基于多特征集成分类器的人脸表情识别研究
|
摘要
人脸表情识别是人工智能与人机交互领域中的一个重要课题,目的是实现计算机自动识别人的表情,进而分析人的情感与心理。这将进一步增强人机交互的友好性与智能性,因此有着很高的研究价值和良好的应用前景。
人脸表情识别系统一般包括人脸检测、特征提取、表情分类等环节。本文主要研究了特征提取和表情分类过程中的一些关键问题,分析了现有算法中的不足,提出改进算法,并进行了仿真实验。主要的工作如下:
第一,改进Gabor特征提取算法。提出一种Gabor特征选择方法,利用分布估计算法对Gabor滤波器组的尺度和方向进行优化选择,选择出最佳的Gabor核的尺度和方向,并在此基础上提取特征。在日本的JAFFE表情数据库上的实验结果表明,无论在计算量还是识别性能上都比传统的Gabor滤波器组更具有优势。
第二,提出双向二维直接线性判别分析算法。该算法从水平和垂直两个方向对图像矩阵执行直接线性判别分析,进行列和行的两次维数压缩,降低了特征维数。在JAFFE人脸表情数据库中的实验结果表明,算法在提高了降维能力的同时,也提高了识别率。
第三,将二维判别保局投影算法应用到人脸表情识别的特征提取中。在JAFFE表情库的实验中,分析比较了二维判别保局投影算法较之于二维保局投影算法在表情特征的识别与分类中的异同及优势。
第四,提出一种基于多特征集成分类器的方法进行人脸表情识别。构造一个基于神经网络的集成分类器模型,对多特征多分类器的输出进行决策融合。在JAFFE表情库的实验中取得了令人满意的结果,体现了多特征集成分类器的明显优势,也充分说明了神经网络的集成分类器模型的准确性和稳定性。
实验结果表明,本文改进的Gabor特征提取算法、提出的双向二维直接线性判别分析算法,在提高了降维能力的同时,也提高了识别率。提出的多特征集成分类器的方法在JAFFE表情库可以实现91.43%的最高识别率,识别效果令人满意。
Facial expression recognition is one of the most challenging research topics in the fields of artificial intelligence and human-machine interaction. Aiming at letting computers recognize human facial expressions automatically. Consequently analyzes emotions and psychology. This will further strengthen the friendliness and intelligence of human-computer interaction. It has both high research value and wide range of potential market value.
Facial expression recognition system consists of such modules as face detection, feature extraction and expression classification. This paper mainly studies a number of key issues in the process of feature extraction and expression classification, analyzes the deficiencies in the existing algorithms. Several improved algorithms and methods for these tasks are developed. And simulation experiments are did. The major contributions of this paper are as follows:
Firstly, improve the Gabor feature extraction algorithm. We propose a new Gabor features dimension reduction method that utilizes estimation of distribution algorithms (EDA) to search optimal Gabor kernels’scales and orientations. Experimental results on JAFFE database demonstrate that our method is more effective for both dimension reduction and image representation than traditional Gabor filter bank.
Secondly, propose two directional two dimensional direct LDA((2D)2DLDA) algorithm. DLDA algorithm first works in row direction of image and then works in the column direction of image to directly extract the image scatter matrix from 2D image. Compress the dimensions from column direction to row direction, reduce the feature dimensions. Experimental results on JAFFE database demonstrate that our proposed algorithm not only enhance the ability to reduce dimensions, but also improve the recognition rates.
Thirdly, apply the two-dimensional discriminant locality preserving projections ,(2D-DLPP) algorithm. Experimental results on JAFFE database show that 2D-DLPP is better than 2DLPP and LPP in expression feature extraction and classification.
Lastly, propose a multi-feature and combining multiple classifiers method for facial expression recognition. We develop a model of combining multiple classifiers based on nerve net. The outputs of three classifiers are input to the model to get facial expression recognition. Experimental results on JAFFE database demonstrate that our proposed method is superior to the single feature and single classifier.
The experimental results show that our improved Gabor feature extraction algorithm and proposed two directional two dimensional direct LDA algorithms not only enhance the ability to reduce dimensions, but also improve the recognition rates. Our proposed multi-feature and combining multiple classifiers method get satisfactory results. The high recognition rate reaches 1.43% on JAFFE database.
