基于小波变换的PCA人脸识别方法
|
摘要
人脸自动识别技术就是利用计算机分析人脸图像，从中提取有效的识别信息，用来辨认身份的一门技术。它使用了人体本身所固有的生物特征，是与传统方法完全不同的崭新技术，具有更好的安全性、可靠性和有效性，越来越受到人们的重视。人脸识别主要有三个部分组成：图像预处理，特征提取和分类识别。本文的图像预处理主要采用了直方图修正，并利用小波变换来降低图像的维数。特征提取方面使用PCA方法进行特征提取，最后使用距离分类法进行图像识别。
主成分分析(PCA)方法作为最成功的线性鉴别方法之一，目前仍然被广泛应用于人脸等图像识别领域，但传统的PCA方法由于提取的是图像的全局特征，因此受光照条件和人脸表情变化影响比较大，造成识别效果不是太好。经过分析发现，当人脸表情和光照条件变化时，一般仅有部分人脸区域变化明显，而其它部分变化不是太大，甚至没有变化。基于这种情况，本论文提出了分块PCA方法，在对图像进行特征提取前，首先对图像进行划分，然后再对子图像使用PCA方法提取特征向量，在特征提取时根据各个子图像在整个图像中的重要性不同，分别赋予不同的权值，最后构造分类器，进行识别。在使用PCA方法进行特征提取时，由于要先将图像转化为一维向量，这样会使图像的向量维数过高，对以后的特征提取造成困难。在此基础上，本论文进一步提出了分块2DPCA方法，与分块PCA方法不同的是，在对原图像进行划分以后，对子图像使用2DPCA方法进特特征提取，2DPCA方法由于直接利用原图像的二维矩阵构造图像的散布矩阵。使得总体散布矩阵的维数远远低于利用PCA方法得到的协方差矩阵。这样可以很大程度上提高特征提取的速度并降低特征提取的复杂度，进一步提高特征提取的准确性，使得整体识别速度提高并可以在一定程度上提高识别率。
最后，在ORL人脸库上进行了实验，验证了改进的PCA算法优于传统的PCA算法。
Automatic face recognition technology is analyzes the person face picture using the computer, extract the effective identification information, uses for identify the status of a technology. It is a totally brand-new technique different from traditional methods because it adopts the inherent organism's characteristics of human body. More and more people pay great attention to it as it is safer, more reliable and effective. Face recognition consists of three parts: Preprocessing, feature extraction and classification. In this thesis, we use histogram equalization to modify the picture and use wavelet transform to reduce the dimension of picture in the processing. Then use PCA extract feature and finally use distance classification to get the result of recognition.
As the most successful method of linear differential, principal component analysis (PCA) method is widely used in identify areas, such as face recognition. But traditional PCA is influenced by the light conditions and facial expression changed because it extract the global feature of the image, so the recognition effect is not very good. We know when expression and light conditions changing, only some face region obvious changed, and the other changed is not too much, even no changed. So based on this situation, this thesis presents a method of block-PCA. In this method, we first segment the picture and then extract eigenvector using the PCA. In extracting feature, for each of the parts in accordance with the different role in the overall image give the different weights. In the finally, we construct classification and get the result of recognition. When we use PCA method to extract feature, we should convert the image to one-dimensional vector, so it make the vector dimension of image too much high and induce difficulty to extract feature. Because of this, this thesis presents another method, it is block-2DPCA. After we segmented the image, we use 2DPCA to extract feature in the sub-image space. The matrix dimension of 2DPCA is far below dimension of the covariance matrix using PCA, because it uses the two-dimensional matrix of original image directly to make the covariance matrix. So is can be greatly improved the speed and accuracy, reduce the complexity of feature extraction. In the finally, it improved the speed of recognition and the recognition rate.
In the finally, the experimental result show the improved method of PCA is superior to method traditional PCA.
