基于对称双线性模型的光照鲁棒性人脸表情识别

刘帅师; 田彦涛; 王新竹

doi:10.3724/SP.J.1004.2012.01933

基于对称双线性模型的光照鲁棒性人脸表情识别

doi: 10.3724/SP.J.1004.2012.01933

1.
吉林大学控制科学与工程系长春 130025;
2.
长春工业大学自动化系长春 130012

详细信息

通讯作者:
田彦涛

计量
- 文章访问数: 2085
- HTML全文浏览量: 36
- PDF下载量: 1155
- 被引次数: 0
出版历程
- 收稿日期: 2012-01-19
- 修回日期: 2012-06-15
- 刊出日期: 2012-12-20

Illumination-robust Facial Expression Recognition Based on Symmetric Bilinear Model

1.
Department of Control Science and Engineering, Jilin University, Changchun 130025;
2.
Department of Automation, Changchun University of Technology, Changchun 130012

摘要

摘要: 针对传统的光照预处理方法降低原始图像质量、丢失部分有效辨识信息的缺点,提出一种新颖的应用对称双线性模型来对人脸表情图像进行光照预处理的光照鲁棒性人脸表情识别方法.首先通过对称双线性模型将训练集图像分解为相互独立的光照因子和表情因子,并提取其光照因子.接下来提取含有未知光照的测试集表情图像的表情因子,并将其转换到训练集的若干个已知光照上,这样处理能够将任意光照的测试图像转换到相同的光照平台上,令所有测试图像的特征具有归一化特性.实验结果表明, 本文所提光照预处理方法在识别性能上优于传统的光照预处理方法,应用在光照处理后的JAFFE表情库上识别率达到92.37%, 表明其适用于光照鲁棒性人脸表情识别.
- 对称双线性模型 /
- 光照预处理 /
- 光照鲁棒性 /
- 表情识别
Abstract: This paper proposes a novel illumination-robust facial expression recognition method using symmetric bilinear model to overcome the disadvantage of traditional illumination preprocessing methods that can degrade the quality of input image and worsen recognition performance. Firstly, the illumination factors are separated from the training database. Secondly, the expression factor is separated from testing image with arbitrary illumination. Thirdly, the testing image is transformed into a number of expression images exhibiting different illuminations of training database. Experimental results show that the proposed method is better than the traditional illumination preprocessing methods in recognition performance. The best recognition rate of 92.37% is achieved in JAFFE database with illumination transformation, indicating this method is suitable for illumination-robust facial expression recognition.
- Symmetric bilinear model /
- illumination preprocessing /
- illumination-robust /
- expression recognition

HTML全文

参考文献(1)

[1]

