人脸表情识别算法研究
|
摘要
人脸表情识别是指利用计算机分析特定人的脸部表情变化,进而确定其内心的情绪,实现人机之间更自然更智能化的交互。在很多领域都有其潜在的应用价值,包括心理学研究、图像理合成脸部动画、视频检索、机器人技术、虚拟现实技术以及基于脸部表情的新型人机交互环境的研究和开发等。
完整的表情识别系统一般包括人脸表情图像捕获、预处理、人脸检测与定位、人脸分割与归一化、人脸表情特征提取、人脸表情识别。本文着重研究了人脸表情特征提取、特征选择及表情分类等关键问题,并提出了一些改进的方法,同时进行了仿真实验。
(1)表情图像的预处理方法是整个识别系统的最初步骤。本文提出了基于复杂度和模板匹配的方法对眼睛区域进行检测并定位,实验证明,该算法简单,计算量小,且无须事先确定人脸位置,即可快速准确地确定眼睛位置,从而为图像的剪切、缩放及灰度归一化等其他预处理奠定良好基础。
(2)重点研究了基于二维Gabor小波的表情特征提取方法。由于Gabor小波变换系数向量具有减弱图像光照及位置的敏感性等优点,所以本文采用Gabor小波提取表情特征,并在五个尺度、六个方向上构造Gabor小波,对每幅图像用这30个Gabor函数进行滤波,得到的系数作为表情特征。实验证明,本文方法相对于传统的PCA算法或2D-PCA算法其识别率更加有效。针对Gabor系数的高维性,本文提出了采用二次降维方法,即第一次降维采用不规则采样法,第二次降维采用2D-PCA方法,通过子空间变换,提取最有代表性的特征,有效地消除了冗余。实验证明,本文方法明显降低了特征向量的维数,从而提高了识别速度。
(3)分别采用最近邻分类器、欧式距离分类器、余弦距离分类器对生气、厌恶、恐惧、高兴、中性、悲伤和惊讶七种表情进行识别,并利用模糊积分对子分类器的识别结果进行融合。在信息融合中,改进了模糊密度函数,将各子分类器的不同表情的识别被赋以不同的密度,充分考虑了一个分类器对不同表情具有不同的识别率。实验结果表明,与基于平均识别率为模糊密度的识别方法相比,本文采用的基于混淆矩阵为模糊密度的识别率更高,证明这种改进是有效的。
Facial expression recognition is to analyze and detect the special expression state from given expression images or video frames and determine the subject's specific inborn emotion so as to achieve smarter and more natural inter-action between human beings and computers. Facial expression recognition has potential application values in many fields, including psychics study, image understanding, synthetically face cartoon, video retrieval, robot technology, virtual reality, and research and develop of new human-computer-interface environment based on facial expression.
The system of facial expression recognition generally consists of face expression image capture, preprocessing, face detection and location, face segmentation and normalization, facial expression feature extraction, facial expression recognition. The task in this paper focuses on the key issues of facial expression recognition, such as feature extraction, feature selection and facial expression classification, and so on. The performances of proposed methods are illustrated by simulation experimental results.
(1) Preprocessing of expression images is the first step in the whole recognition system. In this paper, we proposed a new algorithm based on the complexity and template match. It can detect directly and locate the human eyes in human face images without determining the human face position in advance. The experimental results show that this algorithm is simple and convenient. It establishes foundation for clipping and scaling, photometric preprocessing and histogram equalization.
(2) The methods of the feature extraction based on Two-dimensional Gabor transform are discussed in details. Gabor wavelets in 5 scales, 6 orientations for extracting features are constructed because of Gabor coefficients’lower sensitivity to variations of lighting and position. Each image is filtered by 30 Gabor functions. After Gabor filtering, the amplitude values are used as facial expression features. The experimental results show that this method is better than PCA or 2D-PCA. On the other hand, Gabor coefficients have large dimensions, we propose two times sampling method to reduce dimension. The first one is irregular sampling which significantly reduces the dimension of feature vector and improves the recognition rate; the second one is using 2D-PCA method. Through the sub-space mapping, the most representative features are extracted to reduce dimension again. The experimental show that this method can reduce dimension obviously.