人脸表情识别系统一般包括人脸检测、特征提取、表情分类等环节。本文主要研究了特征提取和表情分类过程中的一些关键问题,分析了现有算法中的不足,提出改进算法,并进行了仿真实验。主要的工作如下:
第一,改进Gabor特征提取算法。提出一种Gabor特征选择方法,利用分布估计算法对Gabor滤波器组的尺度和方向进行优化选择,选择出最佳的Gabor核的尺度和方向,并在此基础上提取特征。在日本的JAFFE表情数据库上的实验结果表明,无论在计算量还是识别性能上都比传统的Gabor滤波器组更具有优势。
第二,提出双向二维直接线性判别分析算法。该算法从水平和垂直两个方向对图像矩阵执行直接线性判别分析,进行列和行的两次维数压缩,降低了特征维数。在JAFFE人脸表情数据库中的实验结果表明,算法在提高了降维能力的同时,也提高了识别率。
第三,将二维判别保局投影算法应用到人脸表情识别的特征提取中。在JAFFE表情库的实验中,分析比较了二维判别保局投影算法较之于二维保局投影算法在表情特征的识别与分类中的异同及优势。
第四,提出一种基于多特征集成分类器的方法进行人脸表情识别。构造一个基于神经网络的集成分类器模型,对多特征多分类器的输出进行决策融合。在JAFFE表情库的实验中取得了令人满意的结果,体现了多特征集成分类器的明显优势,也充分说明了神经网络的集成分类器模型的准确性和稳定性。
实验结果表明,本文改进的Gabor特征提取算法、提出的双向二维直接线性判别分析算法,在提高了降维能力的同时,也提高了识别率。提出的多特征集成分类器的方法在JAFFE表情库可以实现91.43%的最高识别率,识别效果令人满意。
Facial expression recognition is one of the most challenging research topics in the fields of artificial intelligence and human-machine interaction. Aiming at letting computers recognize human facial expressions automatically. Consequently analyzes emotions and psychology. This will further strengthen the friendliness and intelligence of human-computer interaction. It has both high research value and wide range of potential market value.
Facial expression recognition system consists of such modules as face detection, feature extraction and expression classification. This paper mainly studies a number of key issues in the process of feature extraction and expression classification, analyzes the deficiencies in the existing algorithms. Several improved algorithms and methods for these tasks are developed. And simulation experiments are did. The major contributions of this paper are as follows:
Firstly, improve the Gabor feature extraction algorithm. We propose a new Gabor features dimension reduction method that utilizes estimation of distribution algorithms (EDA) to search optimal Gabor kernels’scales and orientations. Experimental results on JAFFE database demonstrate that our method is more effective for both dimension reduction and image representation than traditional Gabor filter bank.
Secondly, propose two directional two dimensional direct LDA((2D)2DLDA) algorithm. DLDA algorithm first works in row direction of image and then works in the column direction of image to directly extract the image scatter matrix from 2D image. Compress the dimensions from column direction to row direction, reduce the feature dimensions. Experimental results on JAFFE database demonstrate that our proposed algorithm not only enhance the ability to reduce dimensions, but also improve the recognition rates.
Thirdly, apply the two-dimensional discriminant locality preserving projections ,(2D-DLPP) algorithm. Experimental results on JAFFE database show that 2D-DLPP is better than 2DLPP and LPP in expression feature extraction and classification.
Lastly, propose a multi-feature and combining multiple classifiers method for facial expression recognition. We develop a model of combining multiple classifiers based on nerve net. The outputs of three classifiers are input to the model to get facial expression recognition. Experimental results on JAFFE database demonstrate that our proposed method is superior to the single feature and single classifier.
The experimental results show that our improved Gabor feature extraction algorithm and proposed two directional two dimensional direct LDA algorithms not only enhance the ability to reduce dimensions, but also improve the recognition rates. Our proposed multi-feature and combining multiple classifiers method get satisfactory results. The high recognition rate reaches 1.43% on JAFFE database.
