基于改进的字典学习与稀疏表示的人脸表情识别

doi:10.16182/j.issn1004731x.joss.201801004

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (1): 28-36.doi: 10.16182/j.issn1004731x.joss.201801004

基于改进的字典学习与稀疏表示的人脸表情识别

黎明^1,2, 彭秀姣¹, 王艳²

1.南昌航空大学信息工程学院,江西南昌330063;
2.南京航空航天大学自动化学院,江苏南京210016

收稿日期:2015-12-02 发布日期:2019-01-02
作者简介:黎明(1965-),男,江西南昌,博士,教授,研究方向为智能计算,图像处理与模式识别;彭秀姣(1990-),女,江西九江,硕士生,研究方向为图像处理与模式识别。
基金资助:
国家自然科学基金(61262019)

Facial Expression Recognition Based on Improved Dictionary Learning and Sparse Representation

Li Ming^1,2, Peng Xiujiao¹, Wang Yan²

1.School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China;
2.College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

Received:2015-12-02 Published:2019-01-02

摘要/Abstract

摘要： 为克服人脸表情图像识别过程中光照、遮挡等带来的影响,减少稀疏表示分类的时间,提出一种融合HOG特征和改进KC-FDDL(K-means Cluster and Fisher Discrimination Dictionary Learning)字典学习稀疏表示的人脸表情识别算法。对归一化后的表情图像提取HOG特征构成训练集,对训练集进行改进的K-均值聚类的Fisher判别字典学习,利用残差加权的稀疏表示进行表情分类。Cohn-Kanade数据库上的实验结果表明,该算法相比其他的人脸表情分类方法具有耗时低、相似表情分类更准确的优势。

关键词: 遮挡, HOG特征, KC-FDDL字典学习, 稀疏表示, 残差加权

Abstract: In order to overcome the problems induced by illumination andocclude in facial expression recognition and reduce the time required by sparse representation classification, the facial expression recognition algorithm withfusion of HOG feature and improved KC-FDDL dictionary learning sparserepresentation is put forward. Improved K-means cluster and Fisher discriminationdictionary learningis implemented on thetraining setgenerated by extracting HOG features of normalized expression image.Facial expression classification is conducted by thesparse representation with weighted residuals. Experimental results on the Cohn-Kanade databaseshow that this method is lower time-consumingand more accurate for similar facial expression classification than other facial expression classification methods.

Key words: occlude, HOG features, KC-FDDLdictionarylearning, sparse representation, weighted residuals

中图分类号:

TP391

黎明, 彭秀姣, 王艳. 基于改进的字典学习与稀疏表示的人脸表情识别[J]. 系统仿真学报, 2018, 30(1): 28-36.

Li Ming, Peng Xiujiao, Wang Yan. Facial Expression Recognition Based on Improved Dictionary Learning and Sparse Representation[J]. Journal of System Simulation, 2018, 30(1): 28-36.

参考文献

[1] 薛雨丽, 毛峡, 郭叶. 人机交互中的人脸表情识别研究进展[J]. 中国图象图形学报, 2009, 14(5): 764-772. DOI:10.1183 4/ jig. 20090503.XueYuli, MAO Xi, GUO Ye. The Research Advance of Facial Expression Recognition in Human Computer Interaction[J]. Journal of Image & Graphics, 2009, 14(5): 764-772. DOI10.11834/jig. 20090503.
[2] 蒋斌, 夏克斌, 杨国胜. 人脸表情识别研究进展[J]. 计算机科学, 2011, 38(4): 25-31.JIANG Bin, XIA Kebin, YANG Guosheng. Research Advance of Facial Expression Recognition[J]. Computer Science, 2011, 38(4): 25-31.
[3] 朱明旱, 李树涛, 叶华. 基于稀疏表示的遮挡人脸表情识别方法[J].模式识别与人工智能, 2014, 27(8): 708-712.ZHU Minghan, LI Shutao, YE Hua. AnOccluded Facial Expression Recognition Method Based on Sparse Representation[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(8): 708-712.
[4] Liu W, Song C, Wang Y.Facial expression recognition based on gabor features and sparser-epresentation[C]// 2012 12th International Co-nference on Control Automation Robotics & Vis-ion (ICARCV), IEEE, 2012: 1402-1406.
[5] Zhen W, Zi L Y.Facial expression recognition based on local phase quantization and sparse representation[C]// 2012 Eighth International Conference on Natural Computation (ICNC), USA: IEEE, 2012: 222-225.
[6] Huang M W, Wang Z W, Ying Z L.A new method for facial expression recognition based on sparse representation plus lbp[C]//2010 Third Internatio- nal Congress on Image and Signal Processing (CISP), USA: IEEE, 2010, 4: 1750-1754.
[7] Wright J, Yang A Y, Ganesh A.Robust face recognition via sparse representation[C]. IEEE Tr-ans. Pattern Anal. Mach. Intell, 2009, 31(2): 210-227.
[8] Cotter S F.Sparse representation for accurate clas-sification of corrupted and occluded facial expres-sions[C]//2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), USA: IEEE, 2010: 838-841.
[9] Ou Y Y.Accurate and robust facial expressions recognition by fusing multiple sparse representati-on based classifiers[J]. Neurocomputing (S0925-2312), 2014, 73(3): 71-78.
[10] Mohammadi M R, Fatemizadeh E, Mahoor MH.PCA-based dictionary building for accurate facial expression recognition via sparse repres-entation[J]. J. Vis. Commun. Image R(S1047-3203), 2014, 25(5): 1082-1092.
[11] Aharon M, Elad M, Bruckstein A.K-svd: an algorithm for designing overcompletedictionar-ies for sparse representation[C]. IEEE Trans. Sig-nal Process, 2006, 54(11): 4311-4322.
[12] Mairal J, Bach F, Ponce J.Learning discriminate-ve dictionaries for local image analysis[C]// CVPR, 2008.
[13] Yang M, Zhang L, Yang J.Metaface learning for sparse representation based face recognition[C]//2010 17th IEEE International Conference on Image Processing (ICIP), USA: IEEE, 2010: 1601-1604.
[14] Rubinstein R, Bruckstein A M, Elad M.Dictiona-ries for sparse representation modeling[C]. Proc. IEEE, USA: IEEE, 2010, 98(6): 1045-1057.
[15] Zhang Q, Li B.Discriminative k-svd for dictiona-dry learning in face recognition[C]// 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA: IEEE, 2010: 2691-2698.
[16] Yang M, Zhang L, Feng X.Fisher discrimination dictionary learning for sparse representation[C]//2011 IEEE International Conference on Com-puter Vision (ICCV), USA: IEEE, 2011: 543-550.
[17] Dalal N, Triggs B.Histograms of oriented gradients for human detection[C]//Proceedings of the IEEE International Conference on Compu-ter Vision and Pattern Recognition, Montbonnot, France, USA: IEEE Press, 2005: 886-893.
[18] 罗元, 崔叶, 王艳. 基于融合DCT和LBP特征提取的面部表情识别[J]. 半导体光电, 2014, 35(2): 330-334.LUO Yuan, CUI Ye, WANG Yan. Face Expression Recognition Based on Fusion Feature of DCT and LBP[J]. Semiconductor Optoelectronics, 2014, 35(2): 330-334.
[19] 李雅倩, 李颖杰, 李海滨. 融合全局与局部多样性特征的人脸表情识别[J]. 光学学报, 2014, 34(5): 1-7.Li Yaqian, Li Yingjie, Li Haibin. Fusion of Global and Local Various Feature for Facial Expression Recognition [J]. Journal of Acta Optica Sinica, 2014, 34(5): 1-7.
[20] 詹曙, 王俊, 杨福猛, 等. 基于Gabor特征和字典学习的高斯混合稀疏表示图像识别[J]. 电子学报, 2015, 43(3): 523-528.ZHAN Shu, WANG Jun, YANG Fumeng, et al. Grassian Mixture Sparse Representation Image Recognition Based on Gabor Features and Dictionary Learning[J]. Journal of Electronics, 2015, 43(3): 523-528.
[21] 练秋生, 石保顺, 陈书贞. 字典学习模型算法及其应用研究进展[J]. 自动化学报, 2015, 41(2): 240-260.Lian Qiusheng, Shi Baoshun, Chen Shuzhen. Research Advances on Dictionary Learning Models Algorithm and Applications [J]. Journal of Acta Automatica Sinica, 2015, 41(2): 240-260.
[22] Yang P, Liu Q S, Metaxas D N.Exploring facial expressions with compositional features[C]//IEEE International Conference on Computer V-ision and P attern Recognition, 2010: 2638-2644.

基于改进的字典学习与稀疏表示的人脸表情识别

Facial Expression Recognition Based on Improved Dictionary Learning and Sparse Representation

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	宋晓瑞, 邹玲, 吴玲达, 徐万朋. 基于背景重建的高光谱图像异常检测[J]. 系统仿真学报, 2020, 32(7): 1287-1293.
[2]	王鑫, 张春燕, 宁晨. 基于Gestalt优化的红外视频时空显著性检测[J]. 系统仿真学报, 2020, 32(6): 1021-1031.
[3]	姜华, 张良. 基于部位分割的人体再识别方法[J]. 系统仿真学报, 2019, 31(6): 1085-1091.
[4]	夏永洪, 李梦茹, 辛建波, 曾繁鹏, 余运俊. 阴影下不同光伏阵列结构输出性能对比与分析[J]. 系统仿真学报, 2019, 31(4): 802-810.
[5]	王远明, 张珺, 秦远辉, 柴秀娟. 基于多特征融合的指挥手势识别方法研究[J]. 系统仿真学报, 2019, 31(2): 346-352.
[6]	李菊, 曹明伟, 余烨, 夏瑜, 周立凡. 抗遮挡自适应的粒子滤波算法[J]. 系统仿真学报, 2018, 30(9): 3552-3557.
[7]	牛为华, 梁贵书, 赵鹏. 基于稀疏表示和M-ELM的断路器故障诊断模型[J]. 系统仿真学报, 2017, 29(11): 2828-2839.
[8]	刘长发, 张俊杰. 直升机飞行模拟器视景显示系统的研究[J]. 系统仿真学报, 2016, 28(6): 1394-1399.
[9]	杨恢先, 刘昭, 刘阳, 刘凡, 贺迪龙. 基于超像素和局部稀疏表示的目标跟踪方法[J]. 系统仿真学报, 2016, 28(5): 1017-1030.
[10]	黄丽韶, 文海英, 顾思思. 基于方法噪声稀疏表字典学习的图像去噪算法[J]. 系统仿真学报, 2016, 28(1): 154-159.
[11]	钱宜婧, 杨旭波. 流体模拟的压缩感知上采样方法研究[J]. 系统仿真学报, 2015, 27(7): 1426-1434.
[12]	刘妍, 金鑫, 赵耿, 李晓东, 陈迎亚, 郭魁. 基于稀疏表示的云环境中人脸图像隐秘识别方法[J]. 系统仿真学报, 2015, 27(10): 2291-2298.
[13]	江静宇, 万丽莉. 一种改进的HKS提取方法及非刚体分类应用[J]. 系统仿真学报, 2015, 27(10): 2422-2426.