基于语义特征的人脸特征提取方法的研究
|
摘要
随着信息化技术、计算机技术、网络技术的迅速发展,可视化的人脸图像资源将变得越来越多。建立快速高效的人脸图像检索机制,己经成为电子信息领域内亟待解决的问题。本课题确定基于语义特征的人脸特征提取方法的研究,将运用数字图像处理技术、人脸模式识别技术与传统的数据库检索技术,融合基于文本的图像检索和基于内容的图像检索两者技术优势为一体,避开在图像之间进行的繁琐匹配处理过程。首先,采取基于结构的方法,用肤色自适应的方法从输入图像中自动找出人脸位置;其次,再利用原灰度图积分投影方法将面部主要器官从人脸图像中自动分割出来;然后,通过对面部器官的几何特征点检测来设定不同的面部器官特征参数,并按照这些特征参数的取值范围进行数据分类处理并转化为形象化的语义描述;最后,将这些形象化的语义描述组合在一起表示人脸,并设计一个语义人脸图像检索系统,通过语义数据库检索出一定量的相似人脸图像,从而实现快速准确的检索目的。以200人为待测样本进行检索实验,正确检索出来的为155人,完全匹配的为125人,系统的识别率为75.55%,平均检索时间<0.1s。实验证明,这种算法具有很强的鲁棒性,使用此方法所建立的语义人脸图像检索系统,具有快速、高效、实用的特点。
With the rapid development of information technology,computer technology and network technology,visual face images resources will become more and more.Establishing a rapid and efficient mechanism for face image retrieval has become urgent problem in electronic information field.My paper determine the research of face features extraction methods based on semantic features.It will use digital image processing technology,facial recognition technology and traditional database retrieval techniques,fusing the advantages of text-based image retrieval and content-based image retrieval to avoid the tedious process of matching face image.First of all,structure-based methods,I use adaptive color mapping method from the input images automatically identify the location of face;secondly,use the original gray image integral projection method will pick up major face organs from the face images automatically;then the geometric characteristics of the face detection organ to set different facial organs parameters,in accordance with these range of parameters for data classification and translated into visualization of the semantic description;Finally,the visualization of the semantic description compose a face together and design a semantic face image retrieval system which can fast search through semantic database to retrieve a certain amount of similar face images. In order to achieve fast and accurate retrieval purposes.With 200 human being tested samples retrieval experiment,correct retrieved is 155,exactly match is 125,system recognition rate is 75.55%,average retrieval time < 0.1s. Experimental results show that the algorithm has strong robustness,use this method to establish the semantic face image retrieval system with fast,efficient and practical character.
With the rapid development of information technology,computer technology and network technology,visual face images resources will become more and more.Establishing a rapid and efficient mechanism for face image retrieval has become urgent problem in electronic information field.My paper determine the research of face features extraction methods based on semantic features.It will use digital image processing technology,facial recognition technology and traditional database retrieval techniques,fusing the advantages of text-based image retrieval and content-based image retrieval to avoid the tedious process of matching face image.First of all,structure-based methods,I use adaptive color mapping method from the input images automatically identify the location of face;secondly,use the original gray image integral projection method will pick up major face organs from the face images automatically;then the geometric characteristics of the face detection organ to set different facial organs parameters,in accordance with these range of parameters for data classification and translated into visualization of the semantic description;Finally,the visualization of the semantic description compose a face together and design a semantic face image retrieval system which can fast search through semantic database to retrieve a certain amount of similar face images. In order to achieve fast and accurate retrieval purposes.With 200 human being tested samples retrieval experiment,correct retrieved is 155,exactly match is 125,system recognition rate is 75.55%,average retrieval time < 0.1s. Experimental results show that the algorithm has strong robustness,use this method to establish the semantic face image retrieval system with fast,efficient and practical character.
引文
[1]祝秀萍,吴学毅,刘文峰.人脸识别综述与展望[J].计算机与信息技术,2008(4):53-55.
[2]王伟,马建光.人脸识别常用方法及其发展现状[J].兵工自动化,2002,21(1):49-51.
[3]陈鹏.人脸特征提取方法的研究[J].中国水运,2006,4(12):106-108.
[4]肖小玲.基于概率支持向量机方法的人脸识别[J].武汉理工大学学报,2009,33(2):1.