(3) Nearest neighbor classifier, Euclidean distance classifier, Cosine distance classifier are used to classify seven expressions including angry, disgust, fear, happy, neutral, and sad and surprise. Then, fuzzy integral is applied to fuse outputs from results of three classifiers to get the final recognition result. The experimental results indicate that this improve method has higher recognition rate than method of based on average recognition rate for fuzzy density.
完整的表情识别系统一般包括人脸表情图像捕获、预处理、人脸检测与定位、人脸分割与归一化、人脸表情特征提取、人脸表情识别。本文着重研究了人脸表情特征提取、特征选择及表情分类等关键问题,并提出了一些改进的方法,同时进行了仿真实验。
(1)表情图像的预处理方法是整个识别系统的最初步骤。本文提出了基于复杂度和模板匹配的方法对眼睛区域进行检测并定位,实验证明,该算法简单,计算量小,且无须事先确定人脸位置,即可快速准确地确定眼睛位置,从而为图像的剪切、缩放及灰度归一化等其他预处理奠定良好基础。
(2)重点研究了基于二维Gabor小波的表情特征提取方法。由于Gabor小波变换系数向量具有减弱图像光照及位置的敏感性等优点,所以本文采用Gabor小波提取表情特征,并在五个尺度、六个方向上构造Gabor小波,对每幅图像用这30个Gabor函数进行滤波,得到的系数作为表情特征。实验证明,本文方法相对于传统的PCA算法或2D-PCA算法其识别率更加有效。针对Gabor系数的高维性,本文提出了采用二次降维方法,即第一次降维采用不规则采样法,第二次降维采用2D-PCA方法,通过子空间变换,提取最有代表性的特征,有效地消除了冗余。实验证明,本文方法明显降低了特征向量的维数,从而提高了识别速度。
(3)分别采用最近邻分类器、欧式距离分类器、余弦距离分类器对生气、厌恶、恐惧、高兴、中性、悲伤和惊讶七种表情进行识别,并利用模糊积分对子分类器的识别结果进行融合。在信息融合中,改进了模糊密度函数,将各子分类器的不同表情的识别被赋以不同的密度,充分考虑了一个分类器对不同表情具有不同的识别率。实验结果表明,与基于平均识别率为模糊密度的识别方法相比,本文采用的基于混淆矩阵为模糊密度的识别率更高,证明这种改进是有效的。
Facial expression recognition is to analyze and detect the special expression state from given expression images or video frames and determine the subject's specific inborn emotion so as to achieve smarter and more natural inter-action between human beings and computers. Facial expression recognition has potential application values in many fields, including psychics study, image understanding, synthetically face cartoon, video retrieval, robot technology, virtual reality, and research and develop of new human-computer-interface environment based on facial expression.
The system of facial expression recognition generally consists of face expression image capture, preprocessing, face detection and location, face segmentation and normalization, facial expression feature extraction, facial expression recognition. The task in this paper focuses on the key issues of facial expression recognition, such as feature extraction, feature selection and facial expression classification, and so on. The performances of proposed methods are illustrated by simulation experimental results.
(1) Preprocessing of expression images is the first step in the whole recognition system. In this paper, we proposed a new algorithm based on the complexity and template match. It can detect directly and locate the human eyes in human face images without determining the human face position in advance. The experimental results show that this algorithm is simple and convenient. It establishes foundation for clipping and scaling, photometric preprocessing and histogram equalization.
(2) The methods of the feature extraction based on Two-dimensional Gabor transform are discussed in details. Gabor wavelets in 5 scales, 6 orientations for extracting features are constructed because of Gabor coefficients’lower sensitivity to variations of lighting and position. Each image is filtered by 30 Gabor functions. After Gabor filtering, the amplitude values are used as facial expression features. The experimental results show that this method is better than PCA or 2D-PCA. On the other hand, Gabor coefficients have large dimensions, we propose two times sampling method to reduce dimension. The first one is irregular sampling which significantly reduces the dimension of feature vector and improves the recognition rate; the second one is using 2D-PCA method. Through the sub-space mapping, the most representative features are extracted to reduce dimension again. The experimental show that this method can reduce dimension obviously.
(3) Nearest neighbor classifier, Euclidean distance classifier, Cosine distance classifier are used to classify seven expressions including angry, disgust, fear, happy, neutral, and sad and surprise. Then, fuzzy integral is applied to fuse outputs from results of three classifiers to get the final recognition result. The experimental results indicate that this improve method has higher recognition rate than method of based on average recognition rate for fuzzy density.
引文
[1] Mehrabian A. Communication without words [J]. Psychology Today, 1968, 2(4):53-56.
[2]王志良.人工心理学--关于更接近人脑工作模式的科学[J].北京科技大学学报,2000, 22(5):478-481.
[3] M.Pardas, A.Bonafonte. Facial animation parameters extraction and expression recognition using Hidden Markov Models. Signal Processing: Image Communication, 2002, 17(9): 675-688.
[4] Zhiliang wang, Lunxie. Artificial Psychology-an Attainable Scientific Research on the Human Brain[C]. IPMM’99(KEYNOTE PAPER), honolulu, USA, July, 1999:10-15.
[5] Ekman P, Friesen W V.Facial Action Coding System:A Technique for the Measurement of Facial Movement[M].Palo A lto:Consulting Psychologists Press,1978.
[6] K.Mase. IEICE Trans. Special Issue on Computer Vision and its Application, 1991, E74 (10)34-38.
[7] Turk M, Pentland A. Face recognition using Eigenfaces[C].In: Proc IEEEConf On computer Vision and Pattern Pecognition, 1991:586-591.
[8] Rajkiran Gottumukkal, Vijayan K.Asari. An improved face recognition technique based on modular PCA approaeh[J].Pattern Recognition LetterS, 2004, 25(4):429-436.
[9] Bartlett MS, Lades HM, Sejnowski TJ.Independent component representations for face recognition[j].In: Proceedings of SPIE1998:528-539.
[10]洪子泉,杨静宇.用于图像识别的图像代数特征抽取.自动化学报,1992,18(2):233-237.
[11]洪子泉,杨静宇.基于奇异特征值和统计模型的人像识别算法.计算机研究与发展,1994,31(3):60-65.
[12]唐京海,张有为.基于FLD特征提取的SVM人脸表情识别方法[J].计算机工程与应用,2006(11):10-12.
[13]金辉,高文.人脸面部混合表情识别系统[J].计算机学报,2000,23(6):602-608.
[14] Ekamn P, Friesen WV. Facial action coding system (FACS):manualM].Consulting Psychologists Press,1978.
[15]王志良,陈锋军,薛为民.人脸表情识别方法综述[J].计算机应用与软件,2003,20(12):63-66.
[16] Suwa M, Sugie N, Fujimora K. Apreliminary note on pattern recognition of human emotional expression[C]. In:Proe 4th Int Joint Conference on Pattern Recognition, 1978, 408-410.
[17]高文,陈熙霖.计算机视觉.北京:清华大学出版社,1998:203-206.
[18] C. Fermuller, D. Shulman, Y. Aloimonos. The Statics of Optical Flow. Computer Vision andImage Understanding, 2001,82: 1-32.
[19] Y. J. Wang, C. S. Chua, Y. K. Ho. Facial feature detection and face recognition from 2D and 3D images. Patter Recognition Letters, 2002, 23(10): 1191-1202.
[20]邹采荣,包永强,何良华,赵力.人脸而部表情识别的研究进展,电路与系统学报,第10卷第1期,2005年2月.
[21]梁路宏,艾海舟,徐光枯,张钱.人脸检测研究综述.计算机学报,2002, 25(5): 449-458.
[22] S. Dubussion, F. Devoine, M. Masson. A solution for facial expression representation and recognition. Signal Processing: Image Communication, 2002, 17(9): 657-673.
