人脸精确检测与多分辨率下识别方法研究
|
摘要
人脸检测与识别技术是生物特征鉴别技术中研究最多和最热门的技术之一,它已经在身份认证、安全检查、罪犯查询、人机交互等广泛领域得到了初步应用。
在人脸检测研究中,构建快速而精确的检测方法一直是该领域的研究热点;在人脸识别研究中,如何克服获取图像光线、表情、视角等变化的影响,提高识别率则是迫切需要研究的问题。针对这两个问题,本文以彩色和灰色正面人脸静态图像为研究对象,将模式识别理论和图像处理技术相结合,重点研究基于LVQ人工神经网络(ANN)的肤色像素检测和基于模板匹配的人脸精确检测方法,以及基于小波包分解(WPD)和(2D)2PCA的不同变化条件人脸图像的识别方法,为建立快速精确的人脸识别系统提供技术依据。
本文的主要研究工作如下:
(1)针对现有人脸检测系统检测精度和速度不平衡的问题,提出了一种基于LVQ ANN的肤色检测与基于模板匹配的精确人脸检测相结合的方法。该方法在获取肤色像素基础上,采用基于全局搜索的Mosaic方法预定位人脸区域。以CVL人脸库图像实验结果表明,LVQ ANN实现了较满意的肤色像素检测效果,又能提高检测速度;Mosaic方法成功地实现了人脸区域的预定位。
(2)为在预定位人脸区域中实现精确的人脸检测,采用一种基于模板匹配的人脸检测方法。该方法首先构建基于R分量的标准灰度人脸模板,然后以相关性系数为匹配准则,使用多尺寸人脸模板实现不同尺寸人脸的检测。实验结果表明,CVL人脸库中常态组、微笑组和大笑组的正确检测率分别为100%、100%和93.6%;与仅采用模板匹配法相比,检测速度从1870.6s/幅提高到208.4s/幅。
(3)为解决从图像小波包分解得到节点图像中选取显著节点困难的问题,提出了采用(2D)2 PCA和最邻近分类器测试所有节点图像的正确识别率(CRR),并依据识别率选取出“成功”节点图像的方法。
(4)为了有效组合“成功”节点的特征矩阵,提出了一种测量测试图像和库图像距离的方法。该方法以“成功”节点图像特征矩阵的加权距离和,做为测试图像和库图像的距离,既考虑了全局和局部特征,又考虑了不同节点图像的识别贡献率,人脸识别实验结果表明该测量方法有效地提高了识别率。
(5)针对变化人脸图像识别困难的问题,提出了一种基于WPD和(2D)2PCA的人脸识别方法。首先,对图像进行小波包分解,采用(2D)2PCA和最邻近分类器得到子节点的正确识别率,选取具有较大识别率的节点作为“成功”节点,然后,组合“成功”节点的特征矩阵,计算测试图像与库图像的距离,最后,采用最邻近分类器实现识别。
(6)以MATLAB 7.0为工具编程实现基于WPD和(2D)2PCA的人脸识别方法,并以CMU PIE、Yale和UMIST人脸库图像为测试对象,分别进行光照、表情和视角变化图像的识别性能实验,以原图像采用(2D)2PCA和最邻近分类器的识别率为对比标准,结果表明,本文方法在3个实验中的识别率均高于标准识别率,其中,光照变化时识别能力最好,最高识别率为98.795%;表情变化其次,最高为89.796%,视角变化最差,最高为36.047%。
(7)实验表明,距离尺度和小波函数的选取对多分辨率下节点的识别率有较大影响。L1在主体节点上的识别率高,而L2在细节节点上的识别率高;小波函数对不同条件图像识别效果也各不相同。因此,要根据图像变化条件选取节点、距离尺度和小波函数。由试验提出了如下选取规则:光照变化时,采用L1和Daubechies4下的A1、A2、H2、V2、HH2组合;表情变化时,采用L1和Haar下的A2。
(8)本文提出的方法在视角变化时效果并不理想,尚需研究并寻求其它特征提取方法。
The technology of face detection and recognition is one of the most widely investigated technologies in the filed of Biometric Identification, and it has been used in such areas as identity authentication, security check-up, criminal enquiry, human-computer interaction etc.
In regard to face detection, proposing a detection method with high speed and accuracy remains a research hot spot. As to face recognition, due to the great variations of illumination, expression, viewpoint, age, etc. of face images, obtaining high recognition rates under these conditions still is a difficult task and research focus point. With respect to these two problems, this dissertation takes colour and gray static frontal facial images as research objects, and studies face detection and recognition methods based on combination of pattern recognition theory and image processing technology. The main content includes skin pixel extraction method on the basis of LVQ artificial neural network, face detection method using template matching technology, and a novel face recognition method employing (2D)2PCA and WPD under varying illumination, expression and pose conditions. This research targets for providing technology supports for a high-speed and accurate face recognition system. The main contributions of this research include:
(1) In order to solve the problem that detection speed and accuracy of current face detection system is unbalanced, a method that extracts skin pixels using LVQ ANN and detects face based on template matching is proposed. Firstly, An LVQ ANN is used to extract skin pixels. Then, a Mosaic method is prompted to primarily locate the face region through searching within the whole image. Experiments on images from CVL indicate that the LVQ ANN gains satisfactory extraction accuracy as well as high speed, and the Mosaic method could successfully pre-locate the face region.
(2) A method using template matching is adopted to detect face in the pre-located face region. First of all, a gray standard face template is gained by using only R channel of RGB images.Then, face is detected in the pre-located face region using template matching by taking relativity coefficient as the matching rule. In the end,the location and size of this face are obtained. Experimental results of three testing sets ( normal, smile and big smile sets) from CVL database show that the adopted method obtains good detection accuracy as well as speed. In the concrete, it gains 100%,100% and 93.6% correct detection rates respectively. Meanwhile, its detection speed increases from 1870.6 second/image to 208.4 second/image comparied with only adopting template matching on the original image.
(3) To address the difficult problem of choosing remarkable plots from all plots gained via WPD on the original image, a method that selects“successful”plots according to the correct recognition rates (CRRs) of plots is proposed. These CRRs are obtained by combining (2D)2PCA with the nearest neighborhood classifier.
(4) Aiming at efficiently fusing the feature matrixes of“successful”plots, a distance measurement between testing image and database image is presented. The L1 or L2 distances between feature matrixes of selected“successful”plots of testing image and each database image are calculated, and then taking the weighted sum of these distances as final distance. This measurement preserves both the local and global features of image, meanwhile, it also takes the CRR contribution differences of different plots into consideration. Experimental results show this measurement improves recognition performance significantly.
(5) Viewing the difficulty to recognize face in images taken under different conditions, a novel recognition method employing WPD and (2D)2PCA is developed. Firstly, 20 plots are obtained via two-level WPD on the original image. Secondly, the CRRs of these plots are gained by (2D)2PCA and the nearest neighborhood classifier, and‘successful’plots are selected based on these CRRs. Thirdly, the distance between testing image and each database image is calcualted using the proposed distance measurement. Finally, the nearest neighborhood classifier is adopted for recognition on the basis of this distance.
(6) The proposed recognition mehod is accomplished by MATLAB 7.0 and images from CMU PIE, Yale or UMIST databases are selected to test the recognition improvement of the proposed method under different illumination, expressions and poses respectively. The performance of (2D)2PCA on the original image is defined as‘standard’method. As the experimental results suggest, the proposed method obtains better performance than‘standard’method under these three conditions. It performs best under different illumination whereas its performance decreases slightly under different expressions and is worst when poses change, and its highest CRRs are 98.795%, 89.796%, 36.047% respectively.
(7) Observed from experimental results, the choice of distance metric has a significant effect on face recognition. In general, L1 shows higher CRRs on approximation plots, whilst L2 performs better on detailed plots. Similarly, the filters also show different performances under three different conditions. Therefore, distance metrics and filters should be selected according to these conditions. In the concrete, L1, Daubechies4, and A1, A2, H2, V2, HH2 are recommended to form the proposed method under different illumination, and L1, Haar and A2 are recommended to form the proposed method under different expressions.
(8) The proposed method fails to gain satisfactory CRRs under different poses, and the highest record is 36.047%. Thus, it is necessary to seek other methods to extract facial features more efficiently.
在人脸检测研究中,构建快速而精确的检测方法一直是该领域的研究热点;在人脸识别研究中,如何克服获取图像光线、表情、视角等变化的影响,提高识别率则是迫切需要研究的问题。针对这两个问题,本文以彩色和灰色正面人脸静态图像为研究对象,将模式识别理论和图像处理技术相结合,重点研究基于LVQ人工神经网络(ANN)的肤色像素检测和基于模板匹配的人脸精确检测方法,以及基于小波包分解(WPD)和(2D)2PCA的不同变化条件人脸图像的识别方法,为建立快速精确的人脸识别系统提供技术依据。
本文的主要研究工作如下:
(1)针对现有人脸检测系统检测精度和速度不平衡的问题,提出了一种基于LVQ ANN的肤色检测与基于模板匹配的精确人脸检测相结合的方法。该方法在获取肤色像素基础上,采用基于全局搜索的Mosaic方法预定位人脸区域。以CVL人脸库图像实验结果表明,LVQ ANN实现了较满意的肤色像素检测效果,又能提高检测速度;Mosaic方法成功地实现了人脸区域的预定位。
(2)为在预定位人脸区域中实现精确的人脸检测,采用一种基于模板匹配的人脸检测方法。该方法首先构建基于R分量的标准灰度人脸模板,然后以相关性系数为匹配准则,使用多尺寸人脸模板实现不同尺寸人脸的检测。实验结果表明,CVL人脸库中常态组、微笑组和大笑组的正确检测率分别为100%、100%和93.6%;与仅采用模板匹配法相比,检测速度从1870.6s/幅提高到208.4s/幅。
(3)为解决从图像小波包分解得到节点图像中选取显著节点困难的问题,提出了采用(2D)2 PCA和最邻近分类器测试所有节点图像的正确识别率(CRR),并依据识别率选取出“成功”节点图像的方法。
(4)为了有效组合“成功”节点的特征矩阵,提出了一种测量测试图像和库图像距离的方法。该方法以“成功”节点图像特征矩阵的加权距离和,做为测试图像和库图像的距离,既考虑了全局和局部特征,又考虑了不同节点图像的识别贡献率,人脸识别实验结果表明该测量方法有效地提高了识别率。
(5)针对变化人脸图像识别困难的问题,提出了一种基于WPD和(2D)2PCA的人脸识别方法。首先,对图像进行小波包分解,采用(2D)2PCA和最邻近分类器得到子节点的正确识别率,选取具有较大识别率的节点作为“成功”节点,然后,组合“成功”节点的特征矩阵,计算测试图像与库图像的距离,最后,采用最邻近分类器实现识别。
(6)以MATLAB 7.0为工具编程实现基于WPD和(2D)2PCA的人脸识别方法,并以CMU PIE、Yale和UMIST人脸库图像为测试对象,分别进行光照、表情和视角变化图像的识别性能实验,以原图像采用(2D)2PCA和最邻近分类器的识别率为对比标准,结果表明,本文方法在3个实验中的识别率均高于标准识别率,其中,光照变化时识别能力最好,最高识别率为98.795%;表情变化其次,最高为89.796%,视角变化最差,最高为36.047%。
(7)实验表明,距离尺度和小波函数的选取对多分辨率下节点的识别率有较大影响。L1在主体节点上的识别率高,而L2在细节节点上的识别率高;小波函数对不同条件图像识别效果也各不相同。因此,要根据图像变化条件选取节点、距离尺度和小波函数。由试验提出了如下选取规则:光照变化时,采用L1和Daubechies4下的A1、A2、H2、V2、HH2组合;表情变化时,采用L1和Haar下的A2。
(8)本文提出的方法在视角变化时效果并不理想,尚需研究并寻求其它特征提取方法。
The technology of face detection and recognition is one of the most widely investigated technologies in the filed of Biometric Identification, and it has been used in such areas as identity authentication, security check-up, criminal enquiry, human-computer interaction etc.
