静态人脸图像识别研究
摘要
人脸识别是当前人工智能和模式识别领域的一个研究热点。特征提取是人脸识别的关键,直接影响识别结果。本文主要对特征提取算法进行研究。
一维方法特征提取时运算量大,特别是图像很大时。二维方法特征提取直接,速度快,但提取出的特征是矩阵,特征数量大,影响分类速度。结合两者的优点,提出一种基于2DPCA(two-Dimensional Principal ComponentsAnalysis)和DLDA(Direct Linear Discriminant Analysis)的人脸识别算法,先用2DPCA处理原始图像,降维后进行DLDA处理,并深入分析了特征向量参数选取的问题。实验结果表明,识别率和分类速度均有很大提高。
传统特征脸方法需要大量人脸样本且当人脸样本增加时需要重新训练“特征脸”,不适合人脸样本较少和实时性要求比较高的场合。针对这一问题,提出一种基于全局和局部特征的LBP(Local Binary Pattern)人脸识别算法。该方法无须训练“特征脸”,直接抽取人脸图像的局部和全局直方图特征作为图像特征进行识别。实验结果表明,该方法具有较好的实时性和识别率,且对光照不敏感。
本文还研究了单样本人脸识别问题。专门研究了增加训练样本和利用单样本进行人脸识别的方法。在ORL人脸库中验证了这些方法的有效性。
Face recognition is one of active research topics in the fields of pattern recognition and artificial intelligence. And feature extraction is the key of human face recognition, which directly influences the recognition result. This paper takes a research on the feature extraction algorithm.
Computational amount is large when using the one-dimensional method of feature extraction, especially for large images. The two-dimensional method extracts feature directly and rapidly, but the features must be expressed with matrixes. Therefore the classification speed is affected by too many features. Hence, by combining their virtues, a new approach is proposed to recognize human faces based on 2DPCA (two-Dimensional Principal Components Analysis) and DLDA (Direct Linear Discriminant Analysis). First, 2DPCA is used to deal with original images, and then DLDA is used to compress the feature. Also the parameter selection of eigenvector is analyzed deeply in this paper. The results show that both recognition rate and classification speed are greatly improved.
The traditional eigenfaces methods demand large face samples, and eigenfaces have to be retrained when additional face samples are added. Thus, it is not suitable for face recognition with requirements of fewer samples and high real time ability. For this problem, a LBP face recognition method based on combination features of global and local features is presented. Without re-training the eigenfaces, it directly extracts the face histogram features of global and local as feature for recognition. The experimental results indicate that the method has a higher recognition rate, better real time character and it was not sensitive to illumination condition.
The single training image per person is also discussed in this paper. Both the methods of increasing training samples and using single training image for face recognition are especially researched. The feasibility of those methods is verified in ORL face database.
一维方法特征提取时运算量大,特别是图像很大时。二维方法特征提取直接,速度快,但提取出的特征是矩阵,特征数量大,影响分类速度。结合两者的优点,提出一种基于2DPCA(two-Dimensional Principal ComponentsAnalysis)和DLDA(Direct Linear Discriminant Analysis)的人脸识别算法,先用2DPCA处理原始图像,降维后进行DLDA处理,并深入分析了特征向量参数选取的问题。实验结果表明,识别率和分类速度均有很大提高。
传统特征脸方法需要大量人脸样本且当人脸样本增加时需要重新训练“特征脸”,不适合人脸样本较少和实时性要求比较高的场合。针对这一问题,提出一种基于全局和局部特征的LBP(Local Binary Pattern)人脸识别算法。该方法无须训练“特征脸”,直接抽取人脸图像的局部和全局直方图特征作为图像特征进行识别。实验结果表明,该方法具有较好的实时性和识别率,且对光照不敏感。
本文还研究了单样本人脸识别问题。专门研究了增加训练样本和利用单样本进行人脸识别的方法。在ORL人脸库中验证了这些方法的有效性。
Face recognition is one of active research topics in the fields of pattern recognition and artificial intelligence. And feature extraction is the key of human face recognition, which directly influences the recognition result. This paper takes a research on the feature extraction algorithm.
Computational amount is large when using the one-dimensional method of feature extraction, especially for large images. The two-dimensional method extracts feature directly and rapidly, but the features must be expressed with matrixes. Therefore the classification speed is affected by too many features. Hence, by combining their virtues, a new approach is proposed to recognize human faces based on 2DPCA (two-Dimensional Principal Components Analysis) and DLDA (Direct Linear Discriminant Analysis). First, 2DPCA is used to deal with original images, and then DLDA is used to compress the feature. Also the parameter selection of eigenvector is analyzed deeply in this paper. The results show that both recognition rate and classification speed are greatly improved.
The traditional eigenfaces methods demand large face samples, and eigenfaces have to be retrained when additional face samples are added. Thus, it is not suitable for face recognition with requirements of fewer samples and high real time ability. For this problem, a LBP face recognition method based on combination features of global and local features is presented. Without re-training the eigenfaces, it directly extracts the face histogram features of global and local as feature for recognition. The experimental results indicate that the method has a higher recognition rate, better real time character and it was not sensitive to illumination condition.
The single training image per person is also discussed in this paper. Both the methods of increasing training samples and using single training image for face recognition are especially researched. The feasibility of those methods is verified in ORL face database.
引文
[1]张敏贵,潘泉,张洪才,张绍武.多生物特征识别.信息与控制.2002,31(6):524-528页
[2]Hong Lin,Jain Anil.Integrating faces and fingerprints for personal identification.IEEE Trans.PAMI.1998,20(12):1295-1307P
[3]Kittler J,Matas J,Jonsson K,et al.Combining evidence in personal identity verification systems.Pattern Recognition Letters.1997,18(9):845-852P
[4]Kin K I,Jung K,Kim H J.Face recognition using kernel principal component analysis.IEEE Signal Processing Letters.2002,9(2):40-42P
[5]万峰,杜明辉.小样本条件下采用Gabor特征的人脸识别.计算机辅助设计与图形学学报.2005,17(2):197-201页
[6]X.He,S.Yan,Y.Hu,P.Niyogi,and H.Zhang.Face recognition using Laplacianfaces.IEEE Trans.PAMI.2005,27(3):328-340P
[7]张翠平,苏光大.人脸识别技术综述.中国图象图形学报.2000,5(11):885-894页
[8]Belhumeur P N.Eigenfaces vs.Fisherfaces:Recognition using class specific linear projection.IEEE Trans.PAMI.1997,19(7):711-720P
[9]Chen Li-Fen,Mark Liao H-Y,M-T Ko et al.A new LDA-based face recognition system which can solve the small sample size problem.Pattern Recognition.2000,33(10):1713-1726P
[10】 曹林,王东峰,邹谋炎.基于小波变换和隐马尔可夫模型的人脸识别方法.计算机工程与应用.2005,41(7):18-23页
[11]清华大学研制成功大型人脸识别系统.http://news.tsinghua.edu.cn/new/news.php?id=9879
[12]T.Kanade.Computer Recognition of Human Faces.Basel and Stuttgart:Birkhauser,1977:77-78P
[13]Kaya Y,Kobayashi K.A Basic Study on Human Face Recognition[A].In Wantanabe S,Editor,Frontiers of Pattern Recognition[C].New York:Academic Press,1972:265-289P
[14]Brunelli R,Poggio T.Face recognition:features versus templates.IEEE Trans.PAMI.1993,15(10):1042-1052P
[15]G.M.Hayley and B.M.Manjunath.Rotation invariant Texture Classification using Modified Gabor Filters.Proc.of.IEEE ICIP95.1995:262-265P
[16]Turk M,Pentland A.Eigenfaces for recognition.Journal of Cognitive Neuroscience.1991,3(1):71-86P
[17]D.Swets and J.Weng.Using discriminant eigenfeatures for image retrieval.IEEE Trans.PAMI.1996,18(8):831-836P
[18】 张杰,黄志同,王晓兰.语音识别中隐马尔可夫模型状态数的选取原则及研究.计算机工程与应用.2000,15(1):67-69页
[19]Rabiner L.A tutorial on Hidden Markov Models and selected applications in speech recognition.Proceeding of IEEE.1999,77(2):257-286P
[20]刘小军,王东峰,张丽飞,时永刚,邹谋炎.一种基于奇异值分解和隐马尔可夫模型的人脸识别方法.计算机学报.2003,26(3):340-344页
[21]Liu X,Chen T.Video-based Face Recognition Using AdaptiveHidden Markov Model[C]//Proceedings of Computer Society Conference on Computer Vision and Pattern Recognition.Nice,France:CVPR,2003:340-345P
[22]Samaria F,Young S.HMM based architecture for face identification.Image and Vision Computing.1994,12(8):537-543P
[23]S.Haykin.神经网络原理.叶世伟,史忠植.第二版.北京:机械工业出版社,2004:183-224页
[24]Kohonen T.The self-organizing map.Proceedings of the IEEE.1990,78(9):1464-1480P
[25]L Wiskott,et al.Face recognition by elastic bunch graph matching.IEEE Trans.on PAMI.1997,19(7):775-779P