主成分分析(PCA)方法作为最成功的线性鉴别方法之一，目前仍然被广泛应用于人脸等图像识别领域，但传统的PCA方法由于提取的是图像的全局特征，因此受光照条件和人脸表情变化影响比较大，造成识别效果不是太好。经过分析发现，当人脸表情和光照条件变化时，一般仅有部分人脸区域变化明显，而其它部分变化不是太大，甚至没有变化。基于这种情况，本论文提出了分块PCA方法，在对图像进行特征提取前，首先对图像进行划分，然后再对子图像使用PCA方法提取特征向量，在特征提取时根据各个子图像在整个图像中的重要性不同，分别赋予不同的权值，最后构造分类器，进行识别。在使用PCA方法进行特征提取时，由于要先将图像转化为一维向量，这样会使图像的向量维数过高，对以后的特征提取造成困难。在此基础上，本论文进一步提出了分块2DPCA方法，与分块PCA方法不同的是，在对原图像进行划分以后，对子图像使用2DPCA方法进特特征提取，2DPCA方法由于直接利用原图像的二维矩阵构造图像的散布矩阵。使得总体散布矩阵的维数远远低于利用PCA方法得到的协方差矩阵。这样可以很大程度上提高特征提取的速度并降低特征提取的复杂度，进一步提高特征提取的准确性，使得整体识别速度提高并可以在一定程度上提高识别率。
最后，在ORL人脸库上进行了实验，验证了改进的PCA算法优于传统的PCA算法。
Automatic face recognition technology is analyzes the person face picture using the computer, extract the effective identification information, uses for identify the status of a technology. It is a totally brand-new technique different from traditional methods because it adopts the inherent organism's characteristics of human body. More and more people pay great attention to it as it is safer, more reliable and effective. Face recognition consists of three parts: Preprocessing, feature extraction and classification. In this thesis, we use histogram equalization to modify the picture and use wavelet transform to reduce the dimension of picture in the processing. Then use PCA extract feature and finally use distance classification to get the result of recognition.
As the most successful method of linear differential, principal component analysis (PCA) method is widely used in identify areas, such as face recognition. But traditional PCA is influenced by the light conditions and facial expression changed because it extract the global feature of the image, so the recognition effect is not very good. We know when expression and light conditions changing, only some face region obvious changed, and the other changed is not too much, even no changed. So based on this situation, this thesis presents a method of block-PCA. In this method, we first segment the picture and then extract eigenvector using the PCA. In extracting feature, for each of the parts in accordance with the different role in the overall image give the different weights. In the finally, we construct classification and get the result of recognition. When we use PCA method to extract feature, we should convert the image to one-dimensional vector, so it make the vector dimension of image too much high and induce difficulty to extract feature. Because of this, this thesis presents another method, it is block-2DPCA. After we segmented the image, we use 2DPCA to extract feature in the sub-image space. The matrix dimension of 2DPCA is far below dimension of the covariance matrix using PCA, because it uses the two-dimensional matrix of original image directly to make the covariance matrix. So is can be greatly improved the speed and accuracy, reduce the complexity of feature extraction. In the finally, it improved the speed of recognition and the recognition rate.
In the finally, the experimental result show the improved method of PCA is superior to method traditional PCA.
引文
[1] Hanson B. A, and Applehaum T. H, Robust Speaker-independent Word Recognition Using Static, Dynamic and Acceleration Features; Experiments with Lombard and Noisy Speech, International conference on Acoustics, speech, and signal Processing (ICASSP), PP: 857-860, 1990
[2] Juang b.H, and Paliwal K. K., "Vector Equalization in Hidden Markov Models for Noisy Speech Recognition", in Proceedings of International Conference on Acoustics, Speech and Signal Processing '92(ICASSP), Ⅰ: 301-304, 1992
[3] Jain A K, Ross A, Prabhakar S. An introduction to biometrical recognition. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(1): 4-20.
[4] Ming-Hsuan Yang, David J Kriegrnan, Detecting Faces in Images: A Survey. IEEE Trans. Pattern Analysis and Machine Intelligence, 2002, 24(1): 34-58.
[5] Ratha N K, Senior A, Boile R M, Automated biometrics. In: Singh S, urshed N, Kropatsch W, eds, Advances in Pattern Recognition - ICARR 2001. Berlin: Springer-Verlag, 2001, 2013: 445-453.
[6] Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces, Opt. Soc. Am A, 1987, 4(3): 519-524
[7] A.M.Martinez, A.C,Kak, PCA versus LDA, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(2): 228-233
[8] M.S.Bartlett, J.R.Movellan, T.J. Sejnowski. Face recognition by independent component analysis, IEEE Transactions on Neural Networks, 2002, 13(6): 1450-1464
[9] Fant, H, Acoustic Theory of Speech Production. Mouton & co. Gravenhage, The Netherlands 1960.