In regard to face detection, proposing a detection method with high speed and accuracy remains a research hot spot. As to face recognition, due to the great variations of illumination, expression, viewpoint, age, etc. of face images, obtaining high recognition rates under these conditions still is a difficult task and research focus point. With respect to these two problems, this dissertation takes colour and gray static frontal facial images as research objects, and studies face detection and recognition methods based on combination of pattern recognition theory and image processing technology. The main content includes skin pixel extraction method on the basis of LVQ artificial neural network, face detection method using template matching technology, and a novel face recognition method employing (2D)2PCA and WPD under varying illumination, expression and pose conditions. This research targets for providing technology supports for a high-speed and accurate face recognition system. The main contributions of this research include:
(1) In order to solve the problem that detection speed and accuracy of current face detection system is unbalanced, a method that extracts skin pixels using LVQ ANN and detects face based on template matching is proposed. Firstly, An LVQ ANN is used to extract skin pixels. Then, a Mosaic method is prompted to primarily locate the face region through searching within the whole image. Experiments on images from CVL indicate that the LVQ ANN gains satisfactory extraction accuracy as well as high speed, and the Mosaic method could successfully pre-locate the face region.
(2) A method using template matching is adopted to detect face in the pre-located face region. First of all, a gray standard face template is gained by using only R channel of RGB images.Then, face is detected in the pre-located face region using template matching by taking relativity coefficient as the matching rule. In the end,the location and size of this face are obtained. Experimental results of three testing sets ( normal, smile and big smile sets) from CVL database show that the adopted method obtains good detection accuracy as well as speed. In the concrete, it gains 100%,100% and 93.6% correct detection rates respectively. Meanwhile, its detection speed increases from 1870.6 second/image to 208.4 second/image comparied with only adopting template matching on the original image.
(3) To address the difficult problem of choosing remarkable plots from all plots gained via WPD on the original image, a method that selects“successful”plots according to the correct recognition rates (CRRs) of plots is proposed. These CRRs are obtained by combining (2D)2PCA with the nearest neighborhood classifier.
(4) Aiming at efficiently fusing the feature matrixes of“successful”plots, a distance measurement between testing image and database image is presented. The L1 or L2 distances between feature matrixes of selected“successful”plots of testing image and each database image are calculated, and then taking the weighted sum of these distances as final distance. This measurement preserves both the local and global features of image, meanwhile, it also takes the CRR contribution differences of different plots into consideration. Experimental results show this measurement improves recognition performance significantly.
(5) Viewing the difficulty to recognize face in images taken under different conditions, a novel recognition method employing WPD and (2D)2PCA is developed. Firstly, 20 plots are obtained via two-level WPD on the original image. Secondly, the CRRs of these plots are gained by (2D)2PCA and the nearest neighborhood classifier, and‘successful’plots are selected based on these CRRs. Thirdly, the distance between testing image and each database image is calcualted using the proposed distance measurement. Finally, the nearest neighborhood classifier is adopted for recognition on the basis of this distance.
(6) The proposed recognition mehod is accomplished by MATLAB 7.0 and images from CMU PIE, Yale or UMIST databases are selected to test the recognition improvement of the proposed method under different illumination, expressions and poses respectively. The performance of (2D)2PCA on the original image is defined as‘standard’method. As the experimental results suggest, the proposed method obtains better performance than‘standard’method under these three conditions. It performs best under different illumination whereas its performance decreases slightly under different expressions and is worst when poses change, and its highest CRRs are 98.795%, 89.796%, 36.047% respectively.
(7) Observed from experimental results, the choice of distance metric has a significant effect on face recognition. In general, L1 shows higher CRRs on approximation plots, whilst L2 performs better on detailed plots. Similarly, the filters also show different performances under three different conditions. Therefore, distance metrics and filters should be selected according to these conditions. In the concrete, L1, Daubechies4, and A1, A2, H2, V2, HH2 are recommended to form the proposed method under different illumination, and L1, Haar and A2 are recommended to form the proposed method under different expressions.
(8) The proposed method fails to gain satisfactory CRRs under different poses, and the highest record is 36.047%. Thus, it is necessary to seek other methods to extract facial features more efficiently.
引文
[1] 周德龙. 人脸识别技术研究[D]. 西安:西北工业大学硕士学位论文,2000.
[2] 王文宁. 人脸的检测定位方法[D]. 济南:山东大学硕士学位论文,2005.
[3] 吕保华. 人脸特征定位方法研究[D]. 西安:西北工业大学硕士学位论文,2007.