[5]曾阳艳.基于PCA方法的人脸特征提取和检测[J].电脑知识与技术,2008(4):742-744.
[6]雷松泽.基于主元分析的人脸特征提取MATLAB实现[J].电脑开发与应用,2006(11):20-21.
[7]丁宝亮.人脸特征建模中特征点的提取[J].科技创新导报,2008(13):11-12.
[8]魏冬冬,谌海新.人脸特征提取与识别技术研究[J].计算机与现代化2007(3):69-76.
[9]刘威.静态场景下人脸的检测与识别[D].中国科学院自动化研究所,2004:1-10.
[10]高建坡.视频序列中的人脸检测与跟踪算法研究[D].东南大学,2007:1.
[11]宗欣露.基于AdaBoost算法的人脸检测方法的研究[D].武汉理工大学,2006:1-7.
[12]沈锐.基于PCA的整体与局部特征融合的人脸识别方法[D].武汉理工大学,2008:1-15.
[13]左旭辉.基于多尺度分析的三维人脸识别[J].计算机应用研究,2009,26(8):3161-3162.
[14]Ji-Liu Z.Research of automatic recognition system for human faces[Master Dissertation].Beijing:Qinghua University 1988.
[15]HuiP,etal.Research of automatic recognition based on K-L transform.Journal of Qinghua University(Science and Technology),1997,37(1):67-70.
[16]Hua W,Jie-GuL.Feature extraction and restoration of the slant facial image.Journal of Shanghai Jiaotong University,1997,31(1):101-104.
[17]Hui Z,Hong-Xiang Z,Zhen-Ya H.Face image feature extraction and recognition based on principal component analysis neural networks.Pattern Recognition and Artificial Intelligence, 1996,9(1):52-57.
[18]张永梅.基于融合的人脸识别方法研究[D].中北大学,2005:1-18.
[19]胡占奇,刘洪玮.基于小波分析和几何特征的人脸识别方法研究[J].信息化纵横,2009(15):21-24.
[20]张红.基于支持向量机的目标图像识别技术[J].微电子学与计算机,2006,23(7):102-104.
[21]Parke F I, J.Brignell.Computer Generated Animation of Faces.Proceedings ACM an Conference,1972,1:451-57.
[22]Goldstion R J,Harmon L D,Lesk A B.Man-machine interaction in human face identification.Bell System Tech Journal,1972,51:399-027.
[23]Kaya Y,Kobayashi K.An Basic Study on Human Recognition.In Frontiers of Pattern Recognition,NewYork:Academic,1971,265-289.
[24]Kanad T.Picture processing system by computer and recognition of human face[PhD Dissertation].Kyoto:Kyoto University,1973
[25]智爱娟,智西湖.基于小波分析和MATLAB的人脸特征提取[J].洛阳师范学院学报,2007(5):91-92.
[26]马晓普,梁晶晶.基于支持向量机的人脸融合特征提取方法[J].南阳师范学院学报,2008,7(12):69-71.
[27]肖发远.证件照片的脸部对象分割与检索研究[D].上海大学,2005:1-9.
[28]朱秋煜.证件照片的特征提取与检索[J].模式识别与人工智能,2007,20(4):545-550.
[29]王成波,李勇平,王琳,张鸿洲.SVM与归一化方法结合的人脸和指纹融合识别[J].微计算机信息,2009,25(2):235-236.
[30]李慎笃,季桂树,黄卫华.基于小波变换的人脸边缘特征提取的研究[J].科技广场,2008(10):101-104.
[31]王敏,李汉强.基于小波变换和奇异值的人脸特征提取[J].中国水运,2006,4(3):163-164.
[32]Ian L.Dryden, Christopher J.Brignell;Linlin Shen.Factored principal component analysis, with applications to face recognition[J].Statistics and Computing,2009,19(3):229-238.
[33]Giuseppina Rametti;Carme Junqué;Pere Vendrell;Rosa Catalán;Rafael Penadés;Nuria Bargalló;Miguel Bernardo. Hippocampal underactivation in an fMRI study of word and face memory recognition in schizophrenia[J].European Archives of Psychiatry and Clinical Neuroscience,2009,259(4):203-211.
[34]Alexander Bronstein;Michael Bronstein and Ron Kimmel.Three dimensional Face Recognition[J].Monographs in Computer Science,2009:1-15.