引文
[1]Ekman P, Friesen W V. Facial Action Coding System: A Technique for the Measurement official Movement [M]. Palo Alto: Consulting Psychologists Press, 197
[2]Y. Yacoob, L. Davis. Recognizing Human Facial Expressions from Long Image Sequences Using Optical Flow [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence, 1996, V18(6): 636-642
[3]Calder Andrew J, Burton A Mike et al. A Principal Component Analysis of Facial Expressions [J]. Vision research, 2001, V41(9): 1179-208
[4]I. Bueiu, G.. Kotropoulos, I. Pitas. Ica and Gabor Representation for Facial Expression Recognition [J]. IEEE Trans. on Proc. Int. Conf. on Image Processing, 2003: 855-858
[5]D. Swets, J. Weng, Using discriminant eigenfeatures for image retrieval, IEEE Trans. On Pattern Analysis and Machine Intelligence, 1996, V18(8): 831-836
[6]R. Lotlikar and R. Kothari, Fractional-step dimensionality reduction [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence, 2000, V22(6): 623–627
[7]Hua Yu, Jie Yang.A direct LDA algorithm for high-dimensional data-with application to face recognition [J]. Pattern Recognition, 2001, V34: 2067-2070
[8]Juwei Lu, Kostantinos N. Plataniotis, and Anastasios N. Venetsanopoulos. Face Recognition Using LDA-Based Algorithms [J]. IEEE Transactions on Neural Networks, 2003, V14(1): 195-200
[9]Zhan Yong-zhao, Ye Jing-fu, Niu De-jiao, Cao Peng. Facial Expression Recognition Based on Gabor Wavelet Transformation and Elastic Templates Matching [A]. Proceedings of the Third International Conference on Image and Graphics [C]. Washington, DC, USA: IEEE Computer Society, 2004: 254-257
[10]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,2005,17(8):993-998
[11]JinHui, GaoWen. Analysis and application of the facial expression motions based on eigen-flow [J]. Journal of Software, 2003,V14(12): 2098-2105.[金辉,高文.基于特征流的面部表情运动分析及应用[J].软件学报,2003,14(12):2098-2105]
[12]董戎萍,唐伯良.基于DCT-BP神经网络的人脸表情识别[J].微计算机信息(测控自动化),2005,21(18):147-149
[13]D.T. Lin, J. Chen, Facial expressions classification with hierarchical radial basis function networks [J]. in: Proceedings of the 6th International Conference on Neural Information Processing, 1999,V3: 202–1207
[14]Chathura R. De Silva, Surendra Ranganath, Liyanage C. De Silva. Cloud basic function neural network: A modified RBF network architecture for holistic facial expression recognition [J], Pattern Recognition, 2008, V41(4): 1241–1253
[15]Yang J, Zhang D, Yang J Y. Two-dimensional PCA: A new approach to appearance-based face representation and recognition [J]. IEEE Transactions Pattern Analysis Machine Intelligence, 2004, V26(1): 131-137
[16]D.Zhang and Z.H.Zhou. (2D)2DPCA: 2-directional 2-dimensional PCA for efficient face representation and recognition[J]. Neurocomputing, 2005, V69(1-3): 224-231
[17]Ming Li , Baozong Yuan. 2D-LDA: A statistical linear discriminant analysis for image matrix [J]. Pattern Recognition Letters, 2005, V26:527–532
[18]Huilin Xiong, M.N.S. Swamy, M.O.Ahmad. Two-dimensional FLD for face recognition [J]. Pattern Recognition, 2005, V38: 1121– 1124
[19]JianYang, David Zhang, XuYong, Jing-yuYang. Two-dimensional discriminant transform for face recognition [J]. Pattern Recognition, 2005, V38: 1125– 1129
[20]P. Nagabhushan, D.S. Guru, B.H. Shekar. (2D)2 FLD: An efficient approach for appearance based object recognition [J]. Neurocomputing, 2006, V69: 934–940