[4] 王婷. 人脸识别与人眼定位方法研究[D]. 开封:河南大学硕士学位论文,2007.
[5] Databases. http://www.face-rec.org/databases.
[6] CVL Face Database. http://www.lrv.fri.uni-lj.si/facedb.html.
[7] PIE Database. http://www.ri.cmu.edu/projects/project_418.html.
[8] Yale Face Databases. http://cvc.yale.edu/projects/yalefaces/yalefaces.html.
[9] The UMIST Face Database. http://images.ee.umist.ac.uk/danny/database.html.
[10] 何婧. 基于肤色和模板匹配的人脸检测[D]. 天津:天津大学硕士学位论文,2006.
[11] 《电脑编程技巧与维护》杂志社. Visual C/C++编程精选集锦(数据库及图形图像分册)[M]. 北京:科学出版社,2003.
[12] 何东健,耿楠,张义宽. 数字图象处理[M]. 西安:西安电子科技大学出版社,2003.
[13] Vladimir Vezhnevets,Vassili Sazonov,Alla Andreeva. A Survey on Pixel-Based Skin Color Detection Techniques [J]. Proc. Graphicon-2003, 2003:85-92.
[14] P. Kakumanu, S. Makrogiannis, N. Bourbakis.A survey of skin-color modeling and detection methods [J]. Pattern Recognition, 2007, 40(3):1106-1122.
[15] Teerayoot Sawangsri, Vorapoj Patanavijit, Somchai Jitapunkul.Face Segmentation Using Novel Skin-Color Map and Morphological Technique [J]. Transactions On Engineering, Computing And Technology V2 December,2004:56-59.
[16] Melanie Po-Leen Ooi. Hardware Implementation for Face Detection on Xilinx Virtex-II FPGA using the Reversible Component Transformation Colour Space [J]. Proceedings of the Third IEEE International Workshop on Electronic Design, Test and Applications, 2006:41-46.
[17] M. Wimmer, B. Radig. Adaptive Skin Color Classificator [J]. Proc. of the first ICGST International Conference on Graphics, Vision and Image Processing GVIP-05, 2005:325-327.
[18] Duy Nguyen, David Halupka, Parham Aarabi, et al. Real-time face detection and lip feature extraction using Field Programmable Gate Arrays [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B, 2006, 36(4):902-912.
[19] Yuichi Hori, Kenji Shimizu, Yutaka Nakamura, et al. A Real-Time Multi Face Detection Technique Using Positive-Negative Lines-of-Face Template [J]. Proceedings of the 17th International Conference on Pattern Recognition, 2004.
[20] 马宇飞,白雪生,徐光佑等. 新闻视频中口播帧检测方法的研究[J]. 软件学报,2001, 12(3):377-381.
[21] M. Turk and A. Pentland. Eigenfaces for recognition [J]. Cognitive Neurosci, 1991, 3(1):71-86.
[22] 赵一甲. 基于主分量分析的BP神经网络人脸图像识别算法[J]. 人工智能及识别技术,2006:203-204.
[23] 沈谦,李树涛,伍君. 基于主分量分析和支持向量机的人脸检测[J]. 计算机与数字工程,2005,4:56-58.
[24] 王承明, 陶飞,王卫等. 基于主成分分析和神经网络的人脸检测新算法[J]. 青岛农业大学学报(自然科学版),2007,24(3):211-214.
[25] H. Rowley, S. Baluja, T. Kanade. Neural network-based face detection [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(1):23-28.
[26] Mohammad S.Sadri, Nasim Shams, Masih Rahmaty, et al. An FPGA Based Fast Face Detector [J]. Global Signal Processing Expo & Conference (GSPx), 2004.
[27] F.Smach, M.Atri, J.Mitéran and M.Abid. Design of a Neural Networks Classifier for Face Detection [J]. Journal of Computer Science, 2006:257-260.
[28] Stavros Paschalakis and Miroslaw Bober. A Low Cost FPGA System for High Speed Face Detection and Tracking [J]. Proc. of IEEE Int. Conf. on Field Programmable Technology, 2003:214-221.
[29] Y. Freund, R. E. Schapire. Experiments with a new boosting algorithm [J]. Proc of the 13th Conf on Machine Learning. Bari, Italy: Morgan Kaufmann, 1996:148-156.
[30] P. Viola, M. Jones. Rapid object detection using a boosted cascade of simple features [J]. IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, USA: IEEE Computer Society, 2001.
[31]武勃,黄畅,艾海舟等. 基于连续Adaboost 算法的多视角人脸检测[J]. 计算机研究与发展,2005,42(9):1612-1621.
[32] T. Theocharides, N. Vijaykrishnan and M. J. Irwin. A Parallel Architecture For Hardware Face Detection [J]. Proceedings of the 2006 Emerging VLSI Technologies and Architectures, 2006.
[33] Yu Wei, Xiong Bing, and Charayaphan Chareonsak. FPGA Implementation Of Adaboost Algorithm For Detection Of Face Biometrics [J]. 2004 IEEE International Workshop on Biomedical Circuits & Systems, 2004:s1.6-17-20.
[34] Phillip Ian Wilson, John Fernandez. Facial feature detection using Haar classifiers [J]. Journal of Computing Sciences in Colleges, 2006:127-133.
[35] 陈超,宋宇,任德昊. 层次型支持向量机人脸检测器[J]. 中国测试技术,2007,33(2):61-64.
[36] 郑逢德,杨友良. 支持向量机的人脸检测方法[J]. 信息技术,2007,8:78-80.
[37] 孙瑞霞. 人脸识别方法的研究与实现[D]. 杭州:浙江理工大学硕士学位论文,2007.
