基于几何和纹理特征的表情层级分类方法
|
摘要
针对表情识别,为提取对个体差异鲁棒性更强的特征,并有效利用特征自身分布特性,本文提出基于几何和纹理特征的表情层级分类方法.首先,构建基于中性脸相似度的几何特征提取方法,自动匹配样本相似中性脸,提取特征点比例系数几何特征;然后,利用充分矢量三角形提取纹理特征;最后,给出表情层级分类框架,在三个层级下分别利用提取特征判定表情类别.所提方法在JAFFE库和CK库上的实验结果表明,本文方法取得了比基于一般几何和纹理特征的识别方法更好的效果,证明了本文方法的有效性.
In order to strengthen the robustness of the extracted features for individual differences and use the distribution characteristics of the features more effectively,this paper presents a hierarchical classification method of expression based on geometric and texture features. Firstly,a geometric feature extract method is constructed based on the similarity of neutral expression,which automatically matches with the similar neutral expression images of sample images and extract geometric features based on feature points scale factor. Then,texture features are extracted by using sufficient vector triangle pattern. Finally,the facial expression hierarchical classification framework is achieved by using the above features to judge expression categories in the three layers respectively. Experiment results in JAFFE database and CK database showthat the proposed method improves the recognition rate compared with the methods based on the typically geometric and texture features.
In order to strengthen the robustness of the extracted features for individual differences and use the distribution characteristics of the features more effectively,this paper presents a hierarchical classification method of expression based on geometric and texture features. Firstly,a geometric feature extract method is constructed based on the similarity of neutral expression,which automatically matches with the similar neutral expression images of sample images and extract geometric features based on feature points scale factor. Then,texture features are extracted by using sufficient vector triangle pattern. Finally,the facial expression hierarchical classification framework is achieved by using the above features to judge expression categories in the three layers respectively. Experiment results in JAFFE database and CK database showthat the proposed method improves the recognition rate compared with the methods based on the typically geometric and texture features.
引文
[1]Eleftheriadis S,Rudovic O,Pantic M.Discriminative shared Gaussian processes for multiview and view-invariant facial expression recognition[J].IEEE Transactions on Image Processing,2015,24(1):189-204.
[2]Whitehill J,Serpell Z,Lin Yi-Ching,Foster A,Movellan J R.The face of engagement:automatic recognition of student engagement from facial expressions[J].IEEE Transactions on Affective Computing,2014,5(1):86-98.
[3]杨飞,苏剑波.人脸显性特征的融合构造方法及识别[J].电子学报,2012,40(3):466-471.Yang Fei,Su Jianbo.Face recognition based on explicit facial features by fusion construction method[J].Acta Electronica Sinica,2012,40(3):466-471.(in Chinese)
[4]Liu Haibin,Zhang Guobao,Huang Yongming,Dong Fei.M ultiple features extraction and coordination using Gabor w avelet transformation and fisherfaces w ith application to facial expression recognition[A].Proceedings of Chinese Conference on Pattern Recognition[C].Chongqing:IEEE Press,2010.1-5.
[5]Shan Caifeng,Gong Shaogang,Mc Owan Peter W.Robust facial expression recognition using local binary patterns[A].Proceedings of IEEE International Conference on Image Processing[C].USA:IEEE Press,2005.370-373.
[6]李根,李文辉.主方向旋转LBP特征的平面旋转人脸检测[J].电子学报,2015,43(1):198-202.Li Gen,Li Wenhui.Face detection under rotation in image plane using principal direction rotation LBP[J].Acta Electronica Sinica,2015,43(1):198-202.(in Chinese)
[7]夏海英.基于纹理和几何特征的表情分类研究[D].武汉:华中科技大学,2011.Xia Haiying.Research on Texture and Geometric Features for Facial Expression Recognition[D].Wuhan:Huazhong University of Science and Technology,2011.(in Chinese)
[8]Anwar Saeed,Ayoub Al-Hamadi,Robert Niese.The effectiveness of using geometrical features for facial expression recognition[A].Proceedings of IEEE International Conference on Cybernetics[C].USA:IEEE Press,2013.122-127.
[9]Song Mingli,Tao Dacheng,Liu Zicheng,Li Xuelong,Zhou M engchu.Image ratio features for facial expression recognition application[J].IEEE Transactions on Systems,M an,and Cybernetics,Part B:Cybernetics,2010,40(3):779-788.
[10]Parna Kundu,Ravindra Kumar Singh.Geometric feature based recognition of facial expressions using ANN[A].Proceedings of IEEE International Conference on Signal Processing[C].USA:IEEE Press,2013.1-6.
[11]易积政,毛峡,Ishizuka Mitsuru,薛雨丽.基于特征点矢量与纹理形变能量参数融合的人脸表情识别[J].电子与信息学报,2013,35(10):2403-2410.Yi Jizheng,M ao Xia,Ishizuka M itsuru,Xue Yuli.Facial expression recognition based on feature point vector and texture deformation energy parameters[J].Journal of Electronics&Information Technology,2013,35(10):2403-2410.(in Chinese)
[12]魏冉,姜莉,陶霖密.融合人脸多特征信息的表情识别系统[J].中国图象图形学报,2009,14(5):792-800.Wei Ran,Jiang Li,Tao Linmi.Facial expression recognition system based on multiple feature integration[J].Journal of Image and Graphics,2009,14(5):792-800.(in Chinese)
[13]刘帅师,田彦涛,万川.基于Gabor多方向特征融合与分块直方图的人脸表情识别[J].自动化学报,2011,37(12):1455-1463.Liu Shuaishi,Tian Yantao,Wan Chuan.Facial expression recognition method based on Gabor multi-orientation features fusion and block histogram[J].Acta Automatica Sinica,2011,37(12):1455-1463.(in Chinese)
[14]Zhang Zheng,Fang Chi,Ding Xiaoqing.A hierarchical algorithm w ith multi-feature fusion for facial expression recognition[A].Proceedings of the 21st International Conference on Pattern Recognition[C].USA:IEEE Press,2012.2363-2366.
[15]胡敏,江河,王晓华,陈红波,李堃,任福继.精确局部特征描述的表情识别[J].中国图象图形学报,2014,19(11):1613-1622.Hu M in,Jiang He,Wang Xiaohua,Chen Hongbo,Li Kun,Ren Fuji.Precise local feature description for facial expression recognition[J].Journal of Image and Graphics,2014,19(11):1613-1622.(in Chinese)
[16]Wang Hongcheng,Ahuja N.Facial expression decomposition[A].Proceedings of IEEE International Conference on Computer Vision[C].USA:IEEE Press,2003.958-965.
[17]谭华春,章毓晋.基于人脸相似度加权距离的非特定人表情识别[J].电子与信息学报,2007,29(2):455-459.Tan Huachun,Zhang Yujin.Person-independent facial expression recognition based on person-similarity w eighted distance[J].Journal of Electronics&Information Technology,2007,29(2):455-459.(in Chinese)
[18]Jiang He,Hu Min,Chen Hongbo,Li Kun,Wang Xiaohua,Ren Fuji.Fcial expression recognition based on multi-scale vector triangle[A].Proceedings of IEEE/SICE International Symposium on System Integration[C].USA:IEEE Press,2013.82-87.
[2]Whitehill J,Serpell Z,Lin Yi-Ching,Foster A,Movellan J R.The face of engagement:automatic recognition of student engagement from facial expressions[J].IEEE Transactions on Affective Computing,2014,5(1):86-98.
[3]杨飞,苏剑波.人脸显性特征的融合构造方法及识别[J].电子学报,2012,40(3):466-471.Yang Fei,Su Jianbo.Face recognition based on explicit facial features by fusion construction method[J].Acta Electronica Sinica,2012,40(3):466-471.(in Chinese)
[4]Liu Haibin,Zhang Guobao,Huang Yongming,Dong Fei.M ultiple features extraction and coordination using Gabor w avelet transformation and fisherfaces w ith application to facial expression recognition[A].Proceedings of Chinese Conference on Pattern Recognition[C].Chongqing:IEEE Press,2010.1-5.
[5]Shan Caifeng,Gong Shaogang,Mc Owan Peter W.Robust facial expression recognition using local binary patterns[A].Proceedings of IEEE International Conference on Image Processing[C].USA:IEEE Press,2005.370-373.
[6]李根,李文辉.主方向旋转LBP特征的平面旋转人脸检测[J].电子学报,2015,43(1):198-202.Li Gen,Li Wenhui.Face detection under rotation in image plane using principal direction rotation LBP[J].Acta Electronica Sinica,2015,43(1):198-202.(in Chinese)
[7]夏海英.基于纹理和几何特征的表情分类研究[D].武汉:华中科技大学,2011.Xia Haiying.Research on Texture and Geometric Features for Facial Expression Recognition[D].Wuhan:Huazhong University of Science and Technology,2011.(in Chinese)
[8]Anwar Saeed,Ayoub Al-Hamadi,Robert Niese.The effectiveness of using geometrical features for facial expression recognition[A].Proceedings of IEEE International Conference on Cybernetics[C].USA:IEEE Press,2013.122-127.
[9]Song Mingli,Tao Dacheng,Liu Zicheng,Li Xuelong,Zhou M engchu.Image ratio features for facial expression recognition application[J].IEEE Transactions on Systems,M an,and Cybernetics,Part B:Cybernetics,2010,40(3):779-788.
[10]Parna Kundu,Ravindra Kumar Singh.Geometric feature based recognition of facial expressions using ANN[A].Proceedings of IEEE International Conference on Signal Processing[C].USA:IEEE Press,2013.1-6.
[11]易积政,毛峡,Ishizuka Mitsuru,薛雨丽.基于特征点矢量与纹理形变能量参数融合的人脸表情识别[J].电子与信息学报,2013,35(10):2403-2410.Yi Jizheng,M ao Xia,Ishizuka M itsuru,Xue Yuli.Facial expression recognition based on feature point vector and texture deformation energy parameters[J].Journal of Electronics&Information Technology,2013,35(10):2403-2410.(in Chinese)
[12]魏冉,姜莉,陶霖密.融合人脸多特征信息的表情识别系统[J].中国图象图形学报,2009,14(5):792-800.Wei Ran,Jiang Li,Tao Linmi.Facial expression recognition system based on multiple feature integration[J].Journal of Image and Graphics,2009,14(5):792-800.(in Chinese)
[13]刘帅师,田彦涛,万川.基于Gabor多方向特征融合与分块直方图的人脸表情识别[J].自动化学报,2011,37(12):1455-1463.Liu Shuaishi,Tian Yantao,Wan Chuan.Facial expression recognition method based on Gabor multi-orientation features fusion and block histogram[J].Acta Automatica Sinica,2011,37(12):1455-1463.(in Chinese)
[14]Zhang Zheng,Fang Chi,Ding Xiaoqing.A hierarchical algorithm w ith multi-feature fusion for facial expression recognition[A].Proceedings of the 21st International Conference on Pattern Recognition[C].USA:IEEE Press,2012.2363-2366.
[15]胡敏,江河,王晓华,陈红波,李堃,任福继.精确局部特征描述的表情识别[J].中国图象图形学报,2014,19(11):1613-1622.Hu M in,Jiang He,Wang Xiaohua,Chen Hongbo,Li Kun,Ren Fuji.Precise local feature description for facial expression recognition[J].Journal of Image and Graphics,2014,19(11):1613-1622.(in Chinese)
[16]Wang Hongcheng,Ahuja N.Facial expression decomposition[A].Proceedings of IEEE International Conference on Computer Vision[C].USA:IEEE Press,2003.958-965.
[17]谭华春,章毓晋.基于人脸相似度加权距离的非特定人表情识别[J].电子与信息学报,2007,29(2):455-459.Tan Huachun,Zhang Yujin.Person-independent facial expression recognition based on person-similarity w eighted distance[J].Journal of Electronics&Information Technology,2007,29(2):455-459.(in Chinese)
[18]Jiang He,Hu Min,Chen Hongbo,Li Kun,Wang Xiaohua,Ren Fuji.Fcial expression recognition based on multi-scale vector triangle[A].Proceedings of IEEE/SICE International Symposium on System Integration[C].USA:IEEE Press,2013.82-87.