[26]L.Sirovich and M.Kirby.Low-dimensional procedure for the characterization of human faces.J.Opt.Soc.Am.1987,4(3):519-524P
[27]Jian Yang,David Zhang,Jing-Yu,Yang.Two-Dimensional PCA:A New Approach to Appearance-Based Face Representation and Recognition.IEEE Trans.PAMI.2004,26(1):131-135P
[28]L-F Chen,H-Y M.Liao,M-T Ko,J-C Lin and G-J Yu.A new LDA-based face recognition system which can solve the small sample size problem.Pattern Recognition.2000,33(5):1713-1726P
[29]Hong Z and Yang J.Optimal discriminant plane for a small number of samples and design method of classifier on the plane.Pattern Recognition.1991,24(4):317-324P
[30]Hua Yu,Jie Yang.A Direct LDA Algorithm for High-Dimensional Data-with Application to Face Recognition.Pattern Recognition.2001,34(10):2067-2070P
[31]http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
[32]苏金明,王永利.MATLAB图形图像.北京:电子工业出版社,2005:265-268页
【33]周大可,杨新,彭宁嵩.改进的线性判别分析算法及其在人脸识别中的应用.上海交通大学学报.2005,39(4):527-530页
[34]Liu C,Wechsler H.Gabor feature based classification using the enhanced Fisher linear discriminant model for face recognition.IEEE Trans Image Processing.2002,11(4):467-476P
[35]Baker S,Nayar S,Murase H.Parametric Feature Detection.International Journal of Computer Vision.1998,27(1):27-50P
[36]Feng,X,Pietik(a|¨)inen,M,Hadid,A.Facial expression recognition with local binary patterns and linear programming.Pattern Recognition and Image Analysis.2005,15(2):550-552P
[37]吕尧新,刘志强,朱祥华.基于相位谱分析技术的图像特征提取研究.计算机应用研究.2005,22(1):258-260页
[38】 毛秉毅.基于自适应LBP算法的纹理分析.计算机工程与应用.2007,43(2):89-90页
[39]Ojala T,Pietikanen M,Maenpa T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns.IEEE Trans on PAMI.2002,24:971-987P
[40]赵群,保铮.径向基函数神经网络的分类机.通信学报.1996,17(2):86-93页
[41]R.O.Duda,P.E.Hart and D.G.Stork.Pattern Classification.The second Edition.NewYork:John Wiley&Sons,2001:117-121,526-528P
【42]阎平凡,张长水.人工神经网络与模拟进化计算.第2版.北京:清华大学出版社,2005:450-455页
[43]Shiguang Shan,Bo Cao,Wen Gao,Debin Zhao.Extended Fisherface For Face Recognition From A Single Example Image Per Person.IEEE International Symposium on Circuits and Systems.2002,24(2):81-84P
[44]Wu X,Zhou Z.H.Face recognition with one training image per person.Pattern Recognition Letters.2002,23(14):1711-1719P
[45]Chen Songcan,Zhang Daoqiang,Zhou Zhi-Hua.Enhanced(PC)2A for face recognition with one training image per person.Pattern Recognition Letters.2004,25(2):1173-1181P
[2]Hong Lin,Jain Anil.Integrating faces and fingerprints for personal identification.IEEE Trans.PAMI.1998,20(12):1295-1307P
[3]Kittler J,Matas J,Jonsson K,et al.Combining evidence in personal identity verification systems.Pattern Recognition Letters.1997,18(9):845-852P
[4]Kin K I,Jung K,Kim H J.Face recognition using kernel principal component analysis.IEEE Signal Processing Letters.2002,9(2):40-42P
[5]万峰,杜明辉.小样本条件下采用Gabor特征的人脸识别.计算机辅助设计与图形学学报.2005,17(2):197-201页
[6]X.He,S.Yan,Y.Hu,P.Niyogi,and H.Zhang.Face recognition using Laplacianfaces.IEEE Trans.PAMI.2005,27(3):328-340P
[7]张翠平,苏光大.人脸识别技术综述.中国图象图形学报.2000,5(11):885-894页
[8]Belhumeur P N.Eigenfaces vs.Fisherfaces:Recognition using class specific linear projection.IEEE Trans.PAMI.1997,19(7):711-720P
[9]Chen Li-Fen,Mark Liao H-Y,M-T Ko et al.A new LDA-based face recognition system which can solve the small sample size problem.Pattern Recognition.2000,33(10):1713-1726P
[10】 曹林,王东峰,邹谋炎.基于小波变换和隐马尔可夫模型的人脸识别方法.计算机工程与应用.2005,41(7):18-23页
[11]清华大学研制成功大型人脸识别系统.http://news.tsinghua.edu.cn/new/news.php?id=9879
[12]T.Kanade.Computer Recognition of Human Faces.Basel and Stuttgart:Birkhauser,1977:77-78P
[13]Kaya Y,Kobayashi K.A Basic Study on Human Face Recognition[A].In Wantanabe S,Editor,Frontiers of Pattern Recognition[C].New York:Academic Press,1972:265-289P