[35]Pascual Ejarque and Javier Hernando. Score Equalization in SVM Multimodal Fusion for Person Recognition[J].Communications in Computer and Information Science,2009(23):152-161.
[36]Ioanna-Ourania Stathopoulou and George A.Tsihrintzis.Recent Developments in Automated Inferencing of Emotional State from Face Images[J].Communications in Computer and Information Science,2009(22):310-319.
[37]Messaoud Bengherabi;Lamia Mezai;Farid Harizi;AbderrazakGuessoum and Mohamed Cheriet.Application of 2DPCA Based Techniques in DCT Domain for Face Recognition[J]. Advances in Soft Computing,2009(5):243-250.
[38]Szu-Chen Stan Jou and Tanja Schultz.Automatic Speech Recognition Based on Electromyo graphic Biosignals[J].Communications in Computer and Information Science,2009(25):305-320.
[39]徐静云.复杂背景下人脸检测与识别技术研究[D].山东理工大学,2007:1-4.
[40]姬光荣,曲翠璐,赵文仓,廖向东.基于分块分形编码的多姿态、表情人脸图像检索[J].中国海洋大学学报,2004,34(5):1.
[41]靳红卫.基于肤色和结构特征的人脸检测技术研究与实现[D].国防科学技术大学,2007:1-5.
[42]杨之光,艾海舟.基于聚类的人脸图像检索及相关反馈[J].自动化学报,2008,34(9):1.
[43]毋立芳.基于人脸对象的图像检索关键技术研究[D].北京工业大学,2003:1-18.
[44]袁芬萍.基于人眼定位与SVM的人脸检测方法研究[D].中南大学,2007:1-6.
[45]吴冬升.基于压缩域和语义级的图像检索[D].东南大学,2003:86-102.
[46]任小龙,苏光大,相燕.使用第2代身份证的人脸识别身份认证系统[J].智能系统学报,2009,4(3):213-216.
[47]牛盼盼,王向阳,周璐,杨红颖.基于多语义特征的彩色图像检索技术研究[J].计算机科学,2009,36(3):226-230.
[48]周璐.基于高级语义特征的图像检索技术研究[D].辽宁师范大学,2008:1-12.
[49]王鹏辉.结合语义特征的图像检索方法研究[D].兰州理工大学,2008:1-4.
[50]Rafael Espí;Francisco A.Pujol;Higinio Mora and Jerónimo Mora.Development of a Distributed Facial Recognition System Based on Graph-Matching[J].Advances in Soft Computing,2009(50):498-502.
[51]M. Rychlik;W. Stankiewicz. Method of Numerical Analysis of Similarity and Differences of Face Shape of Twins[J].IFMBE Proceeding,2009(23):1854-1857.
[52]Shaiq A.Haq.Keynote Speech:Computer Vision:Object Recognition and Scene Interpretation[J].Communications in Computer and Information Science,2009(20).
[53]Marco Grassi;Marcos Faundez-Zanuy and Francesco Piazza.Face Localization in 2D Frontal Face Images Using Luminosity Profiles Analysis[J].Lecture Notes in Computer Science,2009(5398):340-346.
[54]N.I.Glumov;A.V.Koryakin;E.V.Myasnikov; A.P.Chikhonadskikh and I.Yu.Terent’eva. Program and research system for the recognition of individuals by photos of faces on documents[J].Pattern Recognition and Image Analysis,2009,19(1):43-47.
[55]E.V.Myasnikov.Investigation of methods of estimating geometrical misalignment in face images[J].Pattern Recognition and Image Analysis,2009,19(1):176-180.
[56]V.K.De Wansa Wickramaratne; and A.P.Vinogradov.Analysis of a 3D face-scanning system by active triangulation[J].Pattern Recognition and Image Analysis,2009,19(1):78-83.
[57]Faja S;Webb SJ;Merkle K;Aylward E;Dawson G.Brief report:face configuration accuracy and processing speed among adults with high-functioning autism spectrum disorders[J].Autism Dev Disord,2009,39(3):532-538. ??
[2]王伟,马建光.人脸识别常用方法及其发展现状[J].兵工自动化,2002,21(1):49-51.