[21]Kohei Inoue, and Kiichi Urahama. Non-Iterative Two-Dimensional Linear Discriminant Analysis [A]. The 18th International Conference on Pattern Recognition (ICPR'06)[C]. IEEE Computer Society, 2006: 540-543
[22]T. Ojala, M Pietikinen, and D. Harwood, .A comparative study of texture measures with classification based on featured distribution [J]. Pattern Recognition, 1996, V29(1): 51-59
[23]Timo Ahonen, Abdenour Hadid, and Matti Pietik¨ainen. Face Recognition with Local Binary Patterns [J]. ECCV 2004, LNCS 3021, 2004: 469–481
[24]Xiaoyi Feng, Abdenour Hadid and Matti Pietik?inen. A Coarse-to-Fine Classification Scheme for Facial Expression Recognition [J]. ICIAR 2004, LNCS 3212, 2004: 668–675
[25]X. Feng, M. Pietik?inen, and A. Hadid. Facial Expression Recognition with Local BinaryPatterns and Linear Programming [J]. Pattern Recognition and Image Analysis, 2005, V15(2): 546–548
[26]Xiangsheng Huang, Stan Z Li, Yangsheng Wang. Jensen-Shannon Boosting Learning for Object Recognition [A]. Computer Vision and Pattern Recognition 2005. (CVPR 2005)[C], IEEE Computer Society Conference on 2(20-25): 144–149
[27]Xiaofei He and Partha Niyogi. Locality Preserving Projections [J] Advances in Neural Information Processing Systems, Vancouver, Canada, 2003
[28]Sibao Chen, Haifeng Zhao, Min Kong, Bin Luo. 2D-LPP: A two-dimensional extensional extension of locality preserving projections [J]. Neurocomputing, 2007, V70: 912–921
[29]Dewen Hu, Guiyu Feng, Zongtan Zhou. Two-dimensional locality preserving projections (2DLPP) with its application to palmprint recognition [J]. Pattern Recognition, 2007, V40: 339–342
[30]Si-Bao Chen, Bin Luo, Guo-Ping Hu, Ren-Hua Wang. Bilateral two-dimensional locality preserving projections [A]. IEEE International Conference on Acoustics, Speech and Signal Processing [C]. 2007, V2: 601-604
[31]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,2006,42(11):10-12
[32]Qinzhen Xu, Pinzheng Zhang, Wenjiang Pei, Luxi Yang, and Zhenya He. A Facial Expression Recognition Approach Based on Confusion-crossed Support Vector Machine Tree [A]. Proceedings of the 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP'06) [C]. IEEE Computer Society, 2006: 309-312
[33]Lin SH, Kung SY, Lin LJ. Face recognition/detection by probabilistic decision-based neural network [J]. IEEE Transactions on Neural Networks 1997; V8(1): 114-32
[33]Jianxin Wu, Zhi-Hua Zhou. Efficient face candidates selector for face detection [J]. Pattern Recognition, 2003, V36: 1175-1186
[34]王力维.表情识别中预处理与人脸特征提取算法的研究.东南大学硕士学位论文,2006
[35]张一鸣.人脸表情识别.大连理工大学硕士学位论文,2006
[36]史宜斌.基于特征融合的人脸表情识别技术的研究.江南大学硕士学位论文,2007
[37] M. Lyons, S. Akamatsu, M. Kamachi, et al. Coding facial expression with Gaborwavelets. Proceedings of 3rd IEEE International Conference on Automatic Face and Gesture Recognition. April 14-16 1998, Nara Japan, IEEE Computer Society: 200-205
[38]陈才扣,王正群,杨静宇,杨健.一种用于人脸识别的非线性鉴别特征的融合方法[J].小型微型计算机系统,2005,26(5)
[39]张建明,杨丽瑞,王良民.基于典型相关分析特征融合的人脸表情识别方法[J].计算机应用,2008,28(3):643-649
[40]Hull.J.J, Commike.A, Ho.T.K, Multiple Algoorithms for Handwritten Character Recognition. Proc Int workshop frontiers in handwriting recognitiom, Montreal, PQ, Canada, 1990:117-129
[41] Kittler J. Improving recognition rates by classifier combination: a theortical framework. In: Downtown AC, Impedovos(eds), Progress in Handwriting Recognition World Scientific, 1997: 231-248
[42]陈羽,赖剑煌.基于多分类器融合的人脸识别方法[J].中山大学学报,2006,45(4):23-27
[43]刘松.基于SVM信息融合的图像识别与并行实现[J].计算机工程与应用,2009,45(33):168-170