[38] A. Bronstein, M. Bronstein, R. Kimmel, and A. Spira. 3D face recognition without facial surface reconstruction [J]. In Proceedings of ECCV 2004, Prague, Czech Republic, 2004:11-14.
[39] 陈松.基于肤色的人脸检测与识别[D]. 成都:电子科技大学硕士学位论文,2007.
[40] Scholkopf B, Smola A, Müller K R. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation, 1998, 10:1299-1319.
[41] 杨琼,丁晓青. 对称主分量分析及其在人脸识别中的应用[J]. 计算机学报,2003,26(9):1146-1151.
[42] Rajkiran Gottumukkal, Vijayan K.Asari. An improved face recognition technique based on modular PCA approach [J]. Pattern Recognition Letters, 2004:429-436.
[43] Rajkiran Gottumukkal, Hau T.Ngo, Vijayan K.Asari. Multi-lane architecture for eigenface based real-time face recognition [J]. Microprocessors and Microsystems, 2006:216-224.
[44] A. Pavan Kumar, V. Kamakoti, Sukhendu Das. System-on-programmable-chip implementation for on-line face recognition [J]. Pattern Recognition, 2006.
[45] Stewart Bartlett Marian, Lades H.M, Sejnowski Terry J.Affiliation. Independent componentrepresentations for face recognition [J]. In Proc. SPIE Conf. on Human Vision and Electronic Imaging III, 1998, 3299:528-539.
[46] Jian Yang and Jing-yu Yang. Why can LDA be performed in PCA transformed space? [J]. PatternRecognition, 2003, 36:563-566.
[47] 郑宇杰,於东军,杨静宇等. 一种基于ICA和LDA组合的人脸识别新方法[J]. 计算机科学,2006,4:194-197.
[48] H. Kong, L. Wang, E. K. Teoh, et al. Generalized 2D principal component analysis for face image representation and recognition [J]. Neural Networks, 2005, 18:585-594.
[49] J. Yang, D. Zhang, A. F. Frangi, et al. Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1):131-137.
[50] D. Zhang and Z. H. Zhou. (2D)2PCA: two-directional two-dimensional PCA for efficient face representation and recognition [J]. Neurocomputing, 2005, 69:224-231.
[51] Takashi Morie, Teppei Nakano. A face/object recognition system using coarse region segmentation and dynamic-link matching [J]. SICE 2003 Annual Conference, 2004:177-180.
[52] Xiaoguang Li, Shawlti Areibi. A Hardware/Software Go-design Approach for Face Recognition [J]. ICM 2004 Proceedings. The 16th International Conference on Microelectronics, 2004:55-58.
[53] Nefian A Hayes M. Hidden Markov models for face recognition [J]. IEEE Intenrational Conference on Acoustics, Sp eech and Signals Processing [C]. Seattle, Washington, 1998, 5: 2721-2724.
[54] V. Pathangay and S. Das. Exploring the use of Selective Wavelet Subbands for PCA basedFace Recognition [J]. http://www.missionreach.org/AboutUs/NCIP%202005/CD/5-ALD/ALD.07.pdf, 2007-10-29.
[55] C. Garcia, G. Zikos and G. Tziritas. Wavelet packet analysis for face recognition [J]. Image and Vision Computing, 2000, 18:289-297.
[56] P.Nicholl, A. Amira and D. Bouchaffra. RH Perrott. Multiresolution Hybrid Approaches for Automated Face Recognition [J]. Second NASA/ESA Conference on Adaptive Hardware and Systems, 2007, 8:89-96.
[57] H. K. Ekenel and B. Sankur. Multiresolution face recognition [J]. Image and Vision Computing, 2005, 23:469-477.
[58] 吴清江,周晓彦,郑文明. 一种基于2D-DWT和2D-PCA的人脸识别方法[J]. 计算机应用,2006,26(9):2089-2091.
[59] Rein-Lien Hsu, Mohamed Abdel-Mottaleb and Anil K. Jain. Face Detection In Color Images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 696–706.
[60] Jure Kovac, Peter Peer and Franc Solina. Eliminating the Influence of Non-Standard Illumination from Images. Research Report, Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia, 2003.
[61] Stavros Paschalakis and Miroslaw Bober. A Low Cost FPGA System for High Speed Face Detection and Trackin [J]. Proc. of IEEE Int. Conf. on Field Programmable Technology, 2003:214-221.
[62] Taigun Lee, Sung-Kee Park and Mignon Park. An effective method for detecting facial features and face in human–robot interaction [J]. Information Sciences, 2006:3166-3189.
[63] Melanie Po-Leen Ooi. Hardware Implementation for Face Detection on Xilinx Virtex-II FPGA usingthe Reversible Component Transformation Colour Space [J]. Proceedings of the Third IEEE International Workshop on Electronic Design, Test and Applications, 2006:41-46.
[64] H. Rowley, S. Baluja and T. Kanade. Neural network-based face detection [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(1):23-28.
[65] Yu Wei, Xiong Bing and Charayaphan Chareonsak. FPGA Implementation Of Adaboost Algorithm For Detection-Of Face Biometrics [J]. 2004 IEEE International Workshop on Biomedical Circuits & Systems, 2004:s1.6-17-20.
[66] David A Brown, Ian Craw and Julian Lewthwaite. A SOM based approach to skin detection with application in real time systems [J]. In Proc.of the British Machine Vision Conference, 2001.
[67] 李锦东,张洪才,梁彦等. 基于学习矢量量化(LVQ)神经网络的雷达体制识别[J]. 火力与指挥控制,2006,31(9):30-33.
