计算机应用研究
計算機應用研究
계산궤응용연구
Application Research of Computers
2015年
11期
3504-3507
,共4页
面部表情%Delaunay 三角剖分%差分纹理特征%主动形状模型
麵部錶情%Delaunay 三角剖分%差分紋理特徵%主動形狀模型
면부표정%Delaunay 삼각부분%차분문리특정%주동형상모형
facial expression%Delaunay triangulation%differential texture features%active shape model(ASM)
考虑到自动人脸表情识别背景复杂性问题，提出了一个新的表情识别方法———基于差分纹理的人脸表情识别，该方法在一定程度上能够有效地屏蔽掉个体人脸之间的差异，同时保留住人脸表情信息。首先选定一个标准人脸参考模型，该模型合理分布面部55个基准点，这些基准点主要分布于眼睛、鼻子、嘴和包含表情丰富的外部轮廓上；然后利用 Delaunay 三角剖分获取这些基准点的相对位置信息。对于人脸表情图像，首先利用主动形状模型（ASM）跟踪定位这55个基准点，然后利用三角剖分获得的相对位置信息，以及应用纹理映射技术将表情图像映射到标准人脸参考模型中，这样中性表情图像（不含表情信息的人脸）和非中性表情（六种基本表情）图像均被映射到同一大小的框架内，最后将它们的差值图像作为表情特征，称为 DT（differential texture，差分纹理）特征。最后分别将 JAFFE 人脸表情库和 CK 人脸表情库中的部分样本组成混合数据并进行实验，结果表明提出的方法对六种基本表情具有较好的识别率，并且该方法优于传统的 Gabor 特征和 LBP 特征方法，并能扩展到动态图像中的表情识别中去。
攷慮到自動人臉錶情識彆揹景複雜性問題，提齣瞭一箇新的錶情識彆方法———基于差分紋理的人臉錶情識彆，該方法在一定程度上能夠有效地屏蔽掉箇體人臉之間的差異，同時保留住人臉錶情信息。首先選定一箇標準人臉參攷模型，該模型閤理分佈麵部55箇基準點，這些基準點主要分佈于眼睛、鼻子、嘴和包含錶情豐富的外部輪廓上；然後利用 Delaunay 三角剖分穫取這些基準點的相對位置信息。對于人臉錶情圖像，首先利用主動形狀模型（ASM）跟蹤定位這55箇基準點，然後利用三角剖分穫得的相對位置信息，以及應用紋理映射技術將錶情圖像映射到標準人臉參攷模型中，這樣中性錶情圖像（不含錶情信息的人臉）和非中性錶情（六種基本錶情）圖像均被映射到同一大小的框架內，最後將它們的差值圖像作為錶情特徵，稱為 DT（differential texture，差分紋理）特徵。最後分彆將 JAFFE 人臉錶情庫和 CK 人臉錶情庫中的部分樣本組成混閤數據併進行實驗，結果錶明提齣的方法對六種基本錶情具有較好的識彆率，併且該方法優于傳統的 Gabor 特徵和 LBP 特徵方法，併能擴展到動態圖像中的錶情識彆中去。
고필도자동인검표정식별배경복잡성문제，제출료일개신적표정식별방법———기우차분문리적인검표정식별，해방법재일정정도상능구유효지병폐도개체인검지간적차이，동시보류주인검표정신식。수선선정일개표준인검삼고모형，해모형합리분포면부55개기준점，저사기준점주요분포우안정、비자、취화포함표정봉부적외부륜곽상；연후이용 Delaunay 삼각부분획취저사기준점적상대위치신식。대우인검표정도상，수선이용주동형상모형（ASM）근종정위저55개기준점，연후이용삼각부분획득적상대위치신식，이급응용문리영사기술장표정도상영사도표준인검삼고모형중，저양중성표정도상（불함표정신식적인검）화비중성표정（륙충기본표정）도상균피영사도동일대소적광가내，최후장타문적차치도상작위표정특정，칭위 DT（differential texture，차분문리）특정。최후분별장 JAFFE 인검표정고화 CK 인검표정고중적부분양본조성혼합수거병진행실험，결과표명제출적방법대륙충기본표정구유교호적식별솔，병차해방법우우전통적 Gabor 특정화 LBP 특정방법，병능확전도동태도상중적표정식별중거。
Considering the problem of automatically recognizing facial expression with complex background,this paper pro-posed a novel method,which could extract expression features regardless of face information.First,the method selected a standard reference model,in which 55 facial landmark points were reasonably distributed by geometric information of the face. Those landmark points mainly located at facial contour,eyebrows,eyes,nose and lips,which constituted the convex hull of face model.Then it deployed the Delaunay triangulation to get the relative location information of those points in the standard reference model.It got 55 landmark points by using ASMlocation for neutral expression and non-neutral expression,and ap-plied the relation location information and texture mapping technology to those expression images.After the above processes, all face images were mapped to a standard reference framework.The difference between neutral expression and non-neutral ex-pressions could be formed to one vector as facial expression features called DT features.In order to verify the effectiveness of the proposed method,it conducted 6 kinds of facial expression recognition experiments on JAFFE database and Cohn-Kanade database.The experiments show that this method has higher recognition rate for expression recognition.It also compared this method with other conventional feature extraction method,namely LBP (local binary pattern)features and Gabor features,the recognition rates show that this method outperforms these methods.This method can also be extended to facial expression rec-ognition of dynamic image sequences.
