基于离散Shearlet类别可分性测度的人脸表情识别方法

doi:10.13229/j.cnki.jdxbgxb20180627

摘要/Abstract

摘要：

针对优化表情特征稀疏表达问题，提出一种基于离散Shearlet类别可分性测度的人脸表情识别方法。首先，对预处理后的图像进行离散Shearlet变换，得到变换系数。然后，根据测度函数评估每个方向与尺度系数的可分性指标，在最佳可分性方向与尺度上，融合低频和高频系数作为特征。最后，引入支持向量机进行分类。结果证明：本文方法选取具有最佳可分性的尺度和方向系数作为特征，抛弃了无用信息，降低了特征维度与计算量，使系统更高效。

关键词: 信息处理技术, 离散可分离剪切波变换, 人脸表情识别, 可分性评价, 多尺度几何分析, 支持向量机

Abstract:

To solve the problem of sparse expression of facial expression features, a facial expression recognition method based on separability assessment of the Discrete Shearlet Transform (DST) is proposed. DST is a relatively new image multiscale geometric analysis method. First, the DST transform is applied to the preprocessed facial expression images, and the transformation coefficients are obtained. Then, according to the separability evaluation function, the separability index in each direction and the scale coefficients are evaluated, and the low and high-frequency coefficients are fused on the best separability direction and scale. Finally, Support Vector Machine (SVM) is introduced to classify the facial expression. The experimental results show that the proposed method can select the best separability scale and direction coefficient as the feature, abandon the useless information, reduce the feature dimension and computation cost, therefore, the system is more efficient.

Key words: information processing technology, discrete separable shearlet transform, facial expression recognition, separability assessment, multiscale geometric analysis, support vector machine

中图分类号:

TN911.7

卢洋,王世刚,赵文婷,赵岩. 基于离散Shearlet类别可分性测度的人脸表情识别方法[J]. 吉林大学学报(工学版), 2019, 49(5): 1715-1725.

Yang LU,Shi-gang WANG,Wen-ting ZHAO,Yan ZHAO. Facial expression recognition based on separability assessment of discrete Shearlet transform[J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(5): 1715-1725.

图/表 13

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

图10

表2

表3

参考文献 23

1	贲晛烨，杨明强，张鹏，等 . 微表情自动识别综述[J]. 计算机辅助设计与图形学学报, 2014, 26(9): 1385-1395.
	Xian-ye Ben , Yang Ming-qiang , Zhang Peng , et al . Survey on automatic micro expression recognition methods[J]. Journal of Computer Aided Design and Computer Graphics, 2014, 26(9): 1385-1395.
2	Zhang W , Ma L . Multimodal learning for facial expression recognition[J]. Pattern Recognition, 2015, 48(10): 3191-3202.
3	万川，田彦涛，刘帅师，等 . 基于主动机器视觉的人脸跟踪与表情识别系统[J]. 吉林大学学报：工学版, 2013, 43(2): 459-465.
	Wan Chuan , Tian Yan-tao , Liu Shuai-shi , et al . Face tracking and facial expression recognition system based on active machine vision[J]. Journal of Jilin University (Engineering and Technology Edition), 2013, 43(2): 459-465.
4	张娟, 詹永照, 毛启容, 等 . 基于Gabor小波和稀疏表示的人脸表情识别[J]. 计算机工程, 2012, 38(6): 207-209, 212.
	Zhang Juan , Zhan Yong-zhao , Mao Qi-rong , et al . Facial expression recognition based on gabor wavelet and sparse representation[J]. Computer Engineering, 2012, 38(6): 207-209, 212.
5	Tang M , Chen F . Facial expression recognition and its application based on curvelet transform and PSO-SVM[J]. OPTIK, 2013, 123(22): 5401-5406.
6	庄志军, 陈延嘉, 王美清 . 基于脊波变换的线性判别分析人脸识别方法[J]. 福州大学学报: 自然科学版, 2008, 36(5): 664-667.
	Zhuang Zhi-jun , Chen Yan-jia , Wang Mei-qing . A face recognition method using linear discriminant analysis based on Ridgelet transform[J]. Journal of Fuzhou University (Natural Science), 2008, 36(5): 664-667.
7	赵阳 . 曲波变换在人脸识别中的应用[D]. 西安: 西安理工大学计算机科学与工程学院, 2009.
	Zhao Yang . Curvelet transform applied on face recognition[D]. Xi'an: School of Computer Science & Engineering, Xi'an University of Technology, 2009.
8	Lu Y , Wang S G , et al . A novel approach of facial expression recognition based on shearlet transform[C]⫽IEEE 5th Global Conference on Signal and Information Processing IEEE, Montreal, QC, 2017: 398-402.
9	Hou B , Zhang X , Bu X . SAR image despeckling based on nonsubsampled Shearlet transform[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2012, 5(3): 809-823.
10	Lim W Q . The discrete shearlet transform: a new directional transform and compactly supported Shearlet frames[J]. IEEE Transactions on Image Processing, 2010, 19(5): 1166-1180.
11	Shao Y H , Deng N Y , Chen W J . Improved generalized eigenvalue proximal support vector machine[J]. IEEE Signal Processing Letters, 2013, 20(3): 213-216.
12	孙雯玉 . 人脸表情识别算法研究[D]. 北京: 北京交通大学电子信息工程学院, 2006.
	Sun Wen-yu . Facial expression recognition arithmetic research[D]. Beijing: School of Electronic Information Engineering, Beijing Jiaotong University, 2006.
13	李宏伟 . 一种综合先验信息的从自然图像中提取感兴趣物体的新方法[D]. 合肥: 中国科学技术大学计算机科学与技术学院, 2009.
	Li Hong-wei . A novel method for extracting object-of-interest from natural image by integrating prior knowlegde[D]. Hefei: School of Computer Science and Technology, University of Science and Technology of China, 2009.
14	Lyons M J , Akamatsu S , Kamachi M G . Coding facial expressions with gabor wavelets[C]⫽3rd IEEE International Conf on Automatic Face and Gesture Recognition, Nara, Japan, 1998: 200-205.
15	Lucey P , Cohn J F , Kanade T , et al . The extended cohn-kanade dataset (CK+): a complete expression dataset for action unit and emotion-specified expression[C]⫽Proceedings of the 3rd International Workshop on CVPR for Human Communicative Behavior Analysis, USA, 2010: 94-101.
16	Ucar A . A new facial expression recognition based on curvelet transform and online sequential extreme learning machine initialized with spherical clustering[J]. Neural Computing & Applications, 2014, 27(1): 131-142.
17	Gu W , Xiang C , Venkatesh Y V . Facial expression recognition using radial encoding of local Gabor features and classifier synthesis[J]. Pattern Recognition, 2012, 45(1): 80-91.
18	Zhang L , Tjondronegoro D . Facial expression recognition using facial movement features[J]. IEEE Transactions on Affective Computing, 2011, 2(4): 219-229.
19	Kyperountas M , Tefas A , Pitas I . Salient feature and reliable classifier selection for facial expression classification[J]. Pattern Recognition, 2010, 43(3): 972-986.
20	Mistry K , Zhang L , Sexton G , et al . Facial expression recongition using firefly-based feature optimization, [C]⫽2017 IEEE Congress on Evolutionary Computation, San Sebastian Spain, 2017: 1652-1658.
21	Zhong L , Liu Q , Yang P , et al . Learning active facial patches for expression analysis[C]⫽Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, USA, 2012: 2562-2569.
22	Shan C , Gong S , Mcowan P W . Facial expression recognition based on local binary patterns: a comprehensive study[J]. Image & Vision Computing, 2009, 27(6): 803-816.
23	代琨，于宏毅，仇文博，等 . 基于SVM的网络数据无监督特征选择算法[J]. 吉林大学学报: 工学版, 2015, 45(2): 576-582.
	Dai Kun , Yu Hong-yi , Wen-bo Chou , et al . Unsupervised feature selection algorithm based on support vector machine for network data[J]. Journal of Jilin University (Engineering and Technology Edition), 2015, 45(2): 576-582.