[68] Mohammad Ali Akbari and Masayuki Nakajima. A novel color region homogenization and its application in improving skin detection accuracy [J]. Proceedings of the 3rd international conference on Computer graphics and interactive techniques in Australasia and South East Asia, Dunedin, New Zealand, 2005:269-272.
[69] Erik V. Cuevas, Daniel Zaldivar and Raul Rojas. LVQ Color Segmentation Applied to Face Localization [J]. 2004 1st lntemational Conference on Electrical and Electronics Engineering, 2004:142-146.
[70] Hariadi, M. Harada and A. Aoki et al. An LVQ-based technique for human motion segmentation, Asia-Pacific Conference on Circuits and Systems, 2002, 2:171-176.
[71] 陈蕾,黄贤武,孙兵. 基于WT 和LVQ 网络的多姿态人脸识别[J]. 计算机工程,2006,32(21):47-49.
[72] 王路,张蕾,周彦军等. 基于LVQ神经网络的植物种类识别[J]. 吉林大学学报(理学版),2007,45(3):421-426.
[73] P. Kakumanu, S. Makrogiannis and N. Bourbakis. A survey of skin-color modeling and detection methods [J]. Pattern Recognition, 2007, 40(3):1106-1122.
[74] H. Rowley, S. Baluja and T. Kanade. Neural network-based face detection [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(1):23-28.
[75] 李强,张钹. 一种基于图像灰度的快速匹配算法[J]. 软件学报,2006,2:216-222.
[76] 马艳. 基于颜色和模板匹配的人脸检测方法[D]. 大连:大连理工大学硕士学位论文,2006.
[77] 胡昌华,张军波,夏军. 基于 Matlab 的系统分析与设计—小波分析[M]. 西安:西安电子科技大学出版社,2000.
[78] 王经民. 小波分析[M]. 陕西:西北农林科技大学出版社,2004.
[79] 赵静. 基于小波分析的自动人脸识别研究[D]. 南京:东南大学博士学位论文,2005.
[80] 李永在. 基于小波分析和主成分分析的人脸识别研究[D]. 济南:山东大学硕士学位论文,2007.
[81] 姚雪梅. 基于小波变换的局部 PCA 人脸识别研究[D]. 乌鲁木齐:新疆大学硕士学位论文,2006.
[82] D. B. Graham and N. M. Allinson. Characterizing Virtual Eigensignatures for General Purpose Face Recognition [J]. (in) Face Recognition: From Theory to Applications, NATO ASI Series F, Computer and Systems Sciences, 1998:446-456.
[83] T. Sim, S. Baker and M. Bsat. The CMU Pose, Illumination, and Expression Database [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(12):1615-1618.
[2] 王文宁. 人脸的检测定位方法[D]. 济南:山东大学硕士学位论文,2005.
[3] 吕保华. 人脸特征定位方法研究[D]. 西安:西北工业大学硕士学位论文,2007.
[4] 王婷. 人脸识别与人眼定位方法研究[D]. 开封:河南大学硕士学位论文,2007.
[5] Databases. http://www.face-rec.org/databases.
[6] CVL Face Database. http://www.lrv.fri.uni-lj.si/facedb.html.
[7] PIE Database. http://www.ri.cmu.edu/projects/project_418.html.
[8] Yale Face Databases. http://cvc.yale.edu/projects/yalefaces/yalefaces.html.
[9] The UMIST Face Database. http://images.ee.umist.ac.uk/danny/database.html.
[10] 何婧. 基于肤色和模板匹配的人脸检测[D]. 天津:天津大学硕士学位论文,2006.
[11] 《电脑编程技巧与维护》杂志社. Visual C/C++编程精选集锦(数据库及图形图像分册)[M]. 北京:科学出版社,2003.
[12] 何东健,耿楠,张义宽. 数字图象处理[M]. 西安:西安电子科技大学出版社,2003.
[13] Vladimir Vezhnevets,Vassili Sazonov,Alla Andreeva. A Survey on Pixel-Based Skin Color Detection Techniques [J]. Proc. Graphicon-2003, 2003:85-92.
[14] P. Kakumanu, S. Makrogiannis, N. Bourbakis.A survey of skin-color modeling and detection methods [J]. Pattern Recognition, 2007, 40(3):1106-1122.
[15] Teerayoot Sawangsri, Vorapoj Patanavijit, Somchai Jitapunkul.Face Segmentation Using Novel Skin-Color Map and Morphological Technique [J]. Transactions On Engineering, Computing And Technology V2 December,2004:56-59.
[16] Melanie Po-Leen Ooi. Hardware Implementation for Face Detection on Xilinx Virtex-II FPGA using the Reversible Component Transformation Colour Space [J]. Proceedings of the Third IEEE International Workshop on Electronic Design, Test and Applications, 2006:41-46.
[17] M. Wimmer, B. Radig. Adaptive Skin Color Classificator [J]. Proc. of the first ICGST International Conference on Graphics, Vision and Image Processing GVIP-05, 2005:325-327.
[18] Duy Nguyen, David Halupka, Parham Aarabi, et al. Real-time face detection and lip feature extraction using Field Programmable Gate Arrays [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B, 2006, 36(4):902-912.
[19] Yuichi Hori, Kenji Shimizu, Yutaka Nakamura, et al. A Real-Time Multi Face Detection Technique Using Positive-Negative Lines-of-Face Template [J]. Proceedings of the 17th International Conference on Pattern Recognition, 2004.
[20] 马宇飞,白雪生,徐光佑等. 新闻视频中口播帧检测方法的研究[J]. 软件学报,2001, 12(3):377-381.
