融合局部紋理和形狀特征的人臉表情識別
doi: 10.11999/JEIT170799
-
2.
(合肥工業(yè)大學(xué)計算機(jī)與信息學(xué)院 合肥 230009) ②(情感計算與先進(jìn)智能機(jī)器安徽省重點實驗室 合肥 230009)
國家自然科學(xué)基金項目(61672202, 61432004, 61502141),國家自然科學(xué)基金-深圳聯(lián)合基金重點項目(U1613217),安徽高校省級自然科學(xué)研究重點項目(KJ2017A368)
Facial Expression Recognition Based on Local Texture and Shape Features
-
2.
(School of Computer and Information of Hefei University of Technology, Hefei 230009, China)
The National Natural Science Foundation of China (61672202, 61432004, 61502141), The National Natural Science Foundation of China-Shenzhen Joint Foundation (Key Project) (U1613217), The Key University Science Research Project of Anhui Province (KJ2017A368)
-
摘要: 針對局部二值模式(LBP)、中心對稱局部二值模式(CS-LBP)和梯度方向直方圖(HOG)的不足進(jìn)行改進(jìn),該文提出中心對稱局部平滑二值模式(CS-LSBP)和絕對梯度方向直方圖(HOAG),并提出一種融合局部紋理特征和局部形狀特征的人臉表情識別方法。該方法首先采用CS-LSBP算子和HOAG算子分別提取人臉表情圖像的局部紋理特征和局部形狀特征,然后使用典型線性分析法(CCA)進(jìn)行特征融合,最后利用支持向量機(jī)(SVM)進(jìn)行表情分類。在JAFFE人臉表情庫和Cohn-Kanade(CK)人臉表情庫上的實驗結(jié)果表明,改進(jìn)的特征提取方法能更加完整、精確地提取圖像的細(xì)節(jié)信息,基于CCA的特征融合方法能充分發(fā)揮特征的表征能力,該文所提人臉表情識別方法取得了較好的分類識別效果。
-
關(guān)鍵詞:
- 人臉表情識別 /
- 中心對稱局部平滑二值模式 /
- 絕對梯度方向直方圖 /
- 典型相關(guān)分析
Abstract: In order to improve the inadequacies of Local Binary Pattern (LBP), Center-Symmetric Local Binary Pattern (CS-LBP) and Histogram of Oriented Gradient (HOG) algorithm, Center-Symmetric Local Smooth Binary Pattern (CS-LSBP) and Histogram of Oriented Absolute Gradient (HOAG) are proposed, and a facial expression recognition method based on local texture and local shape features is proposed in this paper. Firstly, CS-LSBP and HOAG are used to extract two local features of expression image of the face. Then, Canonical Correlation Analysis (CCA) is used to fuse two local features. Finally, Support Vector Machine (SVM) is performed for the expression classification. Experimental results on JAFFE and Cohn-Kanade (CK) facial expression databases show that, the improved feature extraction method can extract the detail information of the image more completely and accurately. And the fusion method based on CCA can give full play to the representation ability of each feature. The facial expression recognition method proposed in this paper obtains a better recognition effect. -
付曉峰, 韋巍. 基于多尺度中心化二值模式的人臉表情識別[J]. 控制理論與應(yīng)用, 2009, 26(6): 629-633. KYPEROUNTAS M, TEFAS A, and PITAS I. Salient feature and reliable classifier selection for facial expression classification[J]. Pattern Recognition, 2010, 43(3): 972-986. doi: 10.1016/j.patcog.2009.07.007. FU Xiaofeng and WEI Wei. Facial expression recognition based on multi-scale centralized binary pattern[J]. Control Theory Applications, 2009, 26(6): 629-633. UAR A, DEMIR Y, and GZELI C. A new facial expression recognition based on curvelet transform and online sequential extreme learning machine initialized with spherical clustering[J]. Neural Computing and Applications, 2016, 27(1): 131-142. doi: 10.1007/s00521-014-1569-1. TAN H C, ZHANG Y J, HAO C, et al. Person-independent expression recognition based on person-similarity weighted expression feature[J]. Journal of Systems Engineering and Electronics, 2010, 21(1): 118-126. doi: 10.3969/j.issn.1004- 4132.2010.01.019. ZHANG S, ZHAO X, and LEI B. Facial expression recognition based on local binary patterns and local fisher discriminant analysis[J]. WSEAS Transactions on Signal Processing, 2012, 8(1): 21-31. WANG Z, RUAN Q, and AN G. Facial expression recognition using sparse local Fisher discriminant analysis[J]. Neurocomputing, 2016, 174(174): 