基于2DPCA和多分类器融合的人脸识别
|
摘要
随着信息技术的发展和日益增长的对安全技术的需要,基于生物特征的身份识别技术在近年来有了迅速发展。作为生物特征识别技术之一的人脸识别技术正在兴起,并显示了很大的优越性。在现有的各类生物识别技术中,人脸识别技术具有使用方便、用户接受度较高、具有直观性、不易被他人仿冒、人脸图像易于获得等优点。
本文以CVL人脸图像数据库为基础,研究了人脸识别的典型算法,并对某些方法进行了改进,最后实现了一个基本的人脸识别过程,本文的主要工作如下:
第一,人脸图像的预处理。主要进行了灰度化、粗切、图像平滑、图像增强及灰度归一化等预处理操作,消除了图像噪声,使图像更清晰。
第二,人脸的检测与定位。首先利用垂直灰度投影曲线得到人脸的轮廓图像,再利用基于混合投影函数(HPF)和Hough变换的方法进行眼睛的精确定位,并以眼睛为基准进行人脸图像的校准,包括旋转、剪裁和缩放等,最后图像变为100×100的标准图像。
第三,特征的选择和提取。主要研究了主成分分析(PCA)、2DPCA和独立分量分析(ICA)的算法,然后对2DPCA的算法进行了实验验证与分析,并与PCA的方法进行了比较。
最后,分类决策。主要研究了最近邻法则、BP神经网络的方法及MCFD的算法,并选择MCFD的算法进行本文的分类器设计。
实验结果表明,2DPCA和MCFD相结合的算法能够得到较好的识别结果和较快的识别速度。
With the development of information technology, biometric recognition technologies have been developed rapidly in recent years. Face recognition is relatively new among the biometric recognition technologies because of its huge potential superiority. This method shows great advantages such as convenient operation, higher acceptance, and stronger visual impression.
A face recognition system based on CVL database was realized, in which the algorithms of two-dimensional principal component analysis (2DPCA) and multi-classifiers fusion decision (MCFD) is developed. The major work includes:
Firstly, image preprocessing algorithms were studied. By image smoothing, enhancement and gray-scale normalization, the noise was cancelled and the influence of illumination was wiped off, thus cleaner images are obtained.
Secondly, image detection and orientation was studied. After the outlines of face images were obtained by the vertical grayscale projection function, the Hybrid Projection Function (HPF) and Hough transform were used to decide the orientation of eyes, then, the images were standardized from the size of 640 x 480 to the size of 100×100.
Then, feature selection and extraction algorithms were studied, including principal component analysis (PCA), 2DPCA and indpendent component analysis (ICA), based on which 2DPCA was used compared to PCA, better performance was achieved.
Finally, the design of classifier was studied. The algorithms such as the nearest neighbor method, BP neural network, and MCFD are studied, and then MCFD was adopted.
Through experiments, the algorithm based on 2DPCA and MCFD was adopted for its higher recognition rate and faster operating speed.
本文以CVL人脸图像数据库为基础,研究了人脸识别的典型算法,并对某些方法进行了改进,最后实现了一个基本的人脸识别过程,本文的主要工作如下:
第一,人脸图像的预处理。主要进行了灰度化、粗切、图像平滑、图像增强及灰度归一化等预处理操作,消除了图像噪声,使图像更清晰。
第二,人脸的检测与定位。首先利用垂直灰度投影曲线得到人脸的轮廓图像,再利用基于混合投影函数(HPF)和Hough变换的方法进行眼睛的精确定位,并以眼睛为基准进行人脸图像的校准,包括旋转、剪裁和缩放等,最后图像变为100×100的标准图像。
第三,特征的选择和提取。主要研究了主成分分析(PCA)、2DPCA和独立分量分析(ICA)的算法,然后对2DPCA的算法进行了实验验证与分析,并与PCA的方法进行了比较。
最后,分类决策。主要研究了最近邻法则、BP神经网络的方法及MCFD的算法,并选择MCFD的算法进行本文的分类器设计。
实验结果表明,2DPCA和MCFD相结合的算法能够得到较好的识别结果和较快的识别速度。
With the development of information technology, biometric recognition technologies have been developed rapidly in recent years. Face recognition is relatively new among the biometric recognition technologies because of its huge potential superiority. This method shows great advantages such as convenient operation, higher acceptance, and stronger visual impression.