[21] M. Turk and A. Pentland. Eigenfaces for recognition [J]. Cognitive Neurosci, 1991, 3(1):71-86.
[22] 赵一甲. 基于主分量分析的BP神经网络人脸图像识别算法[J]. 人工智能及识别技术,2006:203-204.
[23] 沈谦,李树涛,伍君. 基于主分量分析和支持向量机的人脸检测[J]. 计算机与数字工程,2005,4:56-58.
[24] 王承明, 陶飞,王卫等. 基于主成分分析和神经网络的人脸检测新算法[J]. 青岛农业大学学报(自然科学版),2007,24(3):211-214.
[25] H. Rowley, S. Baluja, T. Kanade. Neural network-based face detection [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(1):23-28.
[26] Mohammad S.Sadri, Nasim Shams, Masih Rahmaty, et al. An FPGA Based Fast Face Detector [J]. Global Signal Processing Expo & Conference (GSPx), 2004.
[27] F.Smach, M.Atri, J.Mitéran and M.Abid. Design of a Neural Networks Classifier for Face Detection [J]. Journal of Computer Science, 2006:257-260.
[28] Stavros Paschalakis and Miroslaw Bober. A Low Cost FPGA System for High Speed Face Detection and Tracking [J]. Proc. of IEEE Int. Conf. on Field Programmable Technology, 2003:214-221.
[29] Y. Freund, R. E. Schapire. Experiments with a new boosting algorithm [J]. Proc of the 13th Conf on Machine Learning. Bari, Italy: Morgan Kaufmann, 1996:148-156.
[30] P. Viola, M. Jones. Rapid object detection using a boosted cascade of simple features [J]. IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, USA: IEEE Computer Society, 2001.
[31]武勃,黄畅,艾海舟等. 基于连续Adaboost 算法的多视角人脸检测[J]. 计算机研究与发展,2005,42(9):1612-1621.
[32] T. Theocharides, N. Vijaykrishnan and M. J. Irwin. A Parallel Architecture For Hardware Face Detection [J]. Proceedings of the 2006 Emerging VLSI Technologies and Architectures, 2006.
[33] Yu Wei, Xiong Bing, and Charayaphan Chareonsak. FPGA Implementation Of Adaboost Algorithm For Detection Of Face Biometrics [J]. 2004 IEEE International Workshop on Biomedical Circuits & Systems, 2004:s1.6-17-20.
[34] Phillip Ian Wilson, John Fernandez. Facial feature detection using Haar classifiers [J]. Journal of Computing Sciences in Colleges, 2006:127-133.
[35] 陈超,宋宇,任德昊. 层次型支持向量机人脸检测器[J]. 中国测试技术,2007,33(2):61-64.
[36] 郑逢德,杨友良. 支持向量机的人脸检测方法[J]. 信息技术,2007,8:78-80.
[37] 孙瑞霞. 人脸识别方法的研究与实现[D]. 杭州:浙江理工大学硕士学位论文,2007.
[38] A. Bronstein, M. Bronstein, R. Kimmel, and A. Spira. 3D face recognition without facial surface reconstruction [J]. In Proceedings of ECCV 2004, Prague, Czech Republic, 2004:11-14.
[39] 陈松.基于肤色的人脸检测与识别[D]. 成都:电子科技大学硕士学位论文,2007.
[40] Scholkopf B, Smola A, Müller K R. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation, 1998, 10:1299-1319.
[41] 杨琼,丁晓青. 对称主分量分析及其在人脸识别中的应用[J]. 计算机学报,2003,26(9):1146-1151.
[42] Rajkiran Gottumukkal, Vijayan K.Asari. An improved face recognition technique based on modular PCA approach [J]. Pattern Recognition Letters, 2004:429-436.
[43] Rajkiran Gottumukkal, Hau T.Ngo, Vijayan K.Asari. Multi-lane architecture for eigenface based real-time face recognition [J]. Microprocessors and Microsystems, 2006:216-224.
[44] A. Pavan Kumar, V. Kamakoti, Sukhendu Das. System-on-programmable-chip implementation for on-line face recognition [J]. Pattern Recognition, 2006.
[45] Stewart Bartlett Marian, Lades H.M, Sejnowski Terry J.Affiliation. Independent componentrepresentations for face recognition [J]. In Proc. SPIE Conf. on Human Vision and Electronic Imaging III, 1998, 3299:528-539.
[46] Jian Yang and Jing-yu Yang. Why can LDA be performed in PCA transformed space? [J]. PatternRecognition, 2003, 36:563-566.
[47] 郑宇杰,於东军,杨静宇等. 一种基于ICA和LDA组合的人脸识别新方法[J]. 计算机科学,2006,4:194-197.
[48] H. Kong, L. Wang, E. K. Teoh, et al. Generalized 2D principal component analysis for face image representation and recognition [J]. Neural Networks, 2005, 18:585-594.
[49] J. Yang, D. Zhang, A. F. Frangi, et al. Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1):131-137.
[50] D. Zhang and Z. H. Zhou. (2D)2PCA: two-directional two-dimensional PCA for efficient face representation and recognition [J]. Neurocomputing, 2005, 69:224-231.
[51] Takashi Morie, Teppei Nakano. A face/object recognition system using coarse region segmentation and dynamic-link matching [J]. SICE 2003 Annual Conference, 2004:177-180.
[52] Xiaoguang Li, Shawlti Areibi. A Hardware/Software Go-design Approach for Face Recognition [J]. ICM 2004 Proceedings. The 16th International Conference on Microelectronics, 2004:55-58.