756-766. doi: 10.1016/ j.neucom.2015.09.083. ZHAO X and ZHANG S. Facial expression recognition based on local binary patterns and kernel discriminant isomap[J]. Sensors, 2011, 11(10): 9573-9588. doi: 10.3390/s111009573. CHEN J, TAKIGUCHI T, and ARIKI Y. Rotation-reversal invariant HOG cascade for facial expression recognition[J]. Signal Image Video Processing, 2017(1-3): 1-8. doi: 10.1007 /s11760-017-1111-x. HEGDE G, SEETHA M, and HEGDE N. Facial expression recognition using entire gabor filter matching score level fusion approach based on subspace methods[J]. Microelectronics Reliability, 2015, 52(3): 497-502. doi: 10.1007/978-3-319-26832-3_6. ZHOU H, LAM K M, and HE X. Shape-appearance- correlated active appearance model[J]. Pattern Recognition, 2016, 56(C): 88-99. doi: 10.1016/j.patcog.2016.03.002. OJALA T, PIETIKINEN M, and HARWOOD D. A comparative study of texture measures with classification based on featured distributions[J]. Pattern recognition, 1996, 29(1): 51-59. doi: 10.1016/0031-3203(95)00067-4. HEIKKIL M, PIETIKINEN M, and SCHMID C. Description of interest regions with local binary patterns[J]. Pattern Recognition, 2009, 42(3): 425-436. doi: 10.1016/ j.patcog.2008.08.014. 王曉華, 李瑞靜, 胡敏, 等. 融合局部特征的面部遮擋表情識別[J]. 中國圖象圖形學(xué)報, 2016, 21(11): 1473-1482. doi: 10.11834/jig.20161107. WANG Xiaohua, LI Ruijing, HU Min, et al. Occluded facial expression recognition based on the fusion of local features[J]. Journal of Image and Graphics, 2016, 21(11): 1473-1482. doi: 10.11834/jig.20161107. 楊利平, 辜小花. 用于人臉識別的相對梯度直方圖特征描述[J]. 光學(xué)精密工程, 2014, 22(1): 152-159. doi: 10.3788/OPE. 20142201.0152. YANG Liping and GU Xiaohua. Relative gradient histogram features for face recognition[J]. Optics and Precision Engineering, 2014, 22(1): 152-159. doi: 10.3788/OPE. 20142201.0152. 劉帥師, 田彥濤, 萬川. 基于Gabor多方向特征融合與分塊直方圖的人臉表情識別方法[J]. 自動化學(xué)報, 2011, 37(12): 1455-1463. doi: 10.3724/SP.J.1004.2011.01455. LIU Shuishi, TIAN Yantao, and WAN Chuan. Facial expression recognition method based on gabor multi- orientation features fusion and block histogram[J]. Acta Automatica Sinica, 2011, 37(12): 1455-1463. doi: 10.3724 /SP.J.1004.2011.01455. TURAN C and LAM K M. Region-based feature fusion for facial-expression recognition[C]. IEEE International Conference on Image Processing, Paris, 2014: 5966-5970. doi: 10.1109/ICIP.2014.7026204. 易積政, 毛峽, ISHIZUKA M, 等. 基于特征點矢量與紋理形變能量參數(shù)融合的人臉表情識別[J]. 電子與信息學(xué)報, 2013, 35(10): 2403-2410. doi: 10.3724/SP.J.1146.2012.01569. YI Jizheng, MAO Xia, ISHIZUKA M, et al. Facial expression recognition based on feature point vector and texture deformation energy parameters[J]. Journal of Electronics Information Technology, 2013, 35(10): 2403-2410. doi: 10.3724/SP.J.1146.2012.01569. 胡敏, 江河, 王曉華, 等. 基于幾何和紋理特征的表情層級分類方法[J]. 電子學(xué)報, 2017, 45(1): 164-172. doi: 10.3969/ j.issn.0372-2112.2017.01.023. HU Min, JIANG He, WANG Xiaohua, et al. A hierarchical classification method of expressions based on geometric and texture features[J]. Acta Electronica Sinica, 2017, 45(1): 164-172. doi: 10.3969/j.issn.0372-2112.2017.01.023. 孫權(quán)森, 曾生根, 王平安, 等. 典型相關(guān)分析的理論及其在特征融合中的應(yīng)用[J]. 計算機(jī)學(xué)報, 2005, 28(9): 1524-1533. doi: 10.3321/j.issn:0254-4164.2005.09.015. SUN Quansen, ZENG Shenggen, WANG Pingan, et al. The theory of canonical correlation analysis and its application to feature fusion[J]. Chinese Journal of Computers, 2005, 28(9): 1524-1533. doi: 10.3321/j.issn:0254-4164.2005.09.015. -
計量
- 文章訪問數(shù): 1612
- HTML全文瀏覽量: 223
- PDF下載量: 314
- 被引次數(shù): 0