[3]陈鹏.人脸特征提取方法的研究[J].中国水运,2006,4(12):106-108.
[4]肖小玲.基于概率支持向量机方法的人脸识别[J].武汉理工大学学报,2009,33(2):1.
[5]曾阳艳.基于PCA方法的人脸特征提取和检测[J].电脑知识与技术,2008(4):742-744.
[6]雷松泽.基于主元分析的人脸特征提取MATLAB实现[J].电脑开发与应用,2006(11):20-21.
[7]丁宝亮.人脸特征建模中特征点的提取[J].科技创新导报,2008(13):11-12.
[8]魏冬冬,谌海新.人脸特征提取与识别技术研究[J].计算机与现代化2007(3):69-76.
[9]刘威.静态场景下人脸的检测与识别[D].中国科学院自动化研究所,2004:1-10.
[10]高建坡.视频序列中的人脸检测与跟踪算法研究[D].东南大学,2007:1.
[11]宗欣露.基于AdaBoost算法的人脸检测方法的研究[D].武汉理工大学,2006:1-7.
[12]沈锐.基于PCA的整体与局部特征融合的人脸识别方法[D].武汉理工大学,2008:1-15.
[13]左旭辉.基于多尺度分析的三维人脸识别[J].计算机应用研究,2009,26(8):3161-3162.
[14]Ji-Liu Z.Research of automatic recognition system for human faces[Master Dissertation].Beijing:Qinghua University 1988.
[15]HuiP,etal.Research of automatic recognition based on K-L transform.Journal of Qinghua University(Science and Technology),1997,37(1):67-70.
[16]Hua W,Jie-GuL.Feature extraction and restoration of the slant facial image.Journal of Shanghai Jiaotong University,1997,31(1):101-104.
[17]Hui Z,Hong-Xiang Z,Zhen-Ya H.Face image feature extraction and recognition based on principal component analysis neural networks.Pattern Recognition and Artificial Intelligence, 1996,9(1):52-57.
[18]张永梅.基于融合的人脸识别方法研究[D].中北大学,2005:1-18.
[19]胡占奇,刘洪玮.基于小波分析和几何特征的人脸识别方法研究[J].信息化纵横,2009(15):21-24.
[20]张红.基于支持向量机的目标图像识别技术[J].微电子学与计算机,2006,23(7):102-104.
[21]Parke F I, J.Brignell.Computer Generated Animation of Faces.Proceedings ACM an Conference,1972,1:451-57.
[22]Goldstion R J,Harmon L D,Lesk A B.Man-machine interaction in human face identification.Bell System Tech Journal,1972,51:399-027.
[23]Kaya Y,Kobayashi K.An Basic Study on Human Recognition.In Frontiers of Pattern Recognition,NewYork:Academic,1971,265-289.
[24]Kanad T.Picture processing system by computer and recognition of human face[PhD Dissertation].Kyoto:Kyoto University,1973
[25]智爱娟,智西湖.基于小波分析和MATLAB的人脸特征提取[J].洛阳师范学院学报,2007(5):91-92.
[26]马晓普,梁晶晶.基于支持向量机的人脸融合特征提取方法[J].南阳师范学院学报,2008,7(12):69-71.
[27]肖发远.证件照片的脸部对象分割与检索研究[D].上海大学,2005:1-9.
[28]朱秋煜.证件照片的特征提取与检索[J].模式识别与人工智能,2007,20(4):545-550.
[29]王成波,李勇平,王琳,张鸿洲.SVM与归一化方法结合的人脸和指纹融合识别[J].微计算机信息,2009,25(2):235-236.
[30]李慎笃,季桂树,黄卫华.基于小波变换的人脸边缘特征提取的研究[J].科技广场,2008(10):101-104.
[31]王敏,李汉强.基于小波变换和奇异值的人脸特征提取[J].中国水运,2006,4(3):163-164.
[32]Ian L.Dryden, Christopher J.Brignell;Linlin Shen.Factored principal component analysis, with applications to face recognition[J].Statistics and Computing,2009,19(3):229-238.
[33]Giuseppina Rametti;Carme Junqué;Pere Vendrell;Rosa Catalán;Rafael Penadés;Nuria Bargalló;Miguel Bernardo. Hippocampal underactivation in an fMRI study of word and face memory recognition in schizophrenia[J].European Archives of Psychiatry and Clinical Neuroscience,2009,259(4):203-211.
