基于局部纹理ASM模型的人脸表情识别.docVIP

基于局部纹理ASM模型的人脸表情识别 第6卷第3期 2011年6月 智能系统 CAMTransactionsonIntelligentSystems VoL6No.3 Jun.201l doi:10.3969/j.issn.1673-4785.2011.03.007 基于局部纹理ASM模型的人脸表情识别 彭程,刘帅师,;0-)11,田彦涛 (1.吉林大学通信工程学院,吉林长春130025;2.吉林大学工程仿生教育部重点实验室,吉林长春130025) 摘要:针对主动形状模型(ASM)迭代过程容易陷入局部最优解的不足,提出了一种基于局部纹理模型的改进ASM 算法,即EWASM.在局部纹理模型构建中,以每个特征点的中垂线方向有哪些信誉好的足球投注网站其邻域信息以确定最佳匹配位置,对衡 量匹配程度的马氏距离加以推广,进而得到改进的扩展加权局部纹理模型,它由中心局部纹理模型,前局部纹理模 型和后局部纹理模型共3个子模型加权组成,并对加权参数进行实验优化,使各个特征点之间的联系更加紧密,模 型的鲁棒性更好.通过表情识别实验对提出的EWASM算法和传统ASM算法进行对比,选用RBF神经网络分类器进 行表情分类,实验结果表明EWASM算法收敛速度更快,识别率也得以提高,并解决了局部最小问题,能更有效地表 征表情. 关键词:人脸表情识别;主动形状模型;局部纹理模型;RBF神经网络分类器 中图分类号:TP391文献标识码:A文章编号:1673-4785(2011)03-0231—08 Anactiveshapemodelforfacialexpressionrecognition basedonalocaltexturemodel PENGCheng,LIUShuaishi,WANChuan,TIANYantao,. (1.SchoolofCommunicationEngineering,JilinUniversity,Changchun130025,China;2.KeyLaboratoryofBionicEngineering(Ji一 1inUniversity),MinistryofEducation,Changchun130025,China) Abstract:Animprovedactiveshapemodel(ASM)calledEWASM(expandedweightedASM)basedonalocaltex- turemodelwasproposedbecauseEWASMovercomesthedisadvantagethattheactiveshapemodeliseasytoinvolve inlocaloptimalsolutionintheiterativeprocess.Inthelocaltexturemodel,searchingadjacentinformationofeach landmarkalongitsperpendicularbisectormadethematchpositionbest.ItimprovedandpromotedMahalanobisdis— tancewhichmeasuredthematchingdegree.Thenthelocaltexturemodelwasextendedtoincludethecenterlocal texturemodel,forwardlocaltexturemodel,andbackwardlocaltexturemode1.Afterthat,theweightedparameters wereoptimizedexperimentally.Thuseachlandmarkismorecloselyrelatedandthelocaltexturemodelismorero— bust.FinallyfacialexpressionrecognitionexperimentswereconductedcomparingEWASMwithclassicalASM,and aRBFneuralnetworkwasusedasaclassificationintheexpressionrecognition.ExperimentsshowthattheEWASM algorithmsolvedthelocalminimumproblemandachievedabetterconvergencerateandrecognitioneffect. Keywords:facialexpressionrecognition;activeshapemodel;localtexturemodel;RBFneuralnetworkclassifier 人脸表情不仅在人与人的交流中发挥