基于動態(tài)時間規(guī)整和主動外觀模型的動態(tài)表情識別

許良鳳; 王家勇; 崔婧楠; 胡敏; 張柯柯; 滕文娣

doi:10.11999/JEIT170416

基于動態(tài)時間規(guī)整和主動外觀模型的動態(tài)表情識別

doi: 10.11999/JEIT170416

1.
(合肥工業(yè)大學(xué)計算機與信息學(xué)院合肥 230009)
2.
(華南理工大學(xué)計算機與信息學(xué)院廣州 510006)

基金項目:

國家自然科學(xué)基金(61300119, 61432004)，安徽省自然科學(xué)基金(1408085MKL16)

計量
- 文章訪問數(shù): 1140
- HTML全文瀏覽量: 197
- PDF下載量: 150
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-05-05
- 修回日期: 2017-11-08
- 刊出日期: 2018-02-19

Dynamic Expression Recognition Based on Dynamic Time Warping and Active Appearance Model

1.
(School of Computer and Information, Hefei University of Technology, Hefei 230009, China)
2.
(School of Computer and Information, South China University of Technology, Guangzhou 510006, China)
3.
(School of Computer and Information, Hefei University of Technology, Hefei 230009, China)

Funds:

The National Natural Science Foundation of China (61300119, 61432004), The National Natural Science Foundation of Anhui Province (1408085MKL16)

摘要

摘要: 針對靜態(tài)表情特征缺乏時間信息，不能充分體現(xiàn)表情的細(xì)微變化，該文提出一種針對非特定人的動態(tài)表情識別方法：基于動態(tài)時間規(guī)整(Dynamic Time Warping, DTW)和主動外觀模型(Active Appearance Model, AAM)的動態(tài)表情識別。首先采用基于局部梯度DT-CWT(Dual-Tree Complex Wavelet Transform)主方向模式(Dominant Direction Pattern, DDP)特征的DTW對表情序列進行規(guī)整。然后采用AAM定位出表情圖像的66個特征點并進行跟蹤，利用中性臉的特征點構(gòu)建人臉幾何模型，通過人臉幾何模型的匹配克服不同人呈現(xiàn)表情的差異，并通過計算表情序列中相鄰兩幀圖像對應(yīng)特征點的位移獲得表情的變化特征。最后采用最近鄰分類器進行分類識別。在CK+庫和實驗室自建庫HFUT-FE(HeFei University of Technology-Face Emotion)上的實驗結(jié)果表明，所提算法具有較高的準(zhǔn)確性。
- 動態(tài)表情識別 /
- 動態(tài)時間規(guī)整 /
- 主動外觀模型 /
- 雙樹復(fù)小波變換 /
- 主方向模式
Abstract: To overcome the deficiency of static expression feature, which lacks time information and can not reflect the subtle changes of expression adequately, a dynamic expression recognition method is proposed for non-specific face: the dynamic expression recognition based on Dynamic Time Warping (DTW) and Active Appearance Model (AAM). Firstly, the method of DTW based on local gradient Dual Tree-Complex Wavelet Transform (DT-CWT) dominant direction pattern is used to warp expression sequence. Secondly, using AAM to locate 66 feature points of face image and track them. The changing feature of expression can be obtained by calculating the displacement of corresponding feature points in two adjacent expression sequences image. And using the feature points of neutral face to build the facial geometry model. The matching of facial geometry model can overcome the expression differences between various people. Finally, the nearest neighbor classifier is used for classification and recognition. The experimental results on CK+ database and HeFei University of Technology-Face Emotion (HFUT-FE) database show that the proposed algorithm has a high degree of accuracy.
- Dynamic expression recognition /
- Dynamic Time Warping (DTW) /
- Active Appearance Model (AAM) /
- Dual Tree-Complex Wavelet Transform (DT-CWT) /
- Dominant direction pattern

HTML全文

參考文獻(25)

於俊, 汪增福, 李睿. 一種同步人臉運動跟蹤與表情識別算法[J]. 電子學(xué)報, 2015, 43(2): 371-376. doi: 10.3969/j.issn. 0372-2112.2015.02.025.

MEHRABIAN A. Communication without words[J]. Psychological Today, 1968, 2: 53-55.

YU Jun, WANG Zengfu, and LI Rui. A simultaneous facial motion tracking and expression recognition algorithm[J]. Acta Electronica Sinica, 2015, 43(2): 371-376. doi: 10.3969/ j.issn.0372-2112.2015.02.025.

JIA J, XU Y, ZHANG S, et al. The facial expression recognition method of random forest based on improved PCA extracting feature[C]. IEEE International Conference on Signal Processing, Communications and Computing, Hong Kong, China. 2016: 1-5. doi: 10.1109/ICSPCC.2016.7753643.

REN Fuji and HUANG Zhong. Facial expression recognition based on AAM-SIFT and adaptive regional weighting[J]. IEEE Transactions on Electrical Electronic Engineering, 2015, 10(6): 713-722. doi: 10.1002/tee.22151.