[44]蒋林波,蔡立军,易叶青.一个新的多分类器组合模型[J].计算机工程与应用,2008,44(17):131–134
[45]J. Kittler, M. Hatef, R. P. W. Duin, and J.Matas. On Combining Classifiers[J]. IEEE Trans.PAMI, V20(3):226-239, 1998
[46] Dang-Hui Liu, Kin-Man Lam, Lan-Sun Shen. Optimal sampling of Gabor features for face recognition. Pattern Recognition Letters V25, 2004: 267-276
[47] Fenlan Li, Kexin Xu. Optimal Gabor Kernel’s Scale and orientation selection for face classification. Optics & Laser Technology 39: 852–857
[48]邓洪波,金连文.一种基于局部Gabor滤波器组及PCA+LDA的人脸表情识别方法.中国图象图形学报,2007,12(2):322–329
[49]WeiFeng Liu, ZengFu Wang. Facial Expression Recognition Based on Fusion of Multiple Gabor Features[A]. The 18th International Conference on Pattern Recognition (ICPR'06)[C]. IEEE Computer Society, 2006: 536–539
[50]Larranaga, P., and Lozano, J. A., Estimation of distribution algorithm. A new tool forevolutionary computation, Kluwer Academic Publishers, 2001
[51]Baluja S.Population-Based Incremental Learning: A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning. Technical Report CMU-CS-94-163, Pittsburgh, PA: Carnegie Mellon University, 1994
[52]L. Chen, H.M. Liao, M. Ko, J. Lin, G. Yu, A new LDA-based face recognition system which can solve the small sample size problem [J], Pattern Recognition, 2000, V33: 1713–1726
[53]Hua Yu, Jie Yang.A direct LDA algorithm for high-dimensional data-with application to face recognition [J]. Pattern Recognition, 2001, V34: 2067-2070
[54]D.U. Cho, U.D. Chang, B.H. Kim, S.H. Lee, Y.L.J. Bae, S.C. Ha, 2D direct LDA algorithm for face recognition[A], Proc. Fourth Int. Conf. Software Eng. Res.(2006)[C]: 245–248
[55]D.U. Cho, U.D. Chang, B.H. Kim, S.H. Lee, Y.L.J. Bae, S.C. Ha, 2D Direct LDA for Efficient Face Recognition, ICIC 2006, LNCIS 345: 566-571
[56]Weiwei Yu, Xiaolong Teng, Chongqing Liu. Face recognition using discriminant locality preserving projections[J]. Image and Vision Computing, 2006, V24(3): 239–248
[57]Ruicong Zhi, Qiuqi Ruan. Facial expression recognition based on two-dimensional discriminant locality preserving projections[J]. Neurocomputing, 2008, V71: 1730–1734
[58]Zhu J K,Mang V, Peng M. Gabor Wavelets Transform and Extended Nearest Feature Space Classifier for Face Recognition[A]. Proceeding of the Third International Conference on Image and Graphics(ICIG'04)[C]. IEEE Computer Society, 2004: 246-249
[59]Zhang H H, Zhang B L, HuangW M. Gabor Wavelet Associative Memory for Face Recognition[J]. IEEE Trans On Neural Networks, 2005, V16(1): 275-278
[60]马晓燕,杨国胜,范秋凤,王应军.基于Gabor小波和二维主元分析的人脸识别[J].计算机工程与应用,2006, (10):55-57
[61]姚伟,孙正兴,张岩.面向脸部表情识别的Gabor特征选择方法[J].计算机辅助设计与图形学学报,2008,20(1):79-84
[62]Jian gang Yu , Bir Bhanu. Evolutionary feature synthesis for facial expression recognition [J]. Available online 10 January 2006 Pattern Recognition Letters, 2006,V27: 1289-1298
[63]王蕴红,范伟,谭铁牛.融合全局与局部特征的子空间人脸识别算法[J].计算机学报,2005,28(10):1657-1663
[64]周艳平,夏利民,宋星光.基于Gabor滤波的多分类器集成人脸表情识别[J].长沙交通学院学报,2005,21(2):70-74
[65]Xiaofei He, Shuicheng Yan, Yuxiao Hu, Niyogi P, Hong-Jiang Zhang. Face Recognition Using laplacianfaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, V27(3): 328-340
[66]Zhan Yong-zhao, Ye Jing-fu, Niu De-jiao, Cao Peng. Facial Expression Recognition Based on Gabor Wavelet Transformation and Elastic Templates Matching[A]. Proceedings of the Third International Conference on Image and Graphics[C]. Washington, DC, USA: IEEE Computer Society, 2004: 254-257