A face recognition system based on CVL database was realized, in which the algorithms of two-dimensional principal component analysis (2DPCA) and multi-classifiers fusion decision (MCFD) is developed. The major work includes:
Firstly, image preprocessing algorithms were studied. By image smoothing, enhancement and gray-scale normalization, the noise was cancelled and the influence of illumination was wiped off, thus cleaner images are obtained.
Secondly, image detection and orientation was studied. After the outlines of face images were obtained by the vertical grayscale projection function, the Hybrid Projection Function (HPF) and Hough transform were used to decide the orientation of eyes, then, the images were standardized from the size of 640 x 480 to the size of 100×100.
Then, feature selection and extraction algorithms were studied, including principal component analysis (PCA), 2DPCA and indpendent component analysis (ICA), based on which 2DPCA was used compared to PCA, better performance was achieved.
Finally, the design of classifier was studied. The algorithms such as the nearest neighbor method, BP neural network, and MCFD are studied, and then MCFD was adopted.
Through experiments, the algorithm based on 2DPCA and MCFD was adopted for its higher recognition rate and faster operating speed.
引文
1.李刚,高政.人脸自动识别方法综述[J],四川:计算机应用研究,2003,8(2):4-9
2.Yang Y Z,Huang T S.Human face detection in a complex background[J],Pattern Recognition[J],1994,27(1):705-763
3.Buederman,P.Kalocsai.Neural and Psychophysical Analysis of Object and Face Recognition[J],Face Recognition:From Theory to Application,Berlin:Springer-Verlag,1998:3-25
4.P.K.Kalocsai,W.zhao,E.Elagin,Face Similarity Space as Perceived by Humans and Artificial Systems[J],Proceedings,International Conference on Automatic Face and Gesture Recognition,1998:177-180
5.V.Bruce,P.J.B.Hancock,A.M.Burton,Human Face Perception and Identification[J],Face Recognition:From Theory to Application,Berlin:Springer-Verlag,1998:51-72
6.Allen AL.Personal Descriptions[M],London:Butterworth,1950
7.Parke F I.Computer Generated Animation of Faces[J],Proceedings ACM National Conference,1972,1:451-457
8.Goldstion R J,Harmon L D,Lesk A B,Man-machine interaction in human face Identification[J],Bell Syst Teeh Journal.1972,51:399-427
9.PN Belhumeur,JP Hespanha,DJ Kriegman,Eigenfacea vs fisherfaces:a recognition using class specific linear projection[J],IEEE Trans.Pattern Analysis and Machine Intelliaence,1997,19(7):711-720
10.Ziquan Hong.Algebraic feature extraction of image for reeognition[J],Pattern Recognition.1991,24(3):211-219
11.Lades M,Vorbuggen J,Buhmann J et al.Distortion invariant object recognition in the dynamic link architecture[J],IEEE Trans,Computers,1993,42(3):300-311
12.Samaria F,Young S.HMM based architecture for face ideniifieation[J],Image and Computer Vision,1996:45-56
13.Rowley H,Baluja S,Kanade T.Neural network-based face detection[J],IEEE Trans.Pattern Analysis and Machine Intelligence.1998,20(1):23-38
14.边肇祺,张学工.模式识别(第2版)[M],北京:清华大学出版社,2000:1-50
15.Turk M and Pentland A.Face recognition using Eigenfaces[J],IEEE Conference On Computer Vision and Pattern Recognition,1991:586-591
