基于主动形状模型差分纹理和局部方向模式特征融合的人脸表情识别

doi:10.11772/j.issn.1001-9081.2015.03.783

计算机应用 ›› 2015, Vol. 35 ›› Issue (3): 783-786.DOI: 10.11772/j.issn.1001-9081.2015.03.783

基于主动形状模型差分纹理和局部方向模式特征融合的人脸表情识别

夏海英, 徐鲁辉

广西师范大学电子工程学院, 广西桂林 541004

收稿日期:2014-10-11 修回日期:2014-11-19 出版日期:2015-03-10 发布日期:2015-03-13
通讯作者: 徐鲁辉
作者简介:夏海英(1983-),女,山东聊城人,副教授,博士,主要研究方向:人脸表情识别、运动目标检测;徐鲁辉(1987-),男,山东济宁人,硕士研究生,主要研究方向:特征提取、模式识别
基金资助:
广西自然科学基金资助项目(2013GXNSFBA019278);广西高等学校科研项目(2013YB032);广西师范大学博士启动基金资助项目;药用资源化学与药物分子工程教育部重点实验室资助课题(CMEMR2014-B15);广西自动检测技术与仪器重点实验室基金资助项目(YQ14202)

Facial expression recognition based on feature fusion of active shape model differential texture and local directional pattern

XIA Haiying, XU Luhui

College of Electronic Engineering, Guangxi Normal University, Guilin Guangxi 541004, China

Received:2014-10-11 Revised:2014-11-19 Online:2015-03-10 Published:2015-03-13

摘要/Abstract

摘要：

针对人脸表情识别背景复杂性以及表情识别的鲁棒性问题,基于Dempster-Shafer(DS)证据理论,提出了一种融合主动形状模型(ASM)差分纹理特征和局部方向模式(LDP)特征的人脸表情识别方法。ASM差分纹理既能有效地屏蔽个体人脸之间的差异,又能保留人脸表情信息。LDP特征通过计算8个方向的边缘响应来对图像进行编码,因此具有很强的抗噪能力,能够捕捉人脸因表情而产生的细微变化。在DS证据理论融合时,针对不同的特征对表情的识别率,分别用不同的权重系数来计算概率分配值。通过对JAFFE和Cohn-Kanade混合数据库进行实验,表情识别的平均识别率为97.08%,比单特征LDP高出一个百分点,有效地提高了表情识别率和鲁棒性。

关键词: 主动形状模型, 差分纹理, 局部方向模式, DS证据理论

Abstract:

To solve the problem of complex background and robustness in facial expression recognition, a novel method for facial expression recognition was proposed, which combined Active Shape Model (ASM) differential texture features and Local Directional Pattern (LDP) features in decision-making level by Dempster-Shafer (DS) evidence theory. ASM differential texture features could shield the differences between individuals effectively. Meanwhile it could try to retain expression information. LDP is a robust feature descriptor, which computes the edge response values in different directions and used these to encode the image texture. So LDP features have strong anti-noise capability and can capture the subtle changes caused by facial expression. With the consideration of different expression recognition rates for different features, different weight coefficients were selected to calculate probability assignment value during the process of DS evidence fusion. By conducting the experiments on JAFFE database and Cohn-Kanade database, the average recognition of facial expression can reach to 97.08% and is 1% higher than the method using single LDP feature. The experimental results show that the recognition rate and the robustness of facial expression are promoted.

Key words: Active Shape Model (ASM), differential texture, Local Directional Pattern (LDP), Dempster-Shafer (DS) evidence theory

中图分类号:

TP391.413

夏海英, 徐鲁辉. 基于主动形状模型差分纹理和局部方向模式特征融合的人脸表情识别[J]. 计算机应用, 2015, 35(3): 783-786.

XIA Haiying, XU Luhui. Facial expression recognition based on feature fusion of active shape model differential texture and local directional pattern[J]. Journal of Computer Applications, 2015, 35(3): 783-786.

参考文献

[1] EKMAN P. Strong evidence for universals in facial expressions: a reply to Russell's mistaken critique[J]. Psychological Bulletin, 1994, 115(2): 268-287.
[2] MURTHY G R S, JADON R S. Effectiveness of eigenspaces for facial expressions recognition[J]. International Journal of Computer Theory and Engineering, 2009, 1(5): 638-642.
[3] LI M, YUAN B. A novel statistical linear discriminant analysis for image matrix: two-dimensional Fisherfaces[C]//Proceedings of the 7th International Conference on Signal Processing. Piscataway: IEEE, 2004:1419-1422.
[4] DEND H-B, JIN L-W, ZHEN L-X, et al. A new facial expression recognition method based on local Gabor filter bank and PCA plus LDA[J]. International Journal of Information Technology, 2005,11(11):86-96.
[5] SHAN C, GONG S, McOWAN P W. Facial expression recognition based on local binary patterns:a comprehensive study[J]. Image and Vision Computing, 2008,27(6):803-816.
[6] CAO Y, ZHENG W, ZHAO L, et al. Expression recognition using elastic graph matching[C]//Proceedings of the 1st International Conference on Affective Computing and Intelligent Interaction. Berlin: Springer, 2005:8-15.
[7] HOMMEL S, HANDMANN U. AAM based continuous facial expression recognition for face image sequences[C]//Proceedings of the 12th International Symposium on Computational Intelligence and Informatics. Piscataway: IEEE, 2011:189-194.
[8] MISTRY V J, GOYANIM M. A literature survey on facial expression recognition using global features[J]. International Journal of Engineering and Advanced Technology, 2013,2(4):653-657.
[9] SHARMA A, DUBEY A. Facial expression recognition using virtual neutral image synthesis[EB/OL].[2014-08-07]. http://www.cs.umd.edu/~bhokaal/files/documents/Virtual%20expression.pdf.
[10] KOUTLAS A, FOTIADIS D. An automatic region based methodology for facial expression recognition[C]//Proceedings of the 2008 IEEE International Conference on Systems, Man and Cybernetics. Piscataway: IEEE, 2008:662-666.
[11] JABID T, KABIR M H, CHAE O. Local Directional Pattern (LDP)-a robust image descriptor for object recognition[C]//Proceedings of the 7th IEEE International Conference on Advanced Video and Signal Based Surveillance. Piscataway: IEEE, 2010:482-487.
[12] JABID T, KABIR M H, CHAE O. Local Directional Pattern (LDP) for face recognition[C]//Proceeding of Digest of Technical Papers International Conference on Consumer Electronics. Piscataway: IEEE, 2010:329-330.
[13] JABID T, KABIR M H, CHAE O. Facial expression recognition using Local Directional Pattern (LDP)[C]//Proceedings of the 17th IEEE International Conference on Image Processing. Piscataway: IEEE, 2010:1605-1608.
[14] HUANG X, ZHAO G, PIETIKAINEN M, et al. Dynamic facial expression recognition using boosted component-based spatiotemporal features and multi-classifier fusion[C]//Proceeding of the 12th International Conference on Advanced Concepts for Intelligent Vision Systems. Berlin: Springer, 2010:312-322.
[15] COOTES T F, TAYLOR C J. Statistical models of appearance for computer vision[EB/OL].[2014-07-11]. http://personalpages.manchester.ac.uk/staff/timothy.f.cootes/Models/app_models.pdf.
[16] CHE H, LYU F, XIANG Z. Defects identification by SVM-DS fusion decision-making with multiple features[J]. Journal of Mechanical Engineering, 2010,46(16):101-105.(车红昆,吕福在,项占琴.多特征SVM-DS融合决策的缺陷识别[J].机械工程学报,2010,46(16):101-105.)

基于主动形状模型差分纹理和局部方向模式特征融合的人脸表情识别

Facial expression recognition based on feature fusion of active shape model differential texture and local directional pattern

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

[1]	罗元, 李慧敏, 张毅. 基于兴趣点定位的局部方向模式人脸识别方法[J]. 计算机应用, 2017, 37(8): 2248-2252.
[2]	孙劲光, 孟凡宇. 基于深度神经网络的特征加权融合人脸识别方法[J]. 计算机应用, 2016, 36(2): 437-443.
[3]	符晓娟黄东军. 基于二维自动主动形状模型的椎间盘核磁共振图像分割算法[J]. 计算机应用, 2013, 33(09): 2686-2689.
[4]	姚丽莎赵海峰罗斌朱珍元. 基于证据理论的小波域多特征医学图像融合[J]. 计算机应用, 2012, 32(06): 1544-1547.
[5]	韩玉峰王小林. 基于主动形状模型算法的局部灰度模型的加权改进方法[J]. 计算机应用, 2011, 31(12): 3392-3394.
[6]	王磊胡超吴捷贺庆刘伟. 基于多相机的人脸姿态识别[J]. 计算机应用, 2010, 30(12): 3307-3310.
[7]	杜立强贾鹏周宗潭胡德文. 基于主动形状模型的人脸脸型自动分类算法[J]. 计算机应用, 2009, 29(10): 2710-2712.
[8]	李嵩刘党辉沈兰荪. 基于ASM和线段Hausdorff距离的人脸识别[J]. 计算机应用, 2008, 28(5): 1217-1220.