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

刘帅师; 田彦涛; 万川

doi:10.3724/SP.J.1004.2011.01455

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

doi: 10.3724/SP.J.1004.2011.01455

刘帅师^1,2,
田彦涛^1, ,,
万川¹

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:
田彦涛吉林大学教授. 1993年于吉林工业大学获得工学博士学位. 主要研究方向为复杂系统建模, 优化与控制, 机器视觉与模式识别. E-mail: tianyt@jlu.edu.cn

计量
- 文章访问数: 2324
- HTML全文浏览量: 75
- PDF下载量: 1814
- 被引次数: 0
出版历程
- 收稿日期: 2011-03-28
- 修回日期: 2011-07-07
- 刊出日期: 2011-12-20

Facial Expression Recognition Method Based on Gabor Multi-orientationFeatures Fusion and Block Histogram

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Gabor特征表征全局特征能力弱以及特征数据存在冗余性的缺点, 提出一种新颖的采用Gabor多方向特征融合与分块直方图统计相结合的方法来提取表情特征. 为了提取局部方向信息并降低特征维数, 首先采用Gabor滤波器提取人脸表情图像的多尺度和多方向特征, 然后按照两个融合规则将相同尺度不同方向的特征融合到一起. 为了能够有效地表征图像全局特征, 将融合图像进一步划分为若干矩形不重叠且大小相等的子块, 分别计算每个子块区域内融合特征的直方图分布, 将其联合起来实现图像表征. 实验结果表明, 这种方法无论在计算量上还是识别性能上都比传统的Gabor滤波器组更具有优势. 该方法的创新处在于提出了两个Gabor多方向特征融合规则, 应用在JAFFE表情库上最高平均识别率达到98.24%, 表明其适用于人脸表情图像的分析.
- 表情识别 /
- 特征融合 /
- 分块直方图 /
- 多尺度 /
- Gabor变换
Abstract: In this paper, the Gabor multi-orientation fused features are combined with block histogram to extract facial expressional features in order to overcome the disadvantage of traditional Gabor filter bank, whose high-dimensional Gabor features are redundant and the global features representation capacity is poor. First, to extract the multi-orientation information and reduce the dimension of the features, two fusion rules are proposed to fuse the original Gabor features of the same scale into a single feature. Second, to represent the global features effectively, the fused image is divided into several nonoverlapping rectangular units, and the histogram of each unit is computed and combined as facial expression features. Experimental results show that the method is effective for both dimension reduction and recognition performance. The novelty of the method is to use two fusion rules to fuse multi-orientation Gabor features. The best average recognition rate of 98.24% is achieved in JAFFE database, which indicates this method is suitable for facial expression linebreak analysis.
- Expression recognition /
- features fusion /
- block histogram /
- multi-scale /
- Gabor transform

HTML全文

参考文献(1)

[1]