[67]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,2005,17(8):993-998
[2]Y. Yacoob, L. Davis. Recognizing Human Facial Expressions from Long Image Sequences Using Optical Flow [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence, 1996, V18(6): 636-642
[3]Calder Andrew J, Burton A Mike et al. A Principal Component Analysis of Facial Expressions [J]. Vision research, 2001, V41(9): 1179-208
[4]I. Bueiu, G.. Kotropoulos, I. Pitas. Ica and Gabor Representation for Facial Expression Recognition [J]. IEEE Trans. on Proc. Int. Conf. on Image Processing, 2003: 855-858
[5]D. Swets, J. Weng, Using discriminant eigenfeatures for image retrieval, IEEE Trans. On Pattern Analysis and Machine Intelligence, 1996, V18(8): 831-836
[6]R. Lotlikar and R. Kothari, Fractional-step dimensionality reduction [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence, 2000, V22(6): 623–627
[7]Hua Yu, Jie Yang.A direct LDA algorithm for high-dimensional data-with application to face recognition [J]. Pattern Recognition, 2001, V34: 2067-2070
[8]Juwei Lu, Kostantinos N. Plataniotis, and Anastasios N. Venetsanopoulos. Face Recognition Using LDA-Based Algorithms [J]. IEEE Transactions on Neural Networks, 2003, V14(1): 195-200
[9]Zhan Yong-zhao, Ye Jing-fu, Niu De-jiao, Cao Peng. Facial Expression Recognition Based on Gabor Wavelet Transformation and Elastic Templates Matching [A]. Proceedings of the Third International Conference on Image and Graphics [C]. Washington, DC, USA: IEEE Computer Society, 2004: 254-257
[10]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,2005,17(8):993-998
[11]JinHui, GaoWen. Analysis and application of the facial expression motions based on eigen-flow [J]. Journal of Software, 2003,V14(12): 2098-2105.[金辉,高文.基于特征流的面部表情运动分析及应用[J].软件学报,2003,14(12):2098-2105]
[12]董戎萍,唐伯良.基于DCT-BP神经网络的人脸表情识别[J].微计算机信息(测控自动化),2005,21(18):147-149
[13]D.T. Lin, J. Chen, Facial expressions classification with hierarchical radial basis function networks [J]. in: Proceedings of the 6th International Conference on Neural Information Processing, 1999,V3: 202–1207
[14]Chathura R. De Silva, Surendra Ranganath, Liyanage C. De Silva. Cloud basic function neural network: A modified RBF network architecture for holistic facial expression recognition [J], Pattern Recognition, 2008, V41(4): 1241–1253
[15]Yang J, Zhang D, Yang J Y. Two-dimensional PCA: A new approach to appearance-based face representation and recognition [J]. IEEE Transactions Pattern Analysis Machine Intelligence, 2004, V26(1): 131-137
[16]D.Zhang and Z.H.Zhou. (2D)2DPCA: 2-directional 2-dimensional PCA for efficient face representation and recognition[J]. Neurocomputing, 2005, V69(1-3): 224-231
[17]Ming Li , Baozong Yuan. 2D-LDA: A statistical linear discriminant analysis for image matrix [J]. Pattern Recognition Letters, 2005, V26:527–532
[18]Huilin Xiong, M.N.S. Swamy, M.O.Ahmad. Two-dimensional FLD for face recognition [J]. Pattern Recognition, 2005, V38: 1121– 1124
[19]JianYang, David Zhang, XuYong, Jing-yuYang. Two-dimensional discriminant transform for face recognition [J]. Pattern Recognition, 2005, V38: 1125– 1129
[20]P. Nagabhushan, D.S. Guru, B.H. Shekar. (2D)2 FLD: An efficient approach for appearance based object recognition [J]. Neurocomputing, 2006, V69: 934–940
[21]Kohei Inoue, and Kiichi Urahama. Non-Iterative Two-Dimensional Linear Discriminant Analysis [A]. The 18th International Conference on Pattern Recognition (ICPR'06)[C]. IEEE Computer Society, 2006: 540-543