[34]Alexander Bronstein;Michael Bronstein and Ron Kimmel.Three dimensional Face Recognition[J].Monographs in Computer Science,2009:1-15.
[35]Pascual Ejarque and Javier Hernando. Score Equalization in SVM Multimodal Fusion for Person Recognition[J].Communications in Computer and Information Science,2009(23):152-161.
[36]Ioanna-Ourania Stathopoulou and George A.Tsihrintzis.Recent Developments in Automated Inferencing of Emotional State from Face Images[J].Communications in Computer and Information Science,2009(22):310-319.
[37]Messaoud Bengherabi;Lamia Mezai;Farid Harizi;AbderrazakGuessoum and Mohamed Cheriet.Application of 2DPCA Based Techniques in DCT Domain for Face Recognition[J]. Advances in Soft Computing,2009(5):243-250.
[38]Szu-Chen Stan Jou and Tanja Schultz.Automatic Speech Recognition Based on Electromyo graphic Biosignals[J].Communications in Computer and Information Science,2009(25):305-320.
[39]徐静云.复杂背景下人脸检测与识别技术研究[D].山东理工大学,2007:1-4.
[40]姬光荣,曲翠璐,赵文仓,廖向东.基于分块分形编码的多姿态、表情人脸图像检索[J].中国海洋大学学报,2004,34(5):1.
[41]靳红卫.基于肤色和结构特征的人脸检测技术研究与实现[D].国防科学技术大学,2007:1-5.
[42]杨之光,艾海舟.基于聚类的人脸图像检索及相关反馈[J].自动化学报,2008,34(9):1.
[43]毋立芳.基于人脸对象的图像检索关键技术研究[D].北京工业大学,2003:1-18.
[44]袁芬萍.基于人眼定位与SVM的人脸检测方法研究[D].中南大学,2007:1-6.
[45]吴冬升.基于压缩域和语义级的图像检索[D].东南大学,2003:86-102.
[46]任小龙,苏光大,相燕.使用第2代身份证的人脸识别身份认证系统[J].智能系统学报,2009,4(3):213-216.
[47]牛盼盼,王向阳,周璐,杨红颖.基于多语义特征的彩色图像检索技术研究[J].计算机科学,2009,36(3):226-230.
[48]周璐.基于高级语义特征的图像检索技术研究[D].辽宁师范大学,2008:1-12.
[49]王鹏辉.结合语义特征的图像检索方法研究[D].兰州理工大学,2008:1-4.
[50]Rafael Espí;Francisco A.Pujol;Higinio Mora and Jerónimo Mora.Development of a Distributed Facial Recognition System Based on Graph-Matching[J].Advances in Soft Computing,2009(50):498-502.
[51]M. Rychlik;W. Stankiewicz. Method of Numerical Analysis of Similarity and Differences of Face Shape of Twins[J].IFMBE Proceeding,2009(23):1854-1857.
[52]Shaiq A.Haq.Keynote Speech:Computer Vision:Object Recognition and Scene Interpretation[J].Communications in Computer and Information Science,2009(20).
[53]Marco Grassi;Marcos Faundez-Zanuy and Francesco Piazza.Face Localization in 2D Frontal Face Images Using Luminosity Profiles Analysis[J].Lecture Notes in Computer Science,2009(5398):340-346.
[54]N.I.Glumov;A.V.Koryakin;E.V.Myasnikov; A.P.Chikhonadskikh and I.Yu.Terent’eva. Program and research system for the recognition of individuals by photos of faces on documents[J].Pattern Recognition and Image Analysis,2009,19(1):43-47.
[55]E.V.Myasnikov.Investigation of methods of estimating geometrical misalignment in face images[J].Pattern Recognition and Image Analysis,2009,19(1):176-180.
[56]V.K.De Wansa Wickramaratne; and A.P.Vinogradov.Analysis of a 3D face-scanning system by active triangulation[J].Pattern Recognition and Image Analysis,2009,19(1):78-83.
[57]Faja S;Webb SJ;Merkle K;Aylward E;Dawson G.Brief report:face configuration accuracy and processing speed among adults with high-functioning autism spectrum disorders[J].Autism Dev Disord,2009,39(3):532-538. ??