LI Y, REN F, and HU M. Facial expression recognition based on DT-CWT and weighted inverse cloud model[C]. Modelling, Simulation and Identification 841: Intelligent Systems and Control, Campinas, Brazil. 2016: 380-388. doi: 10.2316/P. 2016.841-010.

ZHAO Guoying and PIETIKAINEN Matti. Dynamic texture recognition using local binary patterns with an application to facial expressions[J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2007, 29(6): 915-928.

JIANG Bihan, VALSTAR Member, MARTINEZ Brais, et al. A dynamic appearance descriptor approach to facial actions temporal modeling[J]. IEEE Transactions on Cybernetics, 2014, 44(2): 161-174. doi: 10.1109/tcyb.2013.2249063.

TAHERI Sima, QIU Qiang, and CHELLAPPA Rama. Structure-preserving sparse decomposition for facial expression analysis[J]. IEEE Transactions on Image Processing, 2014, 23(8): 3590-3603. doi: 10.1109/tip.2014. 2331141.

FAN Xijian and TJAHJADI Tardi. 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. doi: 10.1016/j. patcog.2015.04.025.

施毅. 基于主動外觀模型的人臉表情識別研究[D]. [碩士論文], 上海交通大學(xué), 2012.

SHI Yi. Facial expression recognition based on active appearance models[D]. [Master dissertation], Shanghai Jiao Tong University, 2012.

CHEON Yeongjae and KIM Daijin. Natural facial expression recognition using differential-AAM and manifold learning[J]. Pattern Recognition, 2009, 42(7): 1340-1350. doi: 10.1016/ j.patcog.2008.10.010.

LEE Yonghwan, HAN Wuri, KIM Youngseop, et al. Robust emotion recognition algorithm for ambiguous facial expression using optimized AAM and k-NN[J]. International Journal of Security Its Applications, 2014, 8(5): 203-212. doi: 10.14257/ijsia.2014.8.5.19.

HIYADI H, ABABSA F, MONTAGNE C, et al. Combination of HMM and DTW for 3D Dynamic gesture recognition using depth only[C]. Informatics in Control, Automation and Robotics 12th International Conference, ICINCO 2015, Colmar, France, 2016: 229-245. doi: 10.1007/978-3-319- 31898-1_13.

傅穎, 郭晶云. 基于動態(tài)時間規(guī)整的人體動作識別方法[J]. 電子測量技術(shù), 2014, 37(3): 69-72. doi: 10.3969/j.issn.1002-7300. 2014.03.018.

FU Ying and GUO Jingyun. Dynamic time warping-based human action recognition[J]. Electronic Measurement Technology, 2014, 37(3): 69-72. doi: 10.3969/j.issn.1002-7300. 2014.03.018.

宋怡煥, 饒秀勤, 應(yīng)義斌. 基于DT-CWT和LS-SVM的蘋果果梗/花萼和缺陷識別[J]. 農(nóng)業(yè)工程學(xué)報, 2012, 28(9): 114-118. doi: 10.3969/j.issn.1002- 6819.2012.09.019.

SONG Yihuan, RAO Xiuqin, and YING Yibing. Apple stem/ calyx and defect discrimination using DT-CWT and LS-SVM [J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(9): 114-118. doi: 10.3969/j.issn.1002- 6819.2012.09.019.

胡敏, 朱弘, 王曉華, 等. 基于梯度Gabor直方圖特征的表情識別方法[J]. 計算機輔助設(shè)計與圖形學(xué)學(xué)報, 2013, 25(12): 1856-1861.

HU Min, ZHU Hong, WANG Xiaohua, et al. Expression recognition method based on gradient Gabor histogram features[J]. Journal of Computer-Aided Design Computer Graphics, 2013, 25(12): 1856-1861.

LIU Jun, JING Xiaojun, SUN Songlin, et al. Local gabor dominant direction pattern for face recognition[J]. Chinese Journal of Electronics, 2015, 24(2): 245-250. doi: 10.1049/cje. 2015.04.004.

HUANG M W, WANG Z W, and YING Z L. A new method for facial expression recognition based on sparse representation plus LBP[C]. IEEE International Congress on Image and Signal Processing, Yantai, China, 2010: 1750-1754. doi: 10.1109/cisp.2010.5647898.

WANG Zhen and YING Zilu. Facial expression recognition based on local phase quantization and sparse representation [J]. IEEE International Conference on Natural Computation, 2012, 2: 222-225. doi: 10.1109/icnc.2012.6234551.

ZHANG Shiqing, ZHAO Xiaoming, and LEI Bicheng. Robust facial expression recognition via compressive sensing[J]. Sensors, 2012, 12(3): 3747-3761. doi: 10.3390/s120303747.

相關(guān)文章

施引文獻

資源附件(0)

訪問統(tǒng)計