Group Sparse Representation Based on Feature Selection and Dictionary Optimization for Expression Recognition
XIE Huihua1,2, LI Ming1,2, WANG Yan2, CHEN Hao1,2
1. School of Information Engineering, Nanchang Hangkong University, Nanchang 330063; 2. Key Laboratory of Nondestructive Testing, Ministry of Education, Nanchang Hangkong University, Nanchang 330063
Abstract To solve the over-fitting problem of recognition model on small sample facial expression database, a group sparse representation classification method based on feature selection and dictionary optimization is put forward. Firstly, the feature selection criterion is proposed, and the complementary features of same class-level sparse mode and different intra-class sparse mode are selected to build a dictionary. Then, the dictionary is learned by maximum scatter difference optimization to reconstruct features without distortion and acquire a high discriminative ability. Finally, the optimized dictionary is combined for group sparse representation classification. Experiments on JAFFE and CK+ databases show that the proposed method is robust to sample reduction with high generalization ability and recognition accuracy.
Fund:National Natural Science Foundation of China(No.61866025,61772255,61440049), Science and Technology Pro-ject of Jiangxi Education Department(No. GJJ170608), Jiangxi Postgraduate Innovation Project(No.YC2019-S339), Open Fund of Key Laboratory of Image Processing and Pattern Recognition of Jiangxi Province(No.ET201604246)
Corresponding Authors:
LI Ming, Ph.D., professor. His research interests include image processing, pattern recognition and many-objective optimization problem.
About author:: XIE Huihua, master student. Her research interests include image processing and pattern recognition.WANG Yan, Ph.D., lecturer. Her research interests include image processing and pattern recognition.CHEN Hao, Ph.D., associate professor. His research interests include evolutionary algorithms, image processing and pattern recognition.
XIE Huihua,LI Ming,WANG Yan等. Group Sparse Representation Based on Feature Selection and Dictionary Optimization for Expression Recognition[J]. , 2021, 34(5): 446-454.
[1] CORNEANU C A,SIMÓN M O,COHN J F,et al. Survey on RGB,3D,Thermal,and Multimodal Approaches for Facial Expre-ssion Recognition:History,Trends,and Affect-Related Applications.IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(8):1548-1568. [2] POURSABERI A,NOUBARI H A,GAVRILOVA M,et al. Gauss-Laguerre Wavelet Textural Feature Fusion with Geometrical Information for Facial Expression Identification.EURASIP Journal on Image and Video Processing,2012.DOI:10.1186/1687-5281-2012-17. [3] WANG X H,LIU A,ZHANG S Q.New Facial Expression Recognition Based on FSVM and KNN.Optik,2015,126(21):3132-3134. [4] JIANG X G,FENG B,JIN L N.Facial Expression Recognition via Sparse Representation Using Positive and Reverse Templates.IET Image Processing,2016,10(8):616-623. [5] OUYANG Y,SANG N,HUANG R.Accurate and Robust Facial Expressions Recognition by Fusing Multiple Sparse Representation Based Classifiers.Neurocomputing,2015,149:71-78. [6] LEKDIOUI K,MESSOUSSI R,RUICHEK Y,et al.Facial Decomposition for Expression Recognition Using Texture/Shape Descriptors and SVM Classifier.Signal Processing:Image Communication,2017,58:300-312. [7] ZHANG X,MAHOOR M H,MAVADATI S M.Facial Expression Recognition Using l_p-norm MKL Multiclass-SVM.Machine Vision and Applications,2015,26(4):467-483. [8] VASANTH P C,NATARAJ K R.Facial Expression Recognition Using SVM Classifier.Indonesian Journal of Electrical Engineering and Informatics,2015,3(1):16-20. [9] MELLOUK W,HANDOUZI W.Facial Emotion Recognition Using Deep Learning:Review and Insights.Procedia Computer Science,2020,175:689-694. [10] LOPES A T,DE AGUIAR E,DE SOUZA A F,et al. Facial Expression Recognition with