16.洪子泉,杨静宇.基于奇异值特征和统计模型的人像识别算法[J],计算机研究与发展,1994,31(3):60-65
17.Liu C,Wechsler H,Enhanced fisher linear discriminant models for face recognition[M],Proc.the14th International Conference on Pattern Recognition,1998(2):1368-1372
18.Hong Z-Q,Yang J-Y,Optimal discriminant plane for a small number of samples and design method of classifier on the plane[M],Pattern Recognition,1991:24(4):317-324
19.Liu K,Yang J-Y,An efficient algorithm for Foley-Sammon optimal set of discriminant vectors by algebraic method[M],International Journal of Pattern Recognition and Artificial Intelligence,1992,6(5):817-829
20.Baudat G;Anouar F.Generalized Discriminant Analysis Using a Kernel Approach[J],Neural Computation,2000,12(10):2385-2404
21.Yang Jian,Jin Zhong,Jing -Yu,et al.Frangi:Essence of kernel Fisher discriminant:KPCA plus LDA[J],Pattern Recognition,2004,37(10):2097-2100
22.高秀梅,金忠,郭丽,杨静宇.基于核的广义Foley-Sammon鉴别分析[J],计算机科学,2004,31(9):165-168
23.徐勇,杨强,杨静宇.Foley-Sammon鉴别矢量集理论分析及优化模型[J],计算机科学,2003,30(9):64-66
24.Kohonen T,Somervuo P.How to make large self-organizing maps for nonvectorial data[J],Nerural Network,2002,(15):945-952
25.Arun KS,Huang TS,Blostein SD.Least-square fitting of two 3-D point sets[J],IEEE Trans Pattern Anal Mach Intell,1987,9(5):698-700
26.Izatt JA,Hee MR,Swanson EA,Lin CP,Huang D,Schuman JS,Puliafito CA,Fujimoto JG,Micrometer-scale resolution imaging of the anterior eye in vivo with optical coherence tomography[J],Arch Ophthalmol,1994;112(12):1584-1589
27.Lee C,Yang W and Parr RG Development of the colle-salvetti correlation-energy formula into a functional of the electron density[J],Phys Rev B,1988,37:785-789
28.Tabata Y,Gutta S Langer R.Controlled delivery systems for proteins using polyanhydride microspheres[J],Pharm Res,1993,10(4):487
29.唐良瑞,景晓军.图像处理实用技术[M],北京:化学工业出版社,2002
30.土井康弘,安藤繁.图像处理概论[M],北京,原子能出版社,1986,12
31.张远鹏,董海,周文灵.计算机图像处理技术基础[M],北京大学出社,1996
32.王家文,曹宇.MATLAB6.5图形图像处理[M],国防工业出版社,2004
33.张欣,徐彦君,杜利民.彩色图像中主要人脸特征位置的全自动标定[J],中国图象图形学报,2000,5(2):138-143
34.Shi-Hong Jeng,Hong Yuan Mark Liao,Chin Chuan Han,Ming Yang Chem,Yao Tsomg Liu,Facial feature detection using geometrical face model:an efficient approach[J],Pattern Recognition,1998,31(3):273-282
35.Toshiaki Kondo,Hong Yan,Automatic human face detection and recognition under non-uniform illumination[J],Pattern Recognition,1999,32(10):1707-1718
36.林维训,潘纲,吴朝晖,潘云鹤.脸部特征定位方法[J],浙江大学学报(工学版),2003(8)
37.Prabhakar S,Jain A K.Decision-level Fusion in Biometric Verification[J],Pattern Recognition,2002,35(4):861-874
38.刘哲,高广珠,余理富.一种快速而有效地定位人脸特征的方法[J],计算机应用研究,2000,17(12):19-21
39.耿新,周志华,陈世福.基于混合投影函数的眼睛定位[J],软件学报,2003,14(8):1394-1400
40.Kenneth.R.Castleman.数字图像处理[M],电子工业出版社,2000
41.边肇祺.模式识别[M],清华大学出版社,1988
42.周杰,卢春雨,张长水.人脸自动识别方法综述[J],电子学报,2000,28(4):102-106
43.张翠平,苏光大.人脸识别技术综述[J],中国图象图形学报,2000,5A(11):885-894
44.周德龙,高文,赵德斌.基于奇异值分解和判别式KL投影的人脸识别[J],软件学报,2003,14(4):783-789
45.Bartlett M,Lades H,Sejnowski T.Independent component representations for face recognition[J],Proceeding of the SIE Symposium on electronic Imaging:Human Vision and Electronic Imaging,SPIE Press,1998,3299
46.徐之海,冯华君,李奇,徐红岩.基于Karhunen-Loeve变换的人脸识别研究[J],光电工程,2001,28(6):48-51
