率模型的人脸识别技术[D]:[学位论文].北京：中国科学院研究生院,2003.
[3]山世光.人脸识别中若干关键问题的研究[D]:[学位论文].北京：中国科学院研究生院,2004.
[4]Viola P, Jones M, Rapid object detection using a boosted cascade of simple features[C]. In:Proc. Of Conf. on Computer Vision and Pattern Recognition,2001, (1):511-518.
[5]Viola P, Jones M, Robust real time object detection[R]. Technical Report:Compaq Cambridge Research Laboratory,2001.
[6]H. Chan & W. W. Bledsoe, A man-machine facial recognition system:some preliminary results, Technical report, Panoramic Research Inc., California,1965.
[7]SIROVICH L, KIRBY M. Low-dimensional procedure for the characterization of human faces [J], Opt. Soc. Am. A,1987,4(3):519-524.
[8]PENTLAND A, MOGHADDAM B, STARNER T. View-based and Modular Eigen spaces for Face Recognition[C]. IEEE Conference on Computer Vision & Pattern Recognition, Seattle, WA, USA,1994,84-91.
[9]ZHAO L, YANG Y H. Theoretical analysis of illumination in PCA-based vision system [J]. Pattern Recognition,1999,32(4):547-564.
[10]GOTTUMUKKAL R, ASARI V K. An improved face recognition technique based on modular PCA approach [J]. Pattern Recognition Letters,2004,25:429-436.
[11]YANG M H, AHUJAN, KRIEGMAN D. Face recognition using kernel Eigen faces [C]. Proc. IEEE Conference on Image Processing. Vancouver, BC, Canada,2000,1:37-40.
[12]ZHANG JIANYANG, FRANGI D, YANG JING YU AF.Two-dimensional PCA:A new approach to appearance-based face representation and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(1):131-137.
[13]CHEN SONGCAN, ZHANG DAOQIANG, ZHOU ZHIHUA. Enhanced (PC)2A for face recognition with one training image per person [J], Pattern Recognition Letters,2004, 25:1173-1181.
[14]PUJOL A, VITRIA J, LUMBRERAS F, eta. Topological principal component analysis for face encoding and recognition [J], Pattern Recognition Letters,2001,22:769-776.
[15]TAN K, CHEN S. Adaptively weighted sub-pattern PCA for face recognition [J], Neurocomputing,2005,64:505-511.
[16]BELHUMEUR P N, PHESPANHA J, KRIEGMAN D J. Eigenfaces.vs.Fisherfaces: Recognition using class specific linear projection [J], IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[17]SHAN SHIGUANG, CAO BO, GAO WEN, ZHAO DEBIN. Extended fisher face for face recognition from a single example image per person [C]. Proceedings of IEEE International Symposium on Circuits and Systems,2002,2:81-84.
[18]杨竹青,李勇,胡德文.独立成分分析综述[J].自动化学报,2002,28(5)：762-772.
[19]BARTLETT M S, SEJNOWSKI T J. Independent components of face images: representation for face recognition[C]. Proceedings of the 4th Annual Journal Symposium on Neural Computation,1997.
[20]DENIZ O, CASTRILLON M., HERNANDEZ M. Face recognition using independent component analysis and support vector machines [J]. Pattern Recognition Letters,2003, 24:2153-2157.
[21]YANG JIAN, GAO XIUMEI, ZHANG DAVID,etal. Kernel ICA:An alternative formulation and its application to face recognition [J]. Pattern Recognition,2005, 38:1784-1787.
[22]CHENG JIAN, LIN QINGSHAN, LU HANQING, etal. Ensemble learning for independent component analysis[J]. Pattern Recognition,2006,39:81-88.
[23]FORTLTNA J, CAPSON D. Improved support vector classification using.PC A and ICA feature space modification[J]. Pattern Recognition,2004,37:117-119.
[24]KIM T K,KIM H, HWANG W, etal. Independent component analysis in a local facial residue space for face recognition[J]. Pattern Recognition,2004,37(9):1873-1885.
[25]M.Lades, J.C.Vorbruggen, J.Buhmann, etal. Distortion invariant object recognition in the dynamic link architecture [J]. IEEE Transaction Computer,1993, (42):300-311
[26]T. Ojala, M. Pietikainen, T. Maenpa. Multi-resolution Gray-scale and Rotation Invariant Texture Classification with Local Binary Patterns[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[27]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,2006,12：2508-2517.
[28]孟昕.基于局部模式的人脸识别方法研究[D]：[学位论文].哈尔滨：哈尔滨工业大学,2006.
[29]KOHONEN T. Self-organization and associative memory. Berlin:Springer,1988.