[53] Nefian A Hayes M. Hidden Markov models for face recognition [J]. IEEE Intenrational Conference on Acoustics, Sp eech and Signals Processing [C]. Seattle, Washington, 1998, 5: 2721-2724.
[54] V. Pathangay and S. Das. Exploring the use of Selective Wavelet Subbands for PCA basedFace Recognition [J]. http://www.missionreach.org/AboutUs/NCIP%202005/CD/5-ALD/ALD.07.pdf, 2007-10-29.
[55] C. Garcia, G. Zikos and G. Tziritas. Wavelet packet analysis for face recognition [J]. Image and Vision Computing, 2000, 18:289-297.
[56] P.Nicholl, A. Amira and D. Bouchaffra. RH Perrott. Multiresolution Hybrid Approaches for Automated Face Recognition [J]. Second NASA/ESA Conference on Adaptive Hardware and Systems, 2007, 8:89-96.
[57] H. K. Ekenel and B. Sankur. Multiresolution face recognition [J]. Image and Vision Computing, 2005, 23:469-477.
[58] 吴清江,周晓彦,郑文明. 一种基于2D-DWT和2D-PCA的人脸识别方法[J]. 计算机应用,2006,26(9):2089-2091.
[59] Rein-Lien Hsu, Mohamed Abdel-Mottaleb and Anil K. Jain. Face Detection In Color Images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 696–706.
[60] Jure Kovac, Peter Peer and Franc Solina. Eliminating the Influence of Non-Standard Illumination from Images. Research Report, Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia, 2003.
[61] Stavros Paschalakis and Miroslaw Bober. A Low Cost FPGA System for High Speed Face Detection and Trackin [J]. Proc. of IEEE Int. Conf. on Field Programmable Technology, 2003:214-221.
[62] Taigun Lee, Sung-Kee Park and Mignon Park. An effective method for detecting facial features and face in human–robot interaction [J]. Information Sciences, 2006:3166-3189.
[63] Melanie Po-Leen Ooi. Hardware Implementation for Face Detection on Xilinx Virtex-II FPGA usingthe Reversible Component Transformation Colour Space [J]. Proceedings of the Third IEEE International Workshop on Electronic Design, Test and Applications, 2006:41-46.
[64] H. Rowley, S. Baluja and T. Kanade. Neural network-based face detection [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(1):23-28.
[65] Yu Wei, Xiong Bing and Charayaphan Chareonsak. FPGA Implementation Of Adaboost Algorithm For Detection-Of Face Biometrics [J]. 2004 IEEE International Workshop on Biomedical Circuits & Systems, 2004:s1.6-17-20.
[66] David A Brown, Ian Craw and Julian Lewthwaite. A SOM based approach to skin detection with application in real time systems [J]. In Proc.of the British Machine Vision Conference, 2001.
[67] 李锦东,张洪才,梁彦等. 基于学习矢量量化(LVQ)神经网络的雷达体制识别[J]. 火力与指挥控制,2006,31(9):30-33.
[68] Mohammad Ali Akbari and Masayuki Nakajima. A novel color region homogenization and its application in improving skin detection accuracy [J]. Proceedings of the 3rd international conference on Computer graphics and interactive techniques in Australasia and South East Asia, Dunedin, New Zealand, 2005:269-272.
[69] Erik V. Cuevas, Daniel Zaldivar and Raul Rojas. LVQ Color Segmentation Applied to Face Localization [J]. 2004 1st lntemational Conference on Electrical and Electronics Engineering, 2004:142-146.
[70] Hariadi, M. Harada and A. Aoki et al. An LVQ-based technique for human motion segmentation, Asia-Pacific Conference on Circuits and Systems, 2002, 2:171-176.
[71] 陈蕾,黄贤武,孙兵. 基于WT 和LVQ 网络的多姿态人脸识别[J]. 计算机工程,2006,32(21):47-49.
[72] 王路,张蕾,周彦军等. 基于LVQ神经网络的植物种类识别[J]. 吉林大学学报(理学版),2007,45(3):421-426.
[73] P. Kakumanu, S. Makrogiannis and N. Bourbakis. A survey of skin-color modeling and detection methods [J]. Pattern Recognition, 2007, 40(3):1106-1122.
[74] H. Rowley, S. Baluja and T. Kanade. Neural network-based face detection [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20(1):23-28.
[75] 李强,张钹. 一种基于图像灰度的快速匹配算法[J]. 软件学报,2006,2:216-222.
[76] 马艳. 基于颜色和模板匹配的人脸检测方法[D]. 大连:大连理工大学硕士学位论文,2006.
[77] 胡昌华,张军波,夏军. 基于 Matlab 的系统分析与设计—小波分析[M]. 西安:西安电子科技大学出版社,2000.
[78] 王经民. 小波分析[M]. 陕西:西北农林科技大学出版社,2004.
[79] 赵静. 基于小波分析的自动人脸识别研究[D]. 南京:东南大学博士学位论文,2005.
[80] 李永在. 基于小波分析和主成分分析的人脸识别研究[D]. 济南:山东大学硕士学位论文,2007.
[81] 姚雪梅. 基于小波变换的局部 PCA 人脸识别研究[D]. 乌鲁木齐:新疆大学硕士学位论文,2006.
[82] D. B. Graham and N. M. Allinson. Characterizing Virtual Eigensignatures for General Purpose Face Recognition [J]. (in) Face Recognition: From Theory to Applications, NATO ASI Series F, Computer and Systems Sciences, 1998:446-456.
[83] T. Sim, S. Baker and M. Bsat. The CMU Pose, Illumination, and Expression Database [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(12):1615-1618.