Jin Hui, Gao Wen. Analysis and recognition of facial expression image sequences based on HMM. Acta Automatica Sinica, 2002, 28(4): 646-650(金辉, 高文. 基于HMM的面部表情图像序列的分析与识别. 自动化学报, 2002, 28(4): 646-650)[2] Liu Xiao-Min, Zhang Yu-Jin. Facial expression recognition based on Gabor histogram feature and MVBoost. Journal of Computer Research and Development, 2007, 44(7): 1089-1096(刘晓旻, 章毓晋. 基于Gabor直方图特征和MVBoost的人脸表情识别. 计算机研究与发展, 2007, 44(7): 1089-1096)[3] Liu Xiao-Min, Tan Hua-Chun, Zhang Yu-Jin. New research advances in facial expression recognition. Journal of Image and Graphics, 2006, 11(10): 1359-1368(刘晓旻, 谭华春, 章毓晋. 人脸表情识别研究的新进展. 中国图象图形学报, 2006, 11(10): 1359-1368)[4] Xue Yu-Li, Mao Xia, Guo Ye, Lv Shan-Wei. The research advance of facial expression recognition in human computer interaction. Journal of Image and Graphics, 2009, 14(5): 764-772(薛雨丽, 毛峡, 郭叶, 吕善伟. 人机交互中的人脸表情识别研究进展. 中国图象图形学报, 2009, 14(5): 764-772)[5] Wu Xiu-Yong, Xu Ke, Xu Jin-Wu. Automatic recognition method of surface defects based on Gabor wavelet and kernel locality preserving projections. Acta Automatica Sinica, 2010, 36(3): 438-441(吴秀永, 徐科, 徐金梧. 基于Gabor小波和核保局投影算法的表面缺陷自动识别方法. 自动化学报, 2010, 36(3): 438-441)[6] Ashraf A B, Lucey S, Chen T. Reinterpreting the application of Gabor filters as a manipulation of the margin in linear support vector machines. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(7): 1335-1341[7] Lee T S. Image representation using 2D Gabor wavelets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(10): 959-971[8] Donato G, Bartlett M S, Hager J C, Ekman P, Sejnowski T J. Classifying facial actions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(10): 947-989[9] Zhang Z Y, Lyons M, Schuster M, Akamatsu S. Comparison between geometry-based and Gabor-wavelets-based facial expression recognition using multi-layer perceptron. In: Proceedings of the 3rd IEEE International Conference on Automatic Face and Gesture Recognition. Nara, Japan: IEEE, 1998. 454-459[10] Wen Z, Huang T S. Capturing subtle facial motions in 3D face tracking. In: Proceedings of the 9th IEEE International Conference on Computer Vision. Nice, France: IEEE, 2003. 1343-1350[11] Yu J G, Bhanu B. Evolutionary feature synthesis for facial expression recognition. Pattern Recognition Letters, 2006, 27(1): 1289-1298[12] Liao S, Fan W, Chung A C S, Yeung D Y. Facial expression recognition using advanced local binary patterns, Tsallis entropies and global appearance features. In: Proceedings of the IEEE International Conference on Image Processing. Atlanta, USA: IEEE, 2006. 665-668[13] Deng Hong-Bo, Jin Lian-Wen. Facial expression recognition based on local Gabor filter bank and PCA + LDA. Journal of Image and Graphics, 2007, 12(2): 322-329(邓洪波, 金连文. 一种基于局部Gabor滤波器组及PCA + LDA的人脸表情识别方法. 中国图象图形学报, 2007, 12(2): 322-329)[14] Zhang B C, Shan S G, Chen X L, Gao W. Histogram of Gabor phase patterns (HGPP): a novel object representation approach for face recognition. IEEE Transactions on Image Processing, 2007, 16(1): 57-68[15] Yang Bo, Jing Zhong-Liang. Image fusion algorithm based on the quincunx-sampled discrete wavelet frame. Acta Automatica Sinica, 2010, 36(1): 12-22(杨波, 敬忠良. 梅花形采样离散小波框架图像融合算法. 自动化学报, 2010, 36(1): 12-22)[16] Gu Xin, Wang Hai-Tao, Wang Ling-Feng, Wang Ying, Chen Ru-Bing, Pan Chun-Hong. Fusing multiple features for object tracking based on uncertainty measurement. Acta Automatica Sinica, 2011, 37(5): 550-559(顾鑫, 王海涛, 汪凌峰, 王颖, 陈如冰, 潘春洪. 基于不确定性度量的多特征融合跟踪. 自动化学报, 2011, 37(5): 550-559)[17] Gao Quan-Xue, Xie De-Yan, Xu Hui, Li Yuan-Zheng, Gao Xi-Quan. Supervised feature extraction based on information fusion of local structure and diversity information. Acta Automatica Sinica, 2010, 36(8): 1107-1114(高全学, 谢德艳, 徐辉, 李远征, 高西全. 融合局部结构和差异信息的监督特征提取算法. 自动化学报, 2010, 36(8): 1107-1114)[18] Lei Z, Liao S, Pietikainen M, Li S Z. Face recognition by exploring information jointly in space, scale and orientation. IEEE Transactions on Image Processing, 2011, 20(1): 247-256[19] Shen Lin-Lin, Ji Zhen. Gabor wavelet selection and SVM classification for object recognition. Acta Automatica Sinica, 2009, 35(4): 350-355[20] 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. Jinan, China: IEEE, 2010. 6267-6271[21] Gong Ting, Hu Tong-Sen, Tian Xian-Zhong. Human face expression recognition based on within-class modular PCA. Mechanical and Electrical Engineering Magazine, 2009, 26(7): 74-76(龚婷, 胡同森, 田贤忠. 基于类内分块PCA方法的人脸表情识别. 机电工程, 2009, 26(7): 74-76)[22] Jadhao D V, Holambe R S. Gabor wavelet feature based face recognition using the fractional power polynomial kernel Fisher discriminant model. In: Proceedings of the International Conference on Computational Intelligence and Multimedia Applications. Tamil Nadu, India: IEEE, 2007. 387-393[23] 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

计量

文章访问数: 2324
HTML全文浏览量: 75
PDF下载量: 1814
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

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

doi: 10.3724/SP.J.1004.2011.01455

通讯作者:
田彦涛吉林大学教授. 1993年于吉林工业大学获得工学博士学位. 主要研究方向为复杂系统建模, 优化与控制, 机器视觉与模式识别. E-mail: tianyt@jlu.edu.cn

计量

Facial Expression Recognition Method Based on Gabor Multi-orientationFeatures Fusion and Block Histogram

计量

目录

留言板

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

doi: 10.3724/SP.J.1004.2011.01455

通讯作者: 田彦涛 吉林大学教授. 1993年于吉林工业大学获得工学博士学位. 主要研究方向为复杂系统建模, 优化与控制, 机器视觉与模式识别. E-mail: tianyt@jlu.edu.cn

计量

出版历程

Facial Expression Recognition Method Based on Gabor Multi-orientationFeatures Fusion and Block Histogram

计量

出版历程

目录

通讯作者:
田彦涛吉林大学教授. 1993年于吉林工业大学获得工学博士学位. 主要研究方向为复杂系统建模, 优化与控制, 机器视觉与模式识别. E-mail: tianyt@jlu.edu.cn