[1]张御宇,倪蓉蓉,杨 彪.基于改进随机森林分类器在RGBD面部表情上的应用研究[J].南京师范大学学报(自然科学版),2019,42(01):82.[doi:10.3969/j.issn.1001-4616.2019.01.013]
 Zhang Yuyu,Ni Rongrong,Yang Biao.Research on Bimodal Facial Expression Based onImproved Random Forest Classifier[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(01):82.[doi:10.3969/j.issn.1001-4616.2019.01.013]
点击复制

基于改进随机森林分类器在RGBD面部表情上的应用研究()
分享到:

《南京师范大学学报》(自然科学版)[ISSN:1001-4616/CN:32-1239/N]

卷:
第42卷
期数:
2019年01期
页码:
82
栏目:
·人工智能算法与应用专栏·
出版日期:
2019-03-20

文章信息/Info

Title:
Research on Bimodal Facial Expression Based onImproved Random Forest Classifier
文章编号:
1001-4616(2019)01-0082-08
作者:
张御宇1倪蓉蓉2杨 彪1
(1.常州大学信息科学与工程学院,江苏 常州 213164)(2.常州纺织服装职业技术学院,江苏 常州 213164)
Author(s):
Zhang Yuyu1Ni Rongrong2Yang Biao1
(1.School of Information Science and Engineering,Changzhou University,Changzhou 213164,China)(2.Changzhou Vocational Institute of Textile and Garment,Changzhou 213164,China)
关键词:
面部检测面部表情识别RGBD面部图像特征选择随机森林面部几何特征
Keywords:
face detectionfacial expression recognitionRGBD facial imagesfeature selection based random forestfacial geometrical feature
分类号:
TP391
DOI:
10.3969/j.issn.1001-4616.2019.01.013
文献标志码:
A
摘要:
面部表情识别是机器感知人类情绪变化的重要途径. 利用面部RGB图像可以进行表情识别,但是容易受到光照变化影响,而且较难刻画细微表情变化. 对采用RGBD面部图像识别6种基本面部表情(高兴、悲伤、愤怒、沮丧、恐惧以及惊讶)进行研究. 首先利用深度图像鲁棒地检测面部; 然后在面部灰度图像中检测并跟踪二维面部标记点,并添加对应的深度信息构造深度面部几何特征,从而有效识别细微表情变化; 最后利用基于特征选择的随机森林分类器对不同面部表情进行识别. 基准数据库上的对比实验结果表明本文算法的表情识别准确率高于主流基于手动提取特征的面部表情识别方法,接近基于卷积神经网络的识别算法性能.
Abstract:
Facial expression recognition is an important way for machines to understand expression changes of human beings. Expression recognition using RGB facial images suffers from illumination changes and detail depicting in minor emotion changes. This work employ RGBD facial images to recognize 6 basic facial expressions(happiness,sadness,angry,disgust,fear and surprise). Depth images are used for robust face detection initially. Gray-scale facial images are employed to detect and to track 2D facial landmark points from the detected face region. Then,corresponding depth information is added into these points to construct depth facial geometrical feature which can recognize minor expression changes more effectively. Finally,a random forest classifier based on feature selection is designed to recognize different facial expressions. Results of comparative evaluations on benchmarking datasets verify the fact that our approach outperforms several state-of-the-art facial expression approaches,which use hand-crafted features,in recognizing six basic facial expressions. Meanwhile,our approach achieves almost similar performance comparing with the convolutional neural network based expression recognition algorithms.

参考文献/References:

[1] 黄建,李文书,高玉娟. 人脸表情识别研究进展[J]. 计算机科学,2016,43(S2):123-126.
[2]WU S Z,KAN M N,HE Z L,et al. Funnel-structured cascade for multi-view face detection with alignment-awareness[J]. Neurocomputing,2017,221:138-145.
[3]DEMIRKUS M,PRECUP D,CLARK J,et al. Multi-layer temporal graphical model for head pose estimation in real-world videos[C]//International Conference on Image Processing. China:IEEE,2014:3392-3396.
[4]JAIN S,HU C B,AGGARWAL J K. Facial expression recognition with temporal modeling of shapes[C]//The 13th International Conference on Computer Vision. Spain:IEEE,2011:1642-1649.
[5]ALI G,IQBAL M A,CHOI T S. Boosted NNE collections for multicultural facial expression recognition[J]. Pattern recognition,2016,55:14-27.
[6]ZHANG Y,ZHANG L,HOSSAIN M A. Adaptive 3D facial action intensity estimation and emotion recognition[J]. Expert systems with applications,2015,42(3):1446-1464.
[7]MOEINI A,FAEZ K,SADEGHI H,et al. 2D facial expression recognition via 3D reconstruction and feature fusion[J]. Journal of visual communication and image representation,2016,35:1-14.
[8]MOHAMMADI M,FATEMIZADEH E,MAHOOR M. Pca-based dictionary building for accurate facial expression recognition via sparse representation[J]. Journal of visual communication and image representation,2014,25(5):1082-1092.
[9]首照宇,杨晓帆. 联合Gabor误差字典和低秩表示的人脸识 别算法[J]. 计算机科学,2017,44(3):296-299.
[10]SHAN C,GONG S,MCOWAN P W. Facial expression recognition based on local binary patterns:a comprehensive study[J]. Image and vision computing,2009,27(6):803-816.
[11]蒋政,程春玲. 基于Haar特性的改进HOG的人脸特征提取算法[J]. 计算机科学,2017,44(1):303-307.
[12]KOBAYASHI H,HARA F. Facial interaction between animated 3d face robot and human beings[C]//IEEE International Conference on Computational Cybernetics and Simulation. USA:IEEE,1997:3732-3737.
[13]KENJI M. Recognition of facial expression from optical flow[J]. Ieice transactions on information and systems,1991,74(10):3474-3483.
[14]VALSTAR M,PANTIC M,PATRAS I. Motion history for facial action detection in video[C]//IEEE International Conference on Systems,Man and Cybernetics. Netherland:IEEE,2004:635-640.
[15]ZHAO G,PIETIKAINEN M. Dynamic texture recognition using local binary patterns with an application to facial expressions[J]. IEEE transactions on pattern analysis and machine intelligence,2007,29(6):915-928.
[16]ZHAO X M,SHI X G,ZHANG S Q. Facial expression recognition via deep learning[J]. IETE technical review,2015,32(5):347-355.
[17]卢官明,何嘉利,闫静杰,等. 一种用于人脸表情识别的卷积神经网络[J]. 南京邮电大学学报(自然科学版),2016,36(1):16-22.
[18]YU Z D,ZHANG C. Image based static facial expression recognition with multiple deep network learning[C]//Proceedings of the 2015 Acm International Conference on Multimodal Interaction. Netherland:ACM,2015:435-442.
[19]FAN X,JIA Q,HU Y K,et al. 3D facial landmark localization using texture regression via conformal mapping[J]. Pattern recognition letters,2016,83:395-402.
[20]DANELAKIS A,THEOHARIS T,PRATIKAKIS I. A spatio-temporal wavelet-based descriptor for dynamic 3D facial expression retrieval and recognition[J]. The visual computer,2016,32(6):1001-1011.
[21]KUNG S H,ZOHDY M A,BOUCHAFFRA D. 3D HMM-based facial expression recognition using histogram of oriented optical flow[J]. Transactions on machine learning and artificial intelligence,2016,3(6):42.
[22]ZHEN Q,HUANG D,WANG Y,et al. Muscular movement model-based automatic 3D/4D facial expression recognition[J]. IEEE transactions on multimedia,2016,18(7):1438-1450.
[23]ZHANG Z,CUI L,LIU X,et al. Emotion detection using Kinect 3D facial points[C]//International Conference on Web Intelligence. USA:IEEE,2016:407-410.
[24]BARNOUTI N H,ALDABBAGH S S M,MATTI W E,et al. Face detection and recognition using Viola-Jones with PCA-LDA and square euclidean distance[J]. International journal of advanced computer science and applications,2016,7(5):371-377.
[25]CHENG S,ASTHANA A,ZAFEIRIOU S,et al. Real-time generic face tracking in the wild with cuda[C]//Proceedings of the 5th ACM Multimedia Systems Conference. USA:ACM,2014:148-151.
[26]BALTRUSAITIS T,ROBINSON P,MORENCY L P. Constrained local neural fields for robust facial landmark detection in the wild[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops. Australia:IEEE,2013:354-361.
[27]LI B,MIAN A,LIU W,et al. Using kinect for face recognition under varying poses,expressions,illumination and disguise[C]//IEEE Workshop on Applications of Computer Vision. Florida:IEEE,2013:186-192.
[28]ALY S,TRUBANOVA A,ABBOTT L,et al. VT-KFER:A Kinect-based RGBD+Time dataset for spontaneous and non-spontaneous facial expression recognition[C]//International Conference on Biometrics. USA:IEEE,2015:90-97.
[29]ALY S,ABBOTT A L,TORKI M. A multi-modal feature fusion framework for kinect-based facial expression recognition using Dual Kernel Discriminant Analysis(DKDA)[C]//IEEE Winter Conference on Applications of Computer Vision. USA:IEEE,2016:1-10.
[30]FAN X,TJAHJADI T. A spatial-temporal framework based on histogram of gradients and optical flow for facial expression recognition in video sequences[J]. Pattern recognition,2015,48(11):3407-3416.
[31]RIVERA A R,CASTILLO J R,CHAE O O. Local directional number pattern for face analysis:Face and expression recognition[J]. IEEE transactions on image processing,2013,22(5):1740-1752.
[32]ZHANG W,ZHANG Y M,MA L,et al. Multimodal learning for facial expression recognition[J]. Pattern recognition,2015,48(10):3191-3202.

备注/Memo

备注/Memo:
收稿日期:2018-08-16.
基金项目:国家自然科学基金(61501060)、江苏省科技厅青年基金(BK20150271)、江苏省道路载运工具新技术应用重点实验室开放课题(ZMF15020068).
通讯联系人:杨彪,博士,讲师,研究方向:机器视觉、模式识别. E-mail:yb6864171@cczu.edu.cn
更新日期/Last Update: 2019-03-30