47.Yang Jian,Zhang David,Yang Jingyu.Two-dimensional PCA:A new approach to appearance-based face representation and recognition[J],IEEE Trans.on Pattern Analysis Machine Intelligence,2004,26(1):131-137
48.R Hecht-Nielsen.Application of counter propagation networks[J],Neural Networks,1988,1:131-139
49.陈刚,戚飞虎.多分类器结合的人脸识别[J],上海交通大学学报,2001,35(2):173-176
50.李士进,郭跃飞,杨静宇.基于多分类器的人脸识别[J],数据采集与处理,2000,15(3):293-296
51.AJ Bell,TJ Sejnowski.An Information-maximization approach to blind separation and blind deconvolution[J],Neural Computation,1995,7(6):1129-1159
52.S.Amari,A.Cichocki,H.H.Yang.A new learning algorithm for blind source separation [J],Advances in Neural Information Processing,Cambridge,MA:MIT Press,1996,757-763
2.Yang Y Z,Huang T S.Human face detection in a complex background[J],Pattern Recognition[J],1994,27(1):705-763
3.Buederman,P.Kalocsai.Neural and Psychophysical Analysis of Object and Face Recognition[J],Face Recognition:From Theory to Application,Berlin:Springer-Verlag,1998:3-25
4.P.K.Kalocsai,W.zhao,E.Elagin,Face Similarity Space as Perceived by Humans and Artificial Systems[J],Proceedings,International Conference on Automatic Face and Gesture Recognition,1998:177-180
5.V.Bruce,P.J.B.Hancock,A.M.Burton,Human Face Perception and Identification[J],Face Recognition:From Theory to Application,Berlin:Springer-Verlag,1998:51-72
6.Allen AL.Personal Descriptions[M],London:Butterworth,1950
7.Parke F I.Computer Generated Animation of Faces[J],Proceedings ACM National Conference,1972,1:451-457
8.Goldstion R J,Harmon L D,Lesk A B,Man-machine interaction in human face Identification[J],Bell Syst Teeh Journal.1972,51:399-427
9.PN Belhumeur,JP Hespanha,DJ Kriegman,Eigenfacea vs fisherfaces:a recognition using class specific linear projection[J],IEEE Trans.Pattern Analysis and Machine Intelliaence,1997,19(7):711-720
10.Ziquan Hong.Algebraic feature extraction of image for reeognition[J],Pattern Recognition.1991,24(3):211-219
11.Lades M,Vorbuggen J,Buhmann J et al.Distortion invariant object recognition in the dynamic link architecture[J],IEEE Trans,Computers,1993,42(3):300-311
12.Samaria F,Young S.HMM based architecture for face ideniifieation[J],Image and Computer Vision,1996:45-56
13.Rowley H,Baluja S,Kanade T.Neural network-based face detection[J],IEEE Trans.Pattern Analysis and Machine Intelligence.1998,20(1):23-38
14.边肇祺,张学工.模式识别(第2版)[M],北京:清华大学出版社,2000:1-50
15.Turk M and Pentland A.Face recognition using Eigenfaces[J],IEEE Conference On Computer Vision and Pattern Recognition,1991:586-591
16.洪子泉,杨静宇.基于奇异值特征和统计模型的人像识别算法[J],计算机研究与发展,1994,31(3):60-65
17.Liu C,Wechsler H,Enhanced fisher linear discriminant models for face recognition[M],Proc.the14th International Conference on Pattern Recognition,1998(2):1368-1372
18.Hong Z-Q,Yang J-Y,Optimal discriminant plane for a small number of samples and design method of classifier on the plane[M],Pattern Recognition,1991:24(4):317-324
19.Liu K,Yang J-Y,An efficient algorithm for Foley-Sammon optimal set of discriminant vectors by algebraic method[M],International Journal of Pattern Recognition and Artificial Intelligence,1992,6(5):817-829
20.Baudat G;Anouar F.Generalized Discriminant Analysis Using a Kernel Approach[J],Neural Computation,2000,12(10):2385-2404