[10] 苏剑波、徐波，《应用模式识别技术导论》，上海交通大学出版社，2001。
[11] 董长虹、赖志国、余啸海，《Matlab图像处理与应用》国防工业出版社。，
[12] 黄贤武、仲兴荣、王加俊，基于WT／PCA的自适应神经网络人脸识别方法，计算机应用，Vol．23．No．6，June，2003．
[13] Turk M, Pentland A. Face processing: models for recognition. In: Proceedings of SPIE, 1989,1192: 22-32
[14] Turk M, Pentland A. Recognition in face space. In: Proceedings of SPIE, 1990, 1381: 43-54.
[15] 高秀梅，李淑琴，杨静宇，一种广义的K—L变换与人脸识别，青岛化工学院报，2003，23(3)，270-272
[16] Jian Yang, David Zhang, Senior Member, Tow-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition, IEEE, Trans. Pattern Analysis and Machine Intelligence, 2004, 26(1), 131-137.
[17] D.Q.Zhang, S.C.Chen, and J. Liu, representing image matrices: Eigenimages vs. Eigenvectors, Proceedings of the 2nd International Symposium on Neural Networks (ISNN'05), Chongqing, China, 2005, 2, 659-664.
[18] 孙涛，谷士文，费耀平，基于PCA算法的人脸识别方法研究比较，现代电子技术 2007，1，240
[19] 张翠平，苏光大。人脸识别技术综述。中国图像图形学报。2000，5(11)：885-894。
[20] Lien J J, Alochower A, Cohn J F, et al. Automated facial expression recognition. In: proc of the third IEEE International Conference on Automatic Face and Gesture-Recognition. Nara, Japan. 1998, 390-395
[21] Liu X M, Chen T, Kumar B K V. Face authentication for multiple subjects using eigenflow. Pattern Recognition. 2003, 36(2):313-328
[22] 孙涛，谷士文，费耀平，基于PCA算法的人脸识别方法研究比较。现代电子技术 2007(1)：113。
[23] 山世光，人脸识别中若干关键问题的研究：(博士论文)。北京：中国科学院计算机研究所，2004。
[24] 边肇其，张学工，模式识别，2版，北京：清化大学出版社，2000
[25] Ranganath S and Arun K. Face recognition using transform features and neural networks. Pattern Recognition, 1997, 30(10):1615-1622.
[26] 周涛，基于PCA的人脸识别研究：(硕士论文)。南京：南京理工大学，2004。
[27] Yambor W, Draper B, and Beveridge J.R., Analysis of PCA-based Face Recognition Algorithms: Eigenvector Selection and Distance Measures. Second Workshop on Empirical Evaluation Methods in Computer vision, 2000
[28] 陈海勇，基于子空间的人脸识别技术：(硕士论文)。南京：南京理工大学，2006
[29] Wendy S. Yambor, Analysis of PCA-Based and Fisher Discriminant-Based Image Recognition Algorithms, Computer Science Technical Report, Colorado State University, 2000
[30] Yambor.W. Draper.B, Beveridge J.R. Analysis of PCA-based Face Recognition Algorithms: Eigenvector Selection and Distance Measures. Second Workshop on Empirical Evaluation Methods in Computer Vision, 2000
[31] Barjkiran Gottumukkal, Vijayan K Asari. An improved face recognition technique based on modular PCA approach. Pattern Recognition Letters. 2004, 25(4): 429-436
[32] 陈伏兵，高秀梅，张生亮，杨静宇，基于分块PCA的人脸识别方法，小型微型计算机系统，2006(10) Vol．27，No．10，1944-1945
[33] Moon H. and Phillips J. Analysis of PCA-based on Faced Recognition Algorithms. In Boyer K and Phillips J., Editors, Empirical Evaluation Techniques In Computer Vision, IEEE Computer Society Press, Los Alamitos, CA 1998.
[2] Juang b.H, and Paliwal K. K., "Vector Equalization in Hidden Markov Models for Noisy Speech Recognition", in Proceedings of International Conference on Acoustics, Speech and Signal Processing '92(ICASSP), Ⅰ: 301-304, 1992
[3] Jain A K, Ross A, Prabhakar S. An introduction to biometrical recognition. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(1): 4-20.
[4] Ming-Hsuan Yang, David J Kriegrnan, Detecting Faces in Images: A Survey. IEEE Trans. Pattern Analysis and Machine Intelligence, 2002, 24(1): 34-58.
[5] Ratha N K, Senior A, Boile R M, Automated biometrics. In: Singh S, urshed N, Kropatsch W, eds, Advances in Pattern Recognition - ICARR 2001. Berlin: Springer-Verlag, 2001, 2013: 445-453.