[22]T. Ojala, M Pietikinen, and D. Harwood, .A comparative study of texture measures with classification based on featured distribution [J]. Pattern Recognition, 1996, V29(1): 51-59
[23]Timo Ahonen, Abdenour Hadid, and Matti Pietik¨ainen. Face Recognition with Local Binary Patterns [J]. ECCV 2004, LNCS 3021, 2004: 469–481
[24]Xiaoyi Feng, Abdenour Hadid and Matti Pietik?inen. A Coarse-to-Fine Classification Scheme for Facial Expression Recognition [J]. ICIAR 2004, LNCS 3212, 2004: 668–675
[25]X. Feng, M. Pietik?inen, and A. Hadid. Facial Expression Recognition with Local BinaryPatterns and Linear Programming [J]. Pattern Recognition and Image Analysis, 2005, V15(2): 546–548
[26]Xiangsheng Huang, Stan Z Li, Yangsheng Wang. Jensen-Shannon Boosting Learning for Object Recognition [A]. Computer Vision and Pattern Recognition 2005. (CVPR 2005)[C], IEEE Computer Society Conference on 2(20-25): 144–149
[27]Xiaofei He and Partha Niyogi. Locality Preserving Projections [J] Advances in Neural Information Processing Systems, Vancouver, Canada, 2003
[28]Sibao Chen, Haifeng Zhao, Min Kong, Bin Luo. 2D-LPP: A two-dimensional extensional extension of locality preserving projections [J]. Neurocomputing, 2007, V70: 912–921
[29]Dewen Hu, Guiyu Feng, Zongtan Zhou. Two-dimensional locality preserving projections (2DLPP) with its application to palmprint recognition [J]. Pattern Recognition, 2007, V40: 339–342
[30]Si-Bao Chen, Bin Luo, Guo-Ping Hu, Ren-Hua Wang. Bilateral two-dimensional locality preserving projections [A]. IEEE International Conference on Acoustics, Speech and Signal Processing [C]. 2007, V2: 601-604
[31]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,2006,42(11):10-12
[32]Qinzhen Xu, Pinzheng Zhang, Wenjiang Pei, Luxi Yang, and Zhenya He. A Facial Expression Recognition Approach Based on Confusion-crossed Support Vector Machine Tree [A]. Proceedings of the 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP'06) [C]. IEEE Computer Society, 2006: 309-312
[33]Lin SH, Kung SY, Lin LJ. Face recognition/detection by probabilistic decision-based neural network [J]. IEEE Transactions on Neural Networks 1997; V8(1): 114-32
[33]Jianxin Wu, Zhi-Hua Zhou. Efficient face candidates selector for face detection [J]. Pattern Recognition, 2003, V36: 1175-1186
[34]王力维.表情识别中预处理与人脸特征提取算法的研究.东南大学硕士学位论文,2006
[35]张一鸣.人脸表情识别.大连理工大学硕士学位论文,2006
[36]史宜斌.基于特征融合的人脸表情识别技术的研究.江南大学硕士学位论文,2007
[37] M. Lyons, S. Akamatsu, M. Kamachi, et al. Coding facial expression with Gaborwavelets. Proceedings of 3rd IEEE International Conference on Automatic Face and Gesture Recognition. April 14-16 1998, Nara Japan, IEEE Computer Society: 200-205
[38]陈才扣,王正群,杨静宇,杨健.一种用于人脸识别的非线性鉴别特征的融合方法[J].小型微型计算机系统,2005,26(5)
[39]张建明,杨丽瑞,王良民.基于典型相关分析特征融合的人脸表情识别方法[J].计算机应用,2008,28(3):643-649
[40]Hull.J.J, Commike.A, Ho.T.K, Multiple Algoorithms for Handwritten Character Recognition. Proc Int workshop frontiers in handwriting recognitiom, Montreal, PQ, Canada, 1990:117-129
[41] Kittler J. Improving recognition rates by classifier combination: a theortical framework. In: Downtown AC, Impedovos(eds), Progress in Handwriting Recognition World Scientific, 1997: 231-248
[42]陈羽,赖剑煌.基于多分类器融合的人脸识别方法[J].中山大学学报,2006,45(4):23-27
[43]刘松.基于SVM信息融合的图像识别与并行实现[J].计算机工程与应用,2009,45(33):168-170
[44]蒋林波,蔡立军,易叶青.一个新的多分类器组合模型[J].计算机工程与应用,2008,44(17):131–134
[45]J. Kittler, M. Hatef, R. P. W. Duin, and J.Matas. On Combining Classifiers[J]. IEEE Trans.PAMI, V20(3):226-239, 1998
[46] Dang-Hui Liu, Kin-Man Lam, Lan-Sun Shen. Optimal sampling of Gabor features for face recognition. Pattern Recognition Letters V25, 2004: 267-276
[47] Fenlan Li, Kexin Xu. Optimal Gabor Kernel’s Scale and orientation selection for face classification. Optics & Laser Technology 39: 852–857
[48]邓洪波,金连文.一种基于局部Gabor滤波器组及PCA+LDA的人脸表情识别方法.中国图象图形学报,2007,12(2):322–329
[49]WeiFeng Liu, ZengFu Wang. Facial Expression Recognition Based on Fusion of Multiple Gabor Features[A]. The 18th International Conference on Pattern Recognition (ICPR'06)[C]. IEEE Computer Society, 2006: 536–539
[50]Larranaga, P., and Lozano, J. A., Estimation of distribution algorithm. A new tool forevolutionary computation, Kluwer Academic Publishers, 2001
[51]Baluja S.Population-Based Incremental Learning: A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning. Technical Report CMU-CS-94-163, Pittsburgh, PA: Carnegie Mellon University, 1994
[52]L. Chen, H.M. Liao, M. Ko, J. Lin, G. Yu, A new LDA-based face recognition system which can solve the small sample size problem [J], Pattern Recognition, 2000, V33: 1713–1726
[53]Hua Yu, Jie Yang.A direct LDA algorithm for high-dimensional data-with application to face recognition [J]. Pattern Recognition, 2001, V34: 2067-2070
[54]D.U. Cho, U.D. Chang, B.H. Kim, S.H. Lee, Y.L.J. Bae, S.C. Ha, 2D direct LDA algorithm for face recognition[A], Proc. Fourth Int. Conf. Software Eng. Res.(2006)[C]: 245–248
[55]D.U. Cho, U.D. Chang, B.H. Kim, S.H. Lee, Y.L.J. Bae, S.C. Ha, 2D Direct LDA for Efficient Face Recognition, ICIC 2006, LNCIS 345: 566-571
[56]Weiwei Yu, Xiaolong Teng, Chongqing Liu. Face recognition using discriminant locality preserving projections[J]. Image and Vision Computing, 2006, V24(3): 239–248
[57]Ruicong Zhi, Qiuqi Ruan. Facial expression recognition based on two-dimensional discriminant locality preserving projections[J]. Neurocomputing, 2008, V71: 1730–1734
[58]Zhu J K,Mang V, Peng M. Gabor Wavelets Transform and Extended Nearest Feature Space Classifier for Face Recognition[A]. Proceeding of the Third International Conference on Image and Graphics(ICIG'04)[C]. IEEE Computer Society, 2004: 246-249
[59]Zhang H H, Zhang B L, HuangW M. Gabor Wavelet Associative Memory for Face Recognition[J]. IEEE Trans On Neural Networks, 2005, V16(1): 275-278
[60]马晓燕,杨国胜,范秋凤,王应军.基于Gabor小波和二维主元分析的人脸识别[J].计算机工程与应用,2006, (10):55-57
[61]姚伟,孙正兴,张岩.面向脸部表情识别的Gabor特征选择方法[J].计算机辅助设计与图形学学报,2008,20(1):79-84
[62]Jian gang Yu , Bir Bhanu. Evolutionary feature synthesis for facial expression recognition [J]. Available online 10 January 2006 Pattern Recognition Letters, 2006,V27: 1289-1298
[63]王蕴红,范伟,谭铁牛.融合全局与局部特征的子空间人脸识别算法[J].计算机学报,2005,28(10):1657-1663
[64]周艳平,夏利民,宋星光.基于Gabor滤波的多分类器集成人脸表情识别[J].长沙交通学院学报,2005,21(2):70-74
[65]Xiaofei He, Shuicheng Yan, Yuxiao Hu, Niyogi P, Hong-Jiang Zhang. Face Recognition Using laplacianfaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, V27(3): 328-340
[66]Zhan Yong-zhao, Ye Jing-fu, Niu De-jiao, Cao Peng. Facial Expression Recognition Based on Gabor Wavelet Transformation and Elastic Templates Matching[A]. Proceedings of the Third International Conference on Image and Graphics[C]. Washington, DC, USA: IEEE Computer Society, 2004: 254-257
[67]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,2005,17(8):993-998