[30]DEMERS D, COTTRELL G W. Nonlinear Dimensionality Reduction [A].In Advances in Neural Information Processing Systems[C]. San Matea, CA:Morgan Kaufmann,1993, 580-587.
[31]LAWRENCE S, GILES C L, TSOI A C. Face Recognition:A Convolution Neural-Network Approach [J]. IEEE Transaction on Neural Networks,1997,8(1):93-113.
[32]LIN S H, KUNG S Y, LINL J. Face recognition/detection by probabilistic decision-based neural network [J]. IEEE Transaction on Neural Networks,1997,8(1):114-132.
[33]RANGANATH S, ARUM K. Face recognition using transform features and neural networks [J]. Pattern Recognition,1997,30(10):1615-1622.
[34]LEE S Y, HAM Y K, PARK R H. Recognition of human front faces using knowledge-based feature extraction and neurofuzzy algorithm [J]. Pattern Recognition,1996, 29(11):1863-1876.
[35]IGUTTA S, WECHSLER H. Face Recognition Using Hybrid Classifiers [J].Pattern Recognition,1997,30(4):539-553.
[36]RABINER L.A tutorial on hidden Markov models and selected application in speed recognition[C].In Proceedings of the IEEE,1989,77(2):257-286.
[37]SAMARIA F. Face recognition using hidden Markov model [M]. Cambridge, University of Cambridge,1994.
[38]NEFIAN A. A hidden Markov model-based approach for face detection and recognition[M].Georgia, Georgia Institute of Technology,1999.
[39]OTHMAN H, ABOULNASR T. A separable low complexity 2D HMM with application to face recognition[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2003, 25(10),1229-1238.
[40]LADES M, VORBRUGGEN J C, J.BUHMANN V, etal. Distortion invariant object recognition in the dynamic link architecture[J]. IEEE Transaction on Computers,1993, 42(3):300-311.
[41]WISKOTT L, FELLOWS J, KRUGER N, etal. Face recognition by elastic bunch graph matching[R]. Internal Report 96-08, Ruhr University, Bochum, Germany,1996.
[42]中国科学院自动化研究所.生物识别与安全技术研究中心[EB/OL]. http://www. sinobiometrics. com.
[43]ZIOU D, TABBONE S. Edge detection techniques-An overview[J].International Journal of Pattern Recognition and Image Analysis,1998,8(4):537-559.
[44]SONKA M, HLAVAC V, BOYLE R. Image processing analysis and machine vision(2nd edition)[M]. PWS Publishing,1998.
[45]朱加涛.基于二值边缘图像的眼睛定位和人脸识别[D]:[学位论文].杭州：浙江大学,2004.
[46]LEE S Y, HAM Y K, HPARK R. Recognition of human resonate faces using knowledge-based refuter extraction and neuro-ufzyz algorithm[J]. Pattern Recognition,1996, 29(11):1863-1876.
[47]徐红侠.基于Gabor小波和局部二值模式的人脸表情识别[D]：[学位论文],南京：南京理工大学,2008.
[48]陈金如.人脸图像分析与识别方法研究[D]：[学位论文],北京：清华大学,2001.
[49]T. Ojala, M. Pietikainen, D. Harwood. A Comparative Study of Texture Measure with Classification based on Featured Algorithms [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,22(10):1090-1104,2000.
[50]T. Ojala, M.Pietikainen, T. Maenpaa. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns [J]. IEEE Transaction Pattern Analysis and Machine Intelligence,24(7):971-987,2002.
[51]Benjamin J Balas, Pawan Sinha. Region-based representations for face recognition[J]. ACM Transactions on Applied Perception,2006,3(4):354-375.
[52]Daugman J G.. Uncertainty Relation for Resolution in Space, Spatial Frequency, and Orientation Optimized by Two-Dimensional Visual Cortical Filters[J]. Optical Soc. Amer, 1985,2(7):160-169.
[53]张文超,山世光,张洪明,陈杰,陈熙霖,高文.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.
[54]David G L. Distinctive Image Feature from Scale-invariant Interest Points[J]. International Journal of Computer Vision,2004,60(2):91-110.
[55]Q.S.Sun, S.G Zeng, Y Liu, et al. A new method of feature fusion and its application in image recognition [J]. Pattern Recognition,2005,38(12):2437-2448.
[56]Gunatilaka A H, Baertlein B A. Feature-level and decision-level fusion of non-coincidently sampled sensors for land mine detection [JJ. IEEE Transactions on Pattern Analysis and Machine Vision,2001,23(6):577-589.
[57]王成波.计算机人脸识别技术的研究[D]：[学位论文].大连：大连理工大学,2005.