[23]程剑,应自炉.基于二维主分量分析的面部表情识别[J].计算机工程与应用,2006(5):32-33.
[24]陈武凡土编.小波分析及其在图象处理中的应用[M].北京:科学出版社,2002.
[25]杨福生.小波变换的工程分析与应用.科学出版社,1999.
[26] http://www.ri.cmu.edu/projects/project_ 421.html, 2004.
[27] L. J. Yin, A. Basu. Color-based mouth shape tracking for synthesizing realistic facial expressions. Proceedings of the IEEE International Conference on Image, v1, 2002: 161-164.
[28]梁路宏,艾海舟,徐光枯,张钱.人脸检测研究综述.计算机学报,2002, 25(5): 449-458.
[29] Y. J. Wang, C. S. Chua, Y. K. Ho. Facial feature detection and face recognition from 2D and 3D images. Patter Recognition Letters, 2002, 23(10): 1191-1202.
[30] J. Zhang, Y. Yan, M. Lades. Face recognition: eigenface, elastic matching, and neural nets. Proceedings of the IEEE, 1998, 85(9): 1422-1435.
[31] K. Mase. Recognition of facial expression from optical flow. IEICE Trans, 1991, E 74(10):3474-3483.
[32] X. W. Chen, T. Huang. Facial expression recognition: A clustering-based approach. Pattern Recognition Letters, 2003, 24(9-10): 1295-1302.
[33] Tian Y, Kanade T, Cohn J. Evaluation of Gabor wavelet-based facial action un it recognition in image sequences of increasing complexity[A].In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition[C].Washingtonn, DC, USA, 2002:26-30.
[34] Y. Yacoob, L. Davis. Recognizing human facial expressions from long image sequences using optical flow[J]. IEEE Trans. Pattern Anal. Machine Intel l.1994, 16(6): 636-642.
[35]孙即祥等.模式识别中的特征提取与计算机视觉中不变量[M].国防工业出版社,2001.
[36]刘小军.人脸识别技术研究[D].中国科学院电子学研究所,2002.
[37]崔连延,徐林,顾树生.基于复杂度和最佳阈值的人眼定位方法[J].控制工程,2008, 15(1): 12-14.
[38]孙艳秋.一种简单快速的人眼定位方法[J].赤峰学院学报,2008, 24(3): 116-119.
[39]陶亮,庄镇泉.基于小波分解和支持向量机的准正面人脸识别方法[J].电路与系统学报,2003, 8(6):107-112.
[40]李士进,杨静宇,陆静峰.基于奇异值特征和隐马尔可夫模型的人脸检测[J].中国图象图形学报,2001, 6(7): 681-687.
[41]李贤帅,李赣华,周东翔等.基于人眼定位的快速人脸检测及归一化算法[J].计算机工程与科学,2006, 8(12): 63-65.
[42]艾海舟.数字图像处理[EB/OL]. http://media.cs.tsinghua.edu.cn/~ahzldigitalimageprocess/CourselmageProcess.html, 2004.
[43] D.Gabor. Theory of communication. J.inst Electr Eng, vo 1. 93, no.111, pp.429-457, Nov. 1946.
[44]叶敬福,詹永照.基于Gabor小波变换的人脸表情特征提取[J].计算机工程.2005, 31(15): 172-174.
[45] S.Marcelja. Mathematical description of the response of simple cortical cells. J. Opt. Soc. Am. A 70, 1980, 1297-1300.
[46] J. G. Daugman. Uncertainty Relation for resolution in space, Spatial Frequency, and Orientation Optimized by Two-Dimensional Visual Cortical Filters. J. Opt. Soc. Amer. A, Vol.2, 1985, 1160-1169.
[47]张贤达,保铮.非平稳信号分析与处理[M].国防工业出版社,1998.
[48] Gabor D. Theory of Communication[J]. J. LEE, 1946, 93: 429-457.
[49]崔锦泰,施咸亮.分段光滑函数的带权有理逼近[J].浙江大学学报(理学版), 1986,13(1):126-128.
[50] Qian S, Chen D. Discrete Gabor expansions[J]. IEEE Trans, Signal Processing, 1993, 41: 2429-2438.
[51] Mallat S. A Theory of Multi resolution Signal Decomposition: The Wavelet Representation[J]. IEEE Trans. On Pattern Analysis and Machine Intelligence. 1989(11):674-693.
[52] aubechies I. Orthonormal Bases of Compactly Supported Wavelets[J]. Comm. On Pure& Applied Mathematics, 1989, 41(7): 909-996.
[53] Marcelja S. Mathematical description of the responses of simple cortical cells[J]. Journal of Optical Society of America, 1980, 70 (I l):1297-1300.
[54] Daugman .1 G. Two-Dimensional Spectral Analysis of Cortical Receptive Field Profile. Vision Research, 1980, 20:847- 856.
[55] Pollen D A, Ronner S F. Visual cortical neurons as localized spatial frequency filters[J]. IEEE Trans. on Systems, Man, and Cybernetics, 1983, 13(5):907-916.
[56] Daugman J G. Uncertainty Relation for Resolution in Space, Spatial Frequency, and OrientationOptimized by Two-Dimensional Visual Cortical Filters. Journal of the Optical Society of America A, 1985, (7):1160-1169.
[57] Jones J P, Palmer L A. An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophysiology, 1987, 58(6):1233-1258.
[58] M Lyons.J Budynek, S Akamastu. Automatic classification of single facial images [J]. IEEE Trans on Pattern Analysis and Machine Intelligence .1999 .21(12):1357-1362.
[59]朱健翔,苏光大,李迎春.结合Gabor特征与Adaboost的人脸表情识别[J].光电子激光,2006, 17(8): 993-998.
[60] LiuD H, Lam KM, Shen LS. Optinal sampling of Gabor features for face recognition [J].Pattern Recognition Letters, 2004, 25 (2)267-276.
[61] Z.Zhang, M.Lyons, M.Schuster, and S.Akamatsu. Comparison between geometry-based and Gabor-wavelets-based facial expression recognition using multi-layer perception [J]. In Proc. 3rd IEEE Int. Conf. Automatic Face and Gesture Recognition,1998:454-459.
[62] Jian Yang. Avid zhang. 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.
[63]程剑,应自炉.基于二维主分量分析的面部表情识别[J].计算机工程与应用,2006,5(2)33-35.
[64]刘永祥,黎湘,庄钊文.基于Choquet模糊积分的决策层信息融合目标识别[J].电子信息学报,2003, 25(5): 695-699.
[65]雍少为,郁文贤,郭桂荣.信息融合的熵理论[J].系统工程与电子技术,1995, 10: 1-6.
[66] Facial Expression Database http://vasc.ri.cmu.edu/idb/html/face/facial_ expression.
[67] Shigeru Akamatsu, Miyuki Kamachi, Jiro Gyoba. Coding Facial Expressions with Gabor Wavelets Michael J. Lyons. Proceedings of Third IEEE International Conference on Automatic Face and Gesture Recognition, Nara, Japan, 1998:200-205.
[68]姜璐,章品正,舒华忠.矩在面部表情识别中的应用[J].东南大学学报,2004,34(4): 557-560.
[69] BraalhenB, BartlettM S, Littlavort Get. An approach to automatic recognition of spontaneous facial actions[A].In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition[C].Washington, DC, USA, 2002: 231-235.
[70] Lien J. Automatic Recognition of Facial Expression Using Hidden Madcov Models and Estimation of Expression Intensity [D]. Pittsburgh: The Robotics Institute, QVIU, 1998.
[71] Cohen I, SebeN, GargA, et al. Facial expression recognition from video sequences Temporal and static modeling [J].Computer Vision and Image Understanding, 2003, 91(1-2):160-187.
[72]张学工.关于统计学习理论与支持向量机[J].自动化学报2000(1):32- 42.
[73] M Sugeno. Fuzzy measures and fuzzy integrals: A Survey. Fuzzy Automata and Decision Processes Amsterdam: North Holland. 1977:89-92.
[74] Zhenyuan Wang, George J.Klir. Fuzzy Measure Theory. Plenum Press, 1992:46-47, 62-63.
[75]哈明虎,吴从炘.模糊测度与模糊积分理论[M].北京:科学出版社,1998.
[76]边肇祺,张学工.模式识别(第二版)[M].北京:清华大学出版社,2000.
[2]王志良.人工心理学--关于更接近人脑工作模式的科学[J].北京科技大学学报,2000, 22(5):478-481.
[3] M.Pardas, A.Bonafonte. Facial animation parameters extraction and expression recognition using Hidden Markov Models. Signal Processing: Image Communication, 2002, 17(9): 675-688.
[4] Zhiliang wang, Lunxie. Artificial Psychology-an Attainable Scientific Research on the Human Brain[C]. IPMM’99(KEYNOTE PAPER), honolulu, USA, July, 1999:10-15.
[5] Ekman P, Friesen W V.Facial Action Coding System:A Technique for the Measurement of Facial Movement[M].Palo A lto:Consulting Psychologists Press,1978.
[6] K.Mase. IEICE Trans. Special Issue on Computer Vision and its Application, 1991, E74 (10)34-38.
[7] Turk M, Pentland A. Face recognition using Eigenfaces[C].In: Proc IEEEConf On computer Vision and Pattern Pecognition, 1991:586-591.
[8] Rajkiran Gottumukkal, Vijayan K.Asari. An improved face recognition technique based on modular PCA approaeh[J].Pattern Recognition LetterS, 2004, 25(4):429-436.
[9] Bartlett MS, Lades HM, Sejnowski TJ.Independent component representations for face recognition[j].In: Proceedings of SPIE1998:528-539.
[10]洪子泉,杨静宇.用于图像识别的图像代数特征抽取.自动化学报,1992,18(2):233-237.
[11]洪子泉,杨静宇.基于奇异特征值和统计模型的人像识别算法.计算机研究与发展,1994,31(3):60-65.
[12]唐京海,张有为.基于FLD特征提取的SVM人脸表情识别方法[J].计算机工程与应用,2006(11):10-12.
[13]金辉,高文.人脸面部混合表情识别系统[J].计算机学报,2000,23(6):602-608.
[14] Ekamn P, Friesen WV. Facial action coding system (FACS):manualM].Consulting Psychologists Press,1978.
[15]王志良,陈锋军,薛为民.人脸表情识别方法综述[J].计算机应用与软件,2003,20(12):63-66.
[16] Suwa M, Sugie N, Fujimora K. Apreliminary note on pattern recognition of human emotional expression[C]. In:Proe 4th Int Joint Conference on Pattern Recognition, 1978, 408-410.
[17]高文,陈熙霖.计算机视觉.北京:清华大学出版社,1998:203-206.
[18] C. Fermuller, D. Shulman, Y. Aloimonos. The Statics of Optical Flow. Computer Vision andImage Understanding, 2001,82: 1-32.
[19] Y. J. Wang, C. S. Chua, Y. K. Ho. Facial feature detection and face recognition from 2D and 3D images. Patter Recognition Letters, 2002, 23(10): 1191-1202.
[20]邹采荣,包永强,何良华,赵力.人脸而部表情识别的研究进展,电路与系统学报,第10卷第1期,2005年2月.
[21]梁路宏,艾海舟,徐光枯,张钱.人脸检测研究综述.计算机学报,2002, 25(5): 449-458.
[22] S. Dubussion, F. Devoine, M. Masson. A solution for facial expression representation and recognition. Signal Processing: Image Communication, 2002, 17(9): 657-673.
[23]程剑,应自炉.基于二维主分量分析的面部表情识别[J].计算机工程与应用,2006(5):32-33.
[24]陈武凡土编.小波分析及其在图象处理中的应用[M].北京:科学出版社,2002.
[25]杨福生.小波变换的工程分析与应用.科学出版社,1999.
[26] http://www.ri.cmu.edu/projects/project_ 421.html, 2004.
