【正文】 for i=round(.5*(r_min+r_max)):1:round(1/3*(r_maxr_min)+r_min) for j=round(.5*(c_max+c_min)):1:round(1/3*(c_maxc_min)+c_min) if(w(i,round(j))==0) flg=1。 break。 end end if(flg==1),break,end end w(i,j) if(w(i,j)==0) e1_x=j。e1_y=i。 %plot(j,i,39。*39。)%Note left eye flg=0。 for i=round(.5*(r_min+r_max)):1:round(1/3*(r_maxr_min)+r_min) for j=round(.5*(c_max+c_min)):round(*(c_maxc_min)+c_min) if(w(i,j)==0)flg=1。break。end end if(flg==1)break,end。 end w(i,j) e2_x=j。e2_y=i。 %plot(j,i,39。*39。)%Note right eye5 結(jié)束語本調(diào)研報告主要介紹國內(nèi)外在人臉檢測和識別方面的發(fā)展?fàn)顩r以及一些研究背景、人臉識別的特點(diǎn)及技術(shù)難點(diǎn)、人臉檢測和識別的基本方法，基本特征和算法介紹。重點(diǎn)介紹當(dāng)前人臉有哪些通用的特征提取算法，同時結(jié)合相應(yīng)特征有那些檢測和識別算法。還重點(diǎn)介紹了人臉檢測的特征提?。簹W式距離度量、KarhunenLoeve(KL)變換、奇異特征值分解和獨(dú)立分量分析（ICA）；人臉檢測算法：基于面部特征、基于統(tǒng)計和基于膚色模型；人臉識別算法：靜態(tài)圖片人臉識別、視頻圖像人臉識別和人臉模型人臉識別。最后還簡單介紹的一種人臉識別算法：隱馬爾可夫（HMM）模型。通過對這些算法的了解，使我從整體上對人臉檢測與識別有了一個充分的了解與認(rèn)識，同時是促進(jìn)了我對本文算法的實(shí)現(xiàn)。參考文獻(xiàn)[1] [J]，2008，8(89):3840[2] YANGM H. Detecting Faces in Images: A Survey [J], IEEE transactions on pattern analysis intelligence, 2002,24(1): 3458.[3] YANG G, HUANG T S. Human Face Detection in Complex Background [J]. Pattern Recognition,1996,2(1) :345350.[4] ZHANG Z, LI S Z, ZHANG H. Realtime multiview face detection[C]. In: Proceedings of Conference on Automatic Face and Gesture Recognition, Washington D C, USA ,200239。 149154.[5] ROWLEY H A, BALUJA S, KANADE T. Neural network2based human face detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1): 23[6] [D]：[博士學(xué)位論文]，北京；中國科學(xué)院，[7] 侯鯤,賈隆佳 等. [J]，2010(11):4344[8] BELHUMEURPN, D faces VS. Fisher faces: Recognition Using Class Specific Linear Projection[j].IEEE Trans .Pattern Analysis and Machine Intelligence, 1997, 19(7): 711720.[9] LADES M, VORBRUGGEN J C, J Buhmann, etal. Distortion Invariant Object Recognition inthe Dynamic Link Architecture[J].IEEE Trans. Comput,1993,1 (42): 300311.[10] WISK0TT L, FELLOWS J M, KRUKGER N, et al. Face Recognition by Elastic Bunch Graph Matching[J]. IEEE Trans, on Pattern. Anal. Mach. Intell. 1997, 1(19):775779.[11] DEMERS D, C0TTRELL G, W. Nonlinear Dimensionality Reduction[A]. Advances in Neural Information Processing Systems[C]. San Mateo, CA: Morgan Kaufmann, 1993. 580587.[12] LAWRENCE S,GILES C, L, TS0I AC,et al . Face Recognition : A ConvolutionalNeuralnetwork Approach [J]. IEEE Transactions on Neural Networks, 1997,8(1) :98113.[13] SAMARIA E. Face recognition using hidden markov models[D]. PhD thesis, University of Cambridge, 1994.[14] NEFIANA,V Embedded bayesian networks for face recognition[C]. Proceedings of IEEE International Conference on Multimedia. 2002. 133136.[15] KWANGI K,JIN H K, KEECHUL J. Face recognition using support vector machines with localcorrelation kernels[J]. International Journal of Pattern Recognition and ArtificialIntelligence, 2002,1 (16):97111.[16] PHILLIPSP. Support vector machines applied to face recognit, ion[J]. Advances in Neural Information Processing Systems, 1998,1 (4):803809. [17] Sung K K, Poggio T. Example Based Learning for View Based Human Face Detection[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2000,20(1):3951.[18] AdaBoost的快速人臉檢測算法若干問題研究[D].南京:南京理工大學(xué),2007[19] 江艷霞. 視頻人臉跟蹤識別算法研究[D].上海:上海交通大學(xué),2007 [20] IngSheen Hsieh,KuoChin Fan,Chiunhsiun Lin,A statistic approach to the detection of human faces in color nature scene,Pattern Recognition,2002,35(7):15831596.