[6] Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces, Opt. Soc. Am A, 1987, 4(3): 519-524
[7] A.M.Martinez, A.C,Kak, PCA versus LDA, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(2): 228-233
[8] M.S.Bartlett, J.R.Movellan, T.J. Sejnowski. Face recognition by independent component analysis, IEEE Transactions on Neural Networks, 2002, 13(6): 1450-1464
[9] Fant, H, Acoustic Theory of Speech Production. Mouton & co. Gravenhage, The Netherlands 1960.
[10] 苏剑波、徐波，《应用模式识别技术导论》，上海交通大学出版社，2001。
[11] 董长虹、赖志国、余啸海，《Matlab图像处理与应用》国防工业出版社。，
[12] 黄贤武、仲兴荣、王加俊，基于WT／PCA的自适应神经网络人脸识别方法，计算机应用，Vol．23．No．6，June，2003．
[13] Turk M, Pentland A. Face processing: models for recognition. In: Proceedings of SPIE, 1989,1192: 22-32
[14] Turk M, Pentland A. Recognition in face space. In: Proceedings of SPIE, 1990, 1381: 43-54.
[15] 高秀梅，李淑琴，杨静宇，一种广义的K—L变换与人脸识别，青岛化工学院报，2003，23(3)，270-272
[16] Jian Yang, David Zhang, Senior Member, Tow-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition, IEEE, Trans. Pattern Analysis and Machine Intelligence, 2004, 26(1), 131-137.
[17] D.Q.Zhang, S.C.Chen, and J. Liu, representing image matrices: Eigenimages vs. Eigenvectors, Proceedings of the 2nd International Symposium on Neural Networks (ISNN'05), Chongqing, China, 2005, 2, 659-664.
[18] 孙涛，谷士文，费耀平，基于PCA算法的人脸识别方法研究比较，现代电子技术 2007，1，240
[19] 张翠平，苏光大。人脸识别技术综述。中国图像图形学报。2000，5(11)：885-894。
[20] Lien J J, Alochower A, Cohn J F, et al. Automated facial expression recognition. In: proc of the third IEEE International Conference on Automatic Face and Gesture-Recognition. Nara, Japan. 1998, 390-395
[21] Liu X M, Chen T, Kumar B K V. Face authentication for multiple subjects using eigenflow. Pattern Recognition. 2003, 36(2):313-328
[22] 孙涛，谷士文，费耀平，基于PCA算法的人脸识别方法研究比较。现代电子技术 2007(1)：113。
[23] 山世光，人脸识别中若干关键问题的研究：(博士论文)。北京：中国科学院计算机研究所，2004。
[24] 边肇其，张学工，模式识别，2版，北京：清化大学出版社，2000
[25] Ranganath S and Arun K. Face recognition using transform features and neural networks. Pattern Recognition, 1997, 30(10):1615-1622.
[26] 周涛，基于PCA的人脸识别研究：(硕士论文)。南京：南京理工大学，2004。
[27] Yambor W, Draper B, and Beveridge J.R., Analysis of PCA-based Face Recognition Algorithms: Eigenvector Selection and Distance Measures. Second Workshop on Empirical Evaluation Methods in Computer vision, 2000
[28] 陈海勇，基于子空间的人脸识别技术：(硕士论文)。南京：南京理工大学，2006
[29] Wendy S. Yambor, Analysis of PCA-Based and Fisher Discriminant-Based Image Recognition Algorithms, Computer Science Technical Report, Colorado State University, 2000
[30] Yambor.W. Draper.B, Beveridge J.R. Analysis of PCA-based Face Recognition Algorithms: Eigenvector Selection and Distance Measures. Second Workshop on Empirical Evaluation Methods in Computer Vision, 2000
[31] Barjkiran Gottumukkal, Vijayan K Asari. An improved face recognition technique based on modular PCA approach. Pattern Recognition Letters. 2004, 25(4): 429-436
[32] 陈伏兵，高秀梅，张生亮，杨静宇，基于分块PCA的人脸识别方法，小型微型计算机系统，2006(10) Vol．27，No．10，1944-1945
[33] Moon H. and Phillips J. Analysis of PCA-based on Faced Recognition Algorithms. In Boyer K and Phillips J., Editors, Empirical Evaluation Techniques In Computer Vision, IEEE Computer Society Press, Los Alamitos, CA 1998.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |