基于局部纹理ASM模型的人脸表情识别.doc

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搜索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