Convolutional Neural Networks:Coping with Few Data and the Training Sample Order.Pattern Recognition,2017,61:610-628. [11] HUANG J Z,ZHANG T.The Benefit of Group Sparsity.The Annuals of Statistics,2010,38(4):1978-2004. [12] SHAFIEE S,KAMANGAR F,ATHITSOS V,et al. Multimodal Sparse Representation Classification with Fisher Discriminative Sample Reduction//Proc of the IEEE International Conference on Image Processing.Washington,USA:IEEE,2014:5192-5196. [13] SUN Z,HU Z P,WANG M,et al. Robust Facial Expression Re-cognition with Low-Rank Sparse Error Dictionary Based Probabilistic Collaborative Representation Classification.International Journal of Artificial Intelligence Tools,2017,26(4).DOI:10.1142/S0218213017500178. [14] XIE S Y,HU H F,YIN Z Y.Facial Expression Recognition Using Intra-class Variation Reduced Features and Manifold Regularisation Dictionary Pair Learning.IET Computer Vision,2018,12(4):458-465. [15] HUANG B B,YING Z L.Sparse Autoencoder for Facial Expre-ssion Recognition//Proc of the 12th IEEE International Confe-rence on Ubiquitous Intelligence and Computing and the 12th IEEE International Conference on Autonomic and Trusted Computing and the 15th IEEE International Conference on Scalable Computing and Communications and Its Associated Workshops.Washington,USA:IEEE,2015:1529-1532. [16] DAPOGNY A,BAILLY K,DUBUISSON S.Dynamic Facial Expression Recognition by Joint Static and Multi-time Gap Transition Classification//Proc of the 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition.Wa-shington,USA:IEEE,2015,I.DOI:10.1109/FG.2015.7163111. [17] MOEINI A,FAEZ K,MOEINI H,et al.Facial Expression Recognition Using Dual Dictionary Learning.Journal of Visual Communication and Image Representation,2017,45:20-33. [18] ZHANG W,ZHANG Y M,MA L,et al.Multimodal Learning for Facial Expression Recognition.Pattern Recognition,2015,48(10):3191-3202. [19] JIA Q,GAO X K,GUO H,et al.Multi-layer Sparse Representation for Weighted LBP-Patches Based Facial Expression Recognition.Sensors,2015,15(3):6719-6739. [20] ZHANG Z,XU Y,YANG J,et al. A Survey of Sparse Represen-tation:Algorithms and Applications.IEEE Access,2015,3:490-530. [21] GHADIMI E,TEIXEIRA A,SHAMES I,et al.Optimal Parameter Selection for the Alternating Direction Method of Multipliers(ADMM):Quadratic Problems.IEEE Transactions on Automatic Control,2015,60(3):644-658. [22] 黎 明,彭秀姣,王 艳.基于改进的字典学习与稀疏表示的人脸表情识别.系统仿真学报,2018,30(1):28-35,44. (LI M,PENG X J,WANG Y.Facial Expression Recognition Based on Improved Dictionary Learning and Sparse Representation.Journal of System Simulation,2018,30(1):28-35,44.) [23] YANG M,ZHANG L,FENG X C,et al. Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification.International Journal of Computer Vision,2014,109(3):209-232. [24] 张善文,李 萍,井荣枝,等.基于最大散度差判别分析的一种目标识别方法.系统仿真学报,2013,25(3):441-444. (ZHANG S W,LI P,JING R Z,et al.Method of Target Recognition Based on Maximum Scatter-Difference Discriminant Analysis.Journal of System Simulation,2013,25(3):441-444.) [25] 李 勇,林小竹,蒋梦莹.基于跨连接LeNet-5网络的面部表情识别.自动化学报,2018,44(1):176-182. (LI Y,LIN X Z,JIANG M Y.Facial Expression Recognition with Cross-Connect LeNet-5 Network.Acta Automatica Sinica,2018,44(1):176-182.) [26] AAMIR M,ALI T,SHAF A,et al. ML DCN Net:Multi level Deep Convolutional Neural Network for Facial Expression Recognition and Intensity Estimation.Arabian Journal for Science and Engineering,2020,45(12):10605-10620. [27] LI K,JIN Y,AKRAM M W,et al.Facial Expression Recognition with Convolutional Neural Networks via a New Face Cropping and Rotation Strategy.The Visual Computer,2020,36(2):391-404. [28] 王 浩,栗永泽,方宝富.基于局部特征聚类损失和多类特征融合的面部表情识别.模式识别与人工智能,2020,33(3):268-276. (WANG H,LI Y Z,FANG B F.Locality Feature Aggregation Loss and Multi-feature Fusion for Facial Expression Recognition.Pattern Recognition and Artificial Intelligence,2020,33(3):268-276.)
2021, Vol. 34 