相关文章 15

[1]	赵宏伟,李明昭,刘静,胡黄水,王丹,臧雪柏. 基于自然性和视觉特征通道的场景分类[J]. 吉林大学学报(工学版), 2019, 49(5): 1668-1675.
[2]	赵金钢,张明,占玉林,谢明志. 基于塑性应变能密度的钢筋混凝土墩柱损伤准则[J]. 吉林大学学报(工学版), 2019, 49(4): 1124-1133.
[3]	董超,刘晶红,徐芳,王仁浩. 光学遥感图像舰船目标快速检测方法[J]. 吉林大学学报(工学版), 2019, 49(4): 1369-1376.
[4]	王柯俨,胡妍,王怀,李云松. 结合天空分割和超像素级暗通道的图像去雾算法[J]. 吉林大学学报(工学版), 2019, 49(4): 1377-1384.
[5]	陈俊,张奇峰,张艾群,蔡笃思. 基于深渊鱼类识别的原位自主观测方法[J]. 吉林大学学报(工学版), 2019, 49(3): 953-962.
[6]	托乎提努尔,张海龙,王杰,王娜,冶鑫晨,王万琼. 基于图形处理器的高速中值滤波算法[J]. 吉林大学学报(工学版), 2019, 49(3): 979-985.
[7]	付银娟,李勇,徐丽琴,张昆辉. NLFM⁃Costas射频隐身雷达信号设计及分析[J]. 吉林大学学报(工学版), 2019, 49(3): 994-999.
[8]	苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.
[9]	徐岩,孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1895-1903.
[10]	李居朋,张祖成,李墨羽,缪德芳. 基于Kalman滤波的电容屏触控轨迹平滑算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1910-1916.
[11]	黄勇,杨德运,乔赛,慕振国. 高分辨合成孔径雷达图像的耦合传统恒虚警目标检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1904-1909.
[12]	应欢,刘松华,唐博文,韩丽芳,周亮. 基于自适应释放策略的低开销确定性重放方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1917-1924.
[13]	陆智俊,钟超,吴敬玉. 星载合成孔径雷达图像小特征的准确分割方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1925-1930.
[14]	刘仲民,王阳,李战明,胡文瑾. 基于简单线性迭代聚类和快速最近邻区域合并的图像分割算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1931-1937.
[15]	单泽彪,刘小松,史红伟,王春阳,石要武. 动态压缩感知波达方向跟踪算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1938-1944.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

核函数	识别率/%
核函数	JAFFE	CK+
线性	95.86	92.05
二阶多项式	96.71	92.89
三阶多项式	97.18	94.17
RBF	97.65	94.60
Sigmoid	82.63	87.50

算法	特征	识别率/%
本文	SST-SJ+SVM	96.26
文献[8]	DST+SVM	89.01
文献[16]	局部曲波变换	94.65
文献[17]	Radial encoded Gabor jets	89.67
文献[18]	Patch-based-Gabor	92.93
文献[19]	FEETS+PRNN	83.84
文献[20]	Overlap LBP+FA variant+Ensemble(SVM)	87.75

算法	特征	识别率/%
本文	SST-SJ+SVM	94.05
文献[21]	CSPL	89.89
文献[22]	基于TC特征	88.90