[14]Brunelli R,Poggio T.Face recognition:features versus templates.IEEE Trans.PAMI.1993,15(10):1042-1052P
[15]G.M.Hayley and B.M.Manjunath.Rotation invariant Texture Classification using Modified Gabor Filters.Proc.of.IEEE ICIP95.1995:262-265P
[16]Turk M,Pentland A.Eigenfaces for recognition.Journal of Cognitive Neuroscience.1991,3(1):71-86P
[17]D.Swets and J.Weng.Using discriminant eigenfeatures for image retrieval.IEEE Trans.PAMI.1996,18(8):831-836P
[18】 张杰,黄志同,王晓兰.语音识别中隐马尔可夫模型状态数的选取原则及研究.计算机工程与应用.2000,15(1):67-69页
[19]Rabiner L.A tutorial on Hidden Markov Models and selected applications in speech recognition.Proceeding of IEEE.1999,77(2):257-286P
[20]刘小军,王东峰,张丽飞,时永刚,邹谋炎.一种基于奇异值分解和隐马尔可夫模型的人脸识别方法.计算机学报.2003,26(3):340-344页
[21]Liu X,Chen T.Video-based Face Recognition Using AdaptiveHidden Markov Model[C]//Proceedings of Computer Society Conference on Computer Vision and Pattern Recognition.Nice,France:CVPR,2003:340-345P
[22]Samaria F,Young S.HMM based architecture for face identification.Image and Vision Computing.1994,12(8):537-543P
[23]S.Haykin.神经网络原理.叶世伟,史忠植.第二版.北京:机械工业出版社,2004:183-224页
[24]Kohonen T.The self-organizing map.Proceedings of the IEEE.1990,78(9):1464-1480P
[25]L Wiskott,et al.Face recognition by elastic bunch graph matching.IEEE Trans.on PAMI.1997,19(7):775-779P
[26]L.Sirovich and M.Kirby.Low-dimensional procedure for the characterization of human faces.J.Opt.Soc.Am.1987,4(3):519-524P
[27]Jian Yang,David Zhang,Jing-Yu,Yang.Two-Dimensional PCA:A New Approach to Appearance-Based Face Representation and Recognition.IEEE Trans.PAMI.2004,26(1):131-135P
[28]L-F Chen,H-Y M.Liao,M-T Ko,J-C Lin and G-J Yu.A new LDA-based face recognition system which can solve the small sample size problem.Pattern Recognition.2000,33(5):1713-1726P
[29]Hong Z and Yang J.Optimal discriminant plane for a small number of samples and design method of classifier on the plane.Pattern Recognition.1991,24(4):317-324P
[30]Hua Yu,Jie Yang.A Direct LDA Algorithm for High-Dimensional Data-with Application to Face Recognition.Pattern Recognition.2001,34(10):2067-2070P
[31]http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
[32]苏金明,王永利.MATLAB图形图像.北京:电子工业出版社,2005:265-268页
【33]周大可,杨新,彭宁嵩.改进的线性判别分析算法及其在人脸识别中的应用.上海交通大学学报.2005,39(4):527-530页
[34]Liu C,Wechsler H.Gabor feature based classification using the enhanced Fisher linear discriminant model for face recognition.IEEE Trans Image Processing.2002,11(4):467-476P
[35]Baker S,Nayar S,Murase H.Parametric Feature Detection.International Journal of Computer Vision.1998,27(1):27-50P
[36]Feng,X,Pietik(a|¨)inen,M,Hadid,A.Facial expression recognition with local binary patterns and linear programming.Pattern Recognition and Image Analysis.2005,15(2):550-552P
[37]吕尧新,刘志强,朱祥华.基于相位谱分析技术的图像特征提取研究.计算机应用研究.2005,22(1):258-260页
[38】 毛秉毅.基于自适应LBP算法的纹理分析.计算机工程与应用.2007,43(2):89-90页
[39]Ojala T,Pietikanen M,Maenpa T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns.IEEE Trans on PAMI.2002,24:971-987P
[40]赵群,保铮.径向基函数神经网络的分类机.通信学报.1996,17(2):86-93页
[41]R.O.Duda,P.E.Hart and D.G.Stork.Pattern Classification.The second Edition.NewYork:John Wiley&Sons,2001:117-121,526-528P
【42]阎平凡,张长水.人工神经网络与模拟进化计算.第2版.北京:清华大学出版社,2005:450-455页
[43]Shiguang Shan,Bo Cao,Wen Gao,Debin Zhao.Extended Fisherface For Face Recognition From A Single Example Image Per Person.IEEE International Symposium on Circuits and Systems.2002,24(2):81-84P
[44]Wu X,Zhou Z.H.Face recognition with one training image per person.Pattern Recognition Letters.2002,23(14):1711-1719P
[45]Chen Songcan,Zhang Daoqiang,Zhou Zhi-Hua.Enhanced(PC)2A for face recognition with one training image per person.Pattern Recognition Letters.2004,25(2):1173-1181P