[27] L. J. Yin, A. Basu. Color-based mouth shape tracking for synthesizing realistic facial expressions. Proceedings of the IEEE International Conference on Image, v1, 2002: 161-164.
[28]梁路宏,艾海舟,徐光枯,张钱.人脸检测研究综述.计算机学报,2002, 25(5): 449-458.
[29] Y. J. Wang, C. S. Chua, Y. K. Ho. Facial feature detection and face recognition from 2D and 3D images. Patter Recognition Letters, 2002, 23(10): 1191-1202.
[30] J. Zhang, Y. Yan, M. Lades. Face recognition: eigenface, elastic matching, and neural nets. Proceedings of the IEEE, 1998, 85(9): 1422-1435.
[31] K. Mase. Recognition of facial expression from optical flow. IEICE Trans, 1991, E 74(10):3474-3483.
[32] X. W. Chen, T. Huang. Facial expression recognition: A clustering-based approach. Pattern Recognition Letters, 2003, 24(9-10): 1295-1302.
[33] Tian Y, Kanade T, Cohn J. Evaluation of Gabor wavelet-based facial action un it recognition in image sequences of increasing complexity[A].In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition[C].Washingtonn, DC, USA, 2002:26-30.
[34] Y. Yacoob, L. Davis. Recognizing human facial expressions from long image sequences using optical flow[J]. IEEE Trans. Pattern Anal. Machine Intel l.1994, 16(6): 636-642.
[35]孙即祥等.模式识别中的特征提取与计算机视觉中不变量[M].国防工业出版社,2001.
[36]刘小军.人脸识别技术研究[D].中国科学院电子学研究所,2002.
[37]崔连延,徐林,顾树生.基于复杂度和最佳阈值的人眼定位方法[J].控制工程,2008, 15(1): 12-14.
[38]孙艳秋.一种简单快速的人眼定位方法[J].赤峰学院学报,2008, 24(3): 116-119.
[39]陶亮,庄镇泉.基于小波分解和支持向量机的准正面人脸识别方法[J].电路与系统学报,2003, 8(6):107-112.
[40]李士进,杨静宇,陆静峰.基于奇异值特征和隐马尔可夫模型的人脸检测[J].中国图象图形学报,2001, 6(7): 681-687.
[41]李贤帅,李赣华,周东翔等.基于人眼定位的快速人脸检测及归一化算法[J].计算机工程与科学,2006, 8(12): 63-65.
[42]艾海舟.数字图像处理[EB/OL]. http://media.cs.tsinghua.edu.cn/~ahzldigitalimageprocess/CourselmageProcess.html, 2004.
[43] D.Gabor. Theory of communication. J.inst Electr Eng, vo 1. 93, no.111, pp.429-457, Nov. 1946.
[44]叶敬福,詹永照.基于Gabor小波变换的人脸表情特征提取[J].计算机工程.2005, 31(15): 172-174.
[45] S.Marcelja. Mathematical description of the response of simple cortical cells. J. Opt. Soc. Am. A 70, 1980, 1297-1300.
[46] J. G. Daugman. Uncertainty Relation for resolution in space, Spatial Frequency, and Orientation Optimized by Two-Dimensional Visual Cortical Filters. J. Opt. Soc. Amer. A, Vol.2, 1985, 1160-1169.
[47]张贤达,保铮.非平稳信号分析与处理[M].国防工业出版社,1998.
[48] Gabor D. Theory of Communication[J]. J. LEE, 1946, 93: 429-457.
[49]崔锦泰,施咸亮.分段光滑函数的带权有理逼近[J].浙江大学学报(理学版), 1986,13(1):126-128.
[50] Qian S, Chen D. Discrete Gabor expansions[J]. IEEE Trans, Signal Processing, 1993, 41: 2429-2438.
[51] Mallat S. A Theory of Multi resolution Signal Decomposition: The Wavelet Representation[J]. IEEE Trans. On Pattern Analysis and Machine Intelligence. 1989(11):674-693.