21.Yang Jian,Jin Zhong,Jing -Yu,et al.Frangi:Essence of kernel Fisher discriminant:KPCA plus LDA[J],Pattern Recognition,2004,37(10):2097-2100
22.高秀梅,金忠,郭丽,杨静宇.基于核的广义Foley-Sammon鉴别分析[J],计算机科学,2004,31(9):165-168
23.徐勇,杨强,杨静宇.Foley-Sammon鉴别矢量集理论分析及优化模型[J],计算机科学,2003,30(9):64-66
24.Kohonen T,Somervuo P.How to make large self-organizing maps for nonvectorial data[J],Nerural Network,2002,(15):945-952
25.Arun KS,Huang TS,Blostein SD.Least-square fitting of two 3-D point sets[J],IEEE Trans Pattern Anal Mach Intell,1987,9(5):698-700
26.Izatt JA,Hee MR,Swanson EA,Lin CP,Huang D,Schuman JS,Puliafito CA,Fujimoto JG,Micrometer-scale resolution imaging of the anterior eye in vivo with optical coherence tomography[J],Arch Ophthalmol,1994;112(12):1584-1589
27.Lee C,Yang W and Parr RG Development of the colle-salvetti correlation-energy formula into a functional of the electron density[J],Phys Rev B,1988,37:785-789
28.Tabata Y,Gutta S Langer R.Controlled delivery systems for proteins using polyanhydride microspheres[J],Pharm Res,1993,10(4):487
29.唐良瑞,景晓军.图像处理实用技术[M],北京:化学工业出版社,2002
30.土井康弘,安藤繁.图像处理概论[M],北京,原子能出版社,1986,12
31.张远鹏,董海,周文灵.计算机图像处理技术基础[M],北京大学出社,1996
32.王家文,曹宇.MATLAB6.5图形图像处理[M],国防工业出版社,2004
33.张欣,徐彦君,杜利民.彩色图像中主要人脸特征位置的全自动标定[J],中国图象图形学报,2000,5(2):138-143
34.Shi-Hong Jeng,Hong Yuan Mark Liao,Chin Chuan Han,Ming Yang Chem,Yao Tsomg Liu,Facial feature detection using geometrical face model:an efficient approach[J],Pattern Recognition,1998,31(3):273-282
35.Toshiaki Kondo,Hong Yan,Automatic human face detection and recognition under non-uniform illumination[J],Pattern Recognition,1999,32(10):1707-1718
36.林维训,潘纲,吴朝晖,潘云鹤.脸部特征定位方法[J],浙江大学学报(工学版),2003(8)
37.Prabhakar S,Jain A K.Decision-level Fusion in Biometric Verification[J],Pattern Recognition,2002,35(4):861-874
38.刘哲,高广珠,余理富.一种快速而有效地定位人脸特征的方法[J],计算机应用研究,2000,17(12):19-21
39.耿新,周志华,陈世福.基于混合投影函数的眼睛定位[J],软件学报,2003,14(8):1394-1400
40.Kenneth.R.Castleman.数字图像处理[M],电子工业出版社,2000
41.边肇祺.模式识别[M],清华大学出版社,1988
42.周杰,卢春雨,张长水.人脸自动识别方法综述[J],电子学报,2000,28(4):102-106
43.张翠平,苏光大.人脸识别技术综述[J],中国图象图形学报,2000,5A(11):885-894
44.周德龙,高文,赵德斌.基于奇异值分解和判别式KL投影的人脸识别[J],软件学报,2003,14(4):783-789
45.Bartlett M,Lades H,Sejnowski T.Independent component representations for face recognition[J],Proceeding of the SIE Symposium on electronic Imaging:Human Vision and Electronic Imaging,SPIE Press,1998,3299
46.徐之海,冯华君,李奇,徐红岩.基于Karhunen-Loeve变换的人脸识别研究[J],光电工程,2001,28(6):48-51
47.Yang Jian,Zhang David,Yang Jingyu.Two-dimensional PCA:A new approach to appearance-based face representation and recognition[J],IEEE Trans.on Pattern Analysis Machine Intelligence,2004,26(1):131-137
48.R Hecht-Nielsen.Application of counter propagation networks[J],Neural Networks,1988,1:131-139
49.陈刚,戚飞虎.多分类器结合的人脸识别[J],上海交通大学学报,2001,35(2):173-176
50.李士进,郭跃飞,杨静宇.基于多分类器的人脸识别[J],数据采集与处理,2000,15(3):293-296
51.AJ Bell,TJ Sejnowski.An Information-maximization approach to blind separation and blind deconvolution[J],Neural Computation,1995,7(6):1129-1159
52.S.Amari,A.Cichocki,H.H.Yang.A new learning algorithm for blind source separation [J],Advances in Neural Information Processing,Cambridge,MA:MIT Press,1996,757-763