[1]谢 非,龚 俊,王元祥,等.基于肤色增强和分块PCA的人脸表情识别方法[J].南京师范大学学报(工程技术版),2017,17(02):049.[doi:10.3969/j.issn.1672-1292.2017.02.008]
 Xie Fei,Gong Jun,Wang Yuanxiang,et al.A Facial Expression Recognition Method Based onSkin Color Enhancement and Block PCA[J].Journal of Nanjing Normal University(Engineering and Technology),2017,17(02):049.[doi:10.3969/j.issn.1672-1292.2017.02.008]
点击复制

基于肤色增强和分块PCA的人脸表情识别方法
分享到:

南京师范大学学报(工程技术版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
17卷
期数:
2017年02期
页码:
049
栏目:
计算机工程
出版日期:
2017-06-30

文章信息/Info

Title:
A Facial Expression Recognition Method Based onSkin Color Enhancement and Block PCA
文章编号:
1672-1292(2017)02-0049-08
作者:
谢 非龚 俊王元祥吴 茜杨建飞
(1.南京师范大学江苏省三维打印装备与制造重点实验室,江苏 南京 210042)(2.南京师范大学电气与自动化工程学院,江苏 南京 210042)
Author(s):
Xie FeiGong JunWang YuanxiangWu QianYang Jianfei
(1.Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing,Nanjing Normal University,Nanjing 210042,China)(2.School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing 210042,China)
关键词:
人脸检测表情识别主成分分析肤色模型
Keywords:
face detectionfacial expression recognitionprincipal component analysisskin model
分类号:
TP312
DOI:
10.3969/j.issn.1672-1292.2017.02.008
文献标志码:
A
摘要:
人脸的表情识别在智能人机交互应用中具有重要意义. 本文提出了一种基于肤色增强和分块PCA的人脸检测及表情识别方法. 首先,使用同态滤波增强肤色图像的亮度范围及对比度,利用YCbCr色彩空间分量分离肤色背景区域,再通过轮廓分析确定人脸目标,最后对分割出的人脸进行均衡化处理,并引入分块主成分分析(PCA)算法进行表情识别. 结果表明,该方法在光线较弱以及背景较复杂的情况下均能有效地进行人脸检测与表情识别,相对于传统的LBP方法可提高识别率约为2.3%.
Abstract:
The facial expression recognition is of great significance in the application of intelligent man-machine interaction. This paper has proposed the face detection and expression recognition method based on the skin color enhancement and block PCA. Firstly,the skin color image luminance range is broadened and the contrast ratio is strengthened by the homomorphic filtering method. Secondly,the skin color background region is separated through YCbCr color space component. Thirdly,the face target is determined by the contour analysis. Finally,the equalization processing is made of the segmented face and the principal component analysis(PCA)is imported to accomplish the facial expression recognition. The experimental results show that in case of the weaker light and more complicated background,the face detection and facial expression recognition both can be achieved effectively through the method proposed in this paper,of which the recognition rate has improved 2.3% compared with the traditional LBP method.

参考文献/References:

[1] TAN X,TRIGGS B. Enhanced local texture feature sets for face recognition under difficult lighting condition[J]. IEEE transactions on image processing,2010,19(6):1 635-1 650.
[2]MAALEJ A,AMOR B,DAOUDI M,et al. Shape analysis of local facial patches for 3D facial expression recognition[J]. Pattern recognition,2011,44(8):1 581-1 589.
[3]谢尔曼,罗森林,潘丽敏. 基于Haar特征的Turbo-Boost表情识别算法[J]. 计算机辅助设计与图形学学报,2011,23(8):1 442-1 446.
XIE E M,LUO S L,PAN L M. Turbo-Boost facial expression recognition using Haar-Like features[J]. Journal of computer-aided design and computer graphics,2011,23(8):1 442-1 446.(in Chinese)
[4]邹璘. 人脸检测混合算法研究[D]. 贵阳:贵州大学,2008.
ZOU L. Research for face detection based on a combination algorithm[D]. Guiyang:Guizhou university,2008.(in Chinese)
[5]喻富. 复杂背景下基于全景图像拼接的人脸检测算法研究[D]. 长沙:湖南大学,2013.
YU F. Study for face detection based on panoramic image mosaics in complex background[D]. Changsha:Hunan university,2013.(in Chinese)
[6]MARKUS A,ANDREAS W,CLIFFORD R,et al. An automatic 3D facial landmarking algorithm using 2D Gabor Wavelets[J]. IEEE transactions on image processing,2016,25(2):580-588.
[7]MOEINI A,KARIM F,HOSSEIN M. Real-world gender classification via local Gabor binary pattern and three-dimensional face reconstruction by generic elastic model[J]. IET image processing,2015,9(8):690-698.
[8]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[J]. 自动化学报,2011,37(12):1 455-1 463.
LIU S S,TIAN Y T,WAN C. Facial expression recognition method based on Gabor multi-orientation features fusion and block histogram[J]. Acta automation sinica,2011,37(12):1 455-1 463.(in Chinese)
[9]LEE H S,KIM D J. Tensor-based AAM with continuous variation estimation:application to variation-robust face recognition[J]. IEEE transactions on pattern analysis and machine intelligence,2009,31(6):1 102-1 116.
[10]XUE T F,XIAO L S. Robust facial expression tracking based on composite constraints AAM[C]//IEEE International Conference on Image Processing. USA:IEEE,2011:3 045-3 048.
[11]NAOUFEL W,CLAUDIO T,STEFANO B,et al. Boosting 3D LBP-based face recognition by fusing shape and texture descriptors on the mesh[J]. IEEE transactions on information forensics and security,2016,11(5):964-979.
[12]谢志华,伍世虔,方志军. LBP与鉴别模式结合的热红外人脸识别[J]. 中国图象图形学报,2012,17(6):708-711.XIE Z H,WU S Q,FANG Z J. Infrared face recognition using LBP and discrimination patterns[J]. Journal of image and graphics,2012,17(6):708-711.(in Chinese)
[13]王晓辉,黄伟,秦传波,等. 使用稀疏加权平均脸及对称脸解决单样本问题[J]. 计算机应用研究,2015,32(5):1 527-1 531.
WANG X H,HUANG W,QIN C B,et al. Using weighted average face and symmetrical face to solve problem of single sample per person based on sparse representation[J]. Application research of computers,2015,32(5):1 527-1 531.(in Chinese)
[14]张静. 基于面部图像分块处理和PCA算法的表情识别研究[D]. 西安:西安电子科技大学,2013.
ZHANG J. Research on facial expression recognition based on face-image-divided processing and PCA algorithm[D]. Xi’an:Xidian university,2013.(in Chinese)
[15]陈鹏飞,王靖. 基于形状识别的人脸轮廓线提取[J]. 计算机工程与设计,2014,35(3):890-894.CHEN P F,WANG J. Contour extraction of human face based on shape recognition[J]. Computer engineering and design,2014,35(3):890-894.(in Chinese)
[16]WISSAM J B,JISOO S,DAE H K,et al. A deep facial landmarks detection with facial contour and facial components constraint[C]//IEEE international conference on image processing. USA:IEEE,2016:3209-3213.

相似文献/References:

[1]曹金梦,倪蓉蓉,杨 彪.面向面部表情识别的双通道卷积神经网络[J].南京师范大学学报(工程技术版),2018,18(03):001.[doi:10.3969/j.issn.1672-1292.2018.03.001]
 Cao Jinmeng,Ni Rongrong,Yang Biao.Binary-Channel Convolutional Neural Network forFacial Expression Recognition[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(02):001.[doi:10.3969/j.issn.1672-1292.2018.03.001]
[2]吕 晶,薛亚非,谷静平.像素邻域差向量协方差特征的多视角人脸检测[J].南京师范大学学报(工程技术版),2022,22(02):073.[doi:10.3969/j.issn.1672-1292.2022.02.011]
 Lü Jing,Xue Yafei,Gu Jingping.Multi-view Face Detection Based on the Pixel Differential Covariance Feature[J].Journal of Nanjing Normal University(Engineering and Technology),2022,22(02):073.[doi:10.3969/j.issn.1672-1292.2022.02.011]
[3]陈 斌,樊飞燕,张 睿.年龄算子深度稀疏融合扩展表情识别[J].南京师范大学学报(工程技术版),2023,23(03):043.[doi:10.3969/j.issn.1672-1292.2023.03.006]
 Chen Bin,Fan Feiyan,Zhang Rui.Age Operator Deep Sparse Fusion Extension of the Expression Recognition[J].Journal of Nanjing Normal University(Engineering and Technology),2023,23(02):043.[doi:10.3969/j.issn.1672-1292.2023.03.006]

备注/Memo

备注/Memo:
收稿日期:2016-09-23.
基金项目:国家自然科学基金(61601228、51407095)、江苏省自然科学基金(BK20161021、BK20151548)、江苏省高校自然科学基金(15KJB510016)、江苏省三维打印装备与制造重点实验室项目(BM2013006)资助开放课题(3DL201607).
通讯联系人:谢非,博士,讲师,研究方向:机器视觉与图像处理、人工智能与模式识别. E-mail:xiefei@njnu.edu.cn
更新日期/Last Update: 2017-06-30