[52] aubechies I. Orthonormal Bases of Compactly Supported Wavelets[J]. Comm. On Pure& Applied Mathematics, 1989, 41(7): 909-996.
[53] Marcelja S. Mathematical description of the responses of simple cortical cells[J]. Journal of Optical Society of America, 1980, 70 (I l):1297-1300.
[54] Daugman .1 G. Two-Dimensional Spectral Analysis of Cortical Receptive Field Profile. Vision Research, 1980, 20:847- 856.
[55] Pollen D A, Ronner S F. Visual cortical neurons as localized spatial frequency filters[J]. IEEE Trans. on Systems, Man, and Cybernetics, 1983, 13(5):907-916.
[56] Daugman J G. Uncertainty Relation for Resolution in Space, Spatial Frequency, and OrientationOptimized by Two-Dimensional Visual Cortical Filters. Journal of the Optical Society of America A, 1985, (7):1160-1169.
[57] Jones J P, Palmer L A. An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophysiology, 1987, 58(6):1233-1258.
[58] M Lyons.J Budynek, S Akamastu. Automatic classification of single facial images [J]. IEEE Trans on Pattern Analysis and Machine Intelligence .1999 .21(12):1357-1362.
[59]朱健翔,苏光大,李迎春.结合Gabor特征与Adaboost的人脸表情识别[J].光电子激光,2006, 17(8): 993-998.
[60] LiuD H, Lam KM, Shen LS. Optinal sampling of Gabor features for face recognition [J].Pattern Recognition Letters, 2004, 25 (2)267-276.
[61] Z.Zhang, M.Lyons, M.Schuster, and S.Akamatsu. Comparison between geometry-based and Gabor-wavelets-based facial expression recognition using multi-layer perception [J]. In Proc. 3rd IEEE Int. Conf. Automatic Face and Gesture Recognition,1998:454-459.
[62] Jian Yang. Avid zhang. 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.
[63]程剑,应自炉.基于二维主分量分析的面部表情识别[J].计算机工程与应用,2006,5(2)33-35.
[64]刘永祥,黎湘,庄钊文.基于Choquet模糊积分的决策层信息融合目标识别[J].电子信息学报,2003, 25(5): 695-699.
[65]雍少为,郁文贤,郭桂荣.信息融合的熵理论[J].系统工程与电子技术,1995, 10: 1-6.
[66] Facial Expression Database http://vasc.ri.cmu.edu/idb/html/face/facial_ expression.
[67] Shigeru Akamatsu, Miyuki Kamachi, Jiro Gyoba. Coding Facial Expressions with Gabor Wavelets Michael J. Lyons. Proceedings of Third IEEE International Conference on Automatic Face and Gesture Recognition, Nara, Japan, 1998:200-205.
[68]姜璐,章品正,舒华忠.矩在面部表情识别中的应用[J].东南大学学报,2004,34(4): 557-560.
[69] BraalhenB, BartlettM S, Littlavort Get. An approach to automatic recognition of spontaneous facial actions[A].In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition[C].Washington, DC, USA, 2002: 231-235.
[70] Lien J. Automatic Recognition of Facial Expression Using Hidden Madcov Models and Estimation of Expression Intensity [D]. Pittsburgh: The Robotics Institute, QVIU, 1998.
[71] Cohen I, SebeN, GargA, et al. Facial expression recognition from video sequences Temporal and static modeling [J].Computer Vision and Image Understanding, 2003, 91(1-2):160-187.
[72]张学工.关于统计学习理论与支持向量机[J].自动化学报2000(1):32- 42.
[73] M Sugeno. Fuzzy measures and fuzzy integrals: A Survey. Fuzzy Automata and Decision Processes Amsterdam: North Holland. 1977:89-92.
[74] Zhenyuan Wang, George J.Klir. Fuzzy Measure Theory. Plenum Press, 1992:46-47, 62-63.
[75]哈明虎,吴从炘.模糊测度与模糊积分理论[M].北京:科学出版社,1998.
[76]边肇祺,张学工.模式识别(第二版)[M].北京:清华大学出版社,2000.