Zhe SUN, Meng WANG, Zhengping HU, huhuan SZHAO

Adaptive joint block-weighted collaborative representation for facial expression recognition

Facial expression recognition (FER) plays a signi cant role in human-computer interactions. Recently, regularized linear representation-based classi cation has achieved satisfying results in FER. Considering that different blocks in a sample should contribute differently to the representation and classi cation, we propose an adaptive joint block-weighted collaborative representation-based classi cation (JBW CRC) method to effectively exploit the similarity and distinctiveness of different blocks. In JBW CRC, samples are divided into different blocks and each block of the query sample is represented as a feature vector. Each feature vector is coded on its related block dictionary, which considers the similarity among the feature vectors. Additionally, the distinctiveness of different feature vectors is obtained by weighting its distance to other features, which addresses the distinctiveness in the different feature vectors. The proposed method is veri ed from the aspect of training samples, time complexity, and Gaussian noise variances on benchmark databases and the extensive experiments show that the proposed method is very competitive with some similar pattern classi cation methods.

PDF

___

[1] Lee SH, Baddar WJ, Yong MR. Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos. Pattern Recogn 2016; 54: 52-67.
[2] Happy SL, Routray A. Automatic facial expression recognition using features of salient facial patches. IEEE Transactions on Affective Computing 2015; 6: 1-12.
[3] Shao J, Gori I, Wan S, Aggarwal JK. 3D Dynamic facial expression recognition using low-resolution videos. Pattern Recogn Lett 2015; 65: 157-162.
[4] Yusuf R, Sharma DG, Tanev I, Shimohara K. Evolving an emotion recognition module for an intelligent agent using genetic programming and a genetic algorithm. Arti cial Life and Robotics 2016; 21: 85-90.
[5] Pablos SM, Garca-Bermejo JG, Casanova EZ, Lopez J. Dynamic facial emotion recognition oriented to HCI applications. Interact Comput 2015; 27: 99-199.
[6] Ekman P, Friesen WV. A new pan-cultural facial expression of emotion. Motivation & Emotion 1986; 10: 159-168.
[7] Ekman P, Rolls ET, Perrett DI, Ellis HD. Facial expressions of emotion: an old controversy and new ndings. Philosophical Transactions of the Royal Society of London 1992; 335: 63-69.
[8] Ekman P, Friesen WV, Ellsworth P. Sampling Emotion Words, Categories, or Dimensions in Judgment Studies. in: Ekman P, editor. Emotion in the Human Face. Emotion in the Human Face. Cambridge, UK: Cambridge University Press, 1998. pp. 45-47.
[9] Fang Y, Chang L. Multi-instance feature learning based on sparse representation for facial expression recognition. Lect Notes Comput Sc 2015; 8935: 224-233.
[10] Ma D, Li M, Nian F, Kong C. Facial expression recognition based on characteristics of block LGBP and sparse representation. Journal of Computational Methods in Sciences and Engineering 2015; 15: 537-547.
[11] Zhang S, Zhao X, Lei B. Facial expression recognition using sparse representation. WSEAS Transactions on Systems 2015; 11: 440-452.
[12] Guo Y, Zhao G, Pietikainen M. Dynamic facial expression with atlas construction and sparse representation. IEEE T Image Process 2016; 25: 1977-1992.
[13] Mery D, Bowyer K. Automatic facial attribute analysis via adaptive sparse representation of random patches. Pattern Recogn Lett 2015; 68: 260-269.
[14] Yan Q, Song N, Huang R. Accurate and robust facial expressions recognition by fusing multiple sparse representation based classi ers. Neurocomputing 2015; 149: 71-78.
[15] Shi Q, Eriksson A, Hengel AVD, