|Table of Contents|

A Facial Expression Recognition Method Based onSkin Color Enhancement and Block PCA(PDF)

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

Issue:
2017年02期
Page:
49-
Research Field:
计算机工程
Publishing date:

Info

Title:
A Facial Expression Recognition Method Based onSkin Color Enhancement and Block PCA
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)
Keywords:
face detectionfacial expression recognitionprincipal component analysisskin model
PACS:
TP312
DOI:
10.3969/j.issn.1672-1292.2017.02.008
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.

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.

Memo

Memo:
-
Last Update: 2017-06-30