Sun Wei, Wang Bo. A survey of facial expression recognition. Computer Knowledge and Technology, 2012, 8(1): 106-108(孙蔚, 王波. 人脸表情识别综述. 电脑知识与技术, 2012, 8(1): 106-108)[2] Zhao Xu-Dong, Liu Peng, Tang Xiang-Long, Liu Jia-Feng. Background modeling adaptive to outdoor illumination variation and foreground detection approach. Acta Automatica Sinica, 2011, 37(8): 915-922(赵旭东, 刘鹏, 唐降龙, 刘家锋. 一种适应户外光照变化的背景建模及目标检测方法. 自动化学报, 2011,37(8): 915-922)[3] Hong J W, Song K T. Facial expression recognition under illumination variation. In: Proceedings of the 2007 IEEE Workshop on Advanced Robotics and Its Social Impacts. Taipei, China: IEEE, 2007. 1-6[4] Li H, Buenaposada J M, Baumela L. Real-time facial expression recognition with illumination-corrected image sequences. In: Proceedings of the 8th IEEE International Conference on Automatic Face and Gesture Recognition. Amsterdam, Netherlands: IEEE, 2008. 1-6[5] Li Xiao-Li, Da Fei-Peng. A rapid method for 3D face recognition based on rejection algorithm. Acta Automatica Sinica, 2010, 36(1): 153-158(李晓莉, 达飞鹏. 基于排除算法的快速三维人脸识别方法. 自动化学报, 2010, 36(1): 153-158)[6] Wang Zhi-Hong, Yuan Heng, Jiang Wen-Tao. A face recognition algorithm based on composite gradient vector. Acta Automatica Sinica, 2011, 37(12): 1445-1454(王志宏, 袁姮, 姜文涛. 基于复合梯度向量的人脸识别算法. 自动化学报, 2011, 37(12): 1445-1454)[7] Georghiades A S, Belhumeur P N, Kriegman D J. From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 643-660[8] Liu Du-Jin, Sun Shu-Xia, Li Si-Ming. Analysis of illumination treatment methods in face recognition. Computer Systems and Applications, 2011, 20(1): 160-163(刘笃晋, 孙淑霞, 李思明. 人脸识别中光照处理方法的分析. 计算机系统应用, 2011, 20(1): 160-163)[9] Blanz V, Vetter T. Face recognition based on fitting a 3D morphable Model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(9): 1063-1074[10] Shan S G, Gao W, Cao B, Zhao D B. Illumination normalization for robust face recognition against varying illumination conditions. In: Proceedings of the 2003 IEEE International Workshop on Analysis and Modeling of Faces and Gestures. Washington D.C., USA: IEEE Computer Society, 2003. 157-164[11] Wang H T, Li S Z, Wang Y S. Face recognition under varying lighting conditions using self quotient image. In: Proceedings of the 6th IEEE International Conference on Automatic Face and Gesture Recognition. Seoul, Korea: IEEE Computer Society, 2004. 819-824[12] Wang Hai-Tao, Liu Jun, Wang Yang-Sheng. Self-quotient image. Computer Engineering, 2005, 31(18): 178-179(王海涛, 刘俊, 王阳生. 自商图像. 计算机工程, 2005, 31(18): 178-179)[13] Chen T, Yin W, Zhou X S, Comaniciu D, Huang T S. Illumination normalization for face recognition and uneven background correction using total variation based image models. In: Proceedings of the 2005 IEEE International Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE, 2005. 532-539[14] Zhang Yi, Zhang Gui-Lin. An illumination invariant face recognition algorithm based on total variation model. Journal of Image and Graphics, 2009, 12(2): 208-213(张熠, 张桂林. 基于总变分模型的光照不变人脸识别算法. 中国图形图像学报, 2009, 12(2): 208-213)[15] Tenenbaum J B, Freeman W T. Separating style and content with bilinear models. Neural Computation, 2000, 12(6): 1247-1283[16] Abboud B, Davoine F. Appearance factorization based facial expression recognition and synthesis. In: Proceedings of the 17th International Conference on Pattern Recognition. Cambridge, UK: IEEE Computer Society, 2004. 163-166[17] Du Y Z, Lin X Y. Multi-view face image synthesis using factorization model. In: Proceedings of the 2004 Computer Vision in Human-computer Interaction. Prague, Czech Republic: IEEE, 2004. 200-210[18] Lee H, Kim D. Facial expression transformations for expression-invariant face recognition. In: Proceedings of the 2006 International Symposium on Visual Computing. Lake Tahoe, NV, USA: IEEE, 2006. 323-333[19] Grimes D, Rao R. A bilinear model for sparse coding. In: Proceedings of the 2003 Advance in Neural Information Processing Systems. Vancouver, Canada: IEEE, 2003. 1287-1294[20] Magnus J R, Neudecker H. Matrix Differential Calculus with Applications in Statistics and Econometrics. New York: Wiley Press, 1988[21] Shashua A, Riklin-Raviv T. The quotient image: class-based re-rendering and recognition with varying illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 32(2): 129-139[22] Liu S S, Tian Y T, Wan C. Gabor feature representation method based on block statistics and its application to facial expression recognition. In: Proceedings of the 8th World Congress on Intelligent Control and Automation. Ji’nan, China: IEEE, 2010. 6267-6271[23] Liu Shuai-Shi, Tian Yan-Tao, Wan Chuan. Facial expression recognition method based on Gabor multi-orientation features fusion and block histogram. Acta Automatica Sinica, 2011, 37(12): 1455-1463(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方法. 自动化学报, 2011, 37(12): 1455-1463)[24] Wang Y M, Zhang Y Z. The facial expression recognition based on KPCA. In: Proceedings of the 2010 International Conference on Intelligence Control and Information Processing. Dalian, China: IEEE, 2010. 365-368[25] Kim S K, Park Y J, Toh K A, Lee S. SVM-based feature extraction for face recognition. Pattern Recognition, 2010, 43(8): 2871-2881

施引文献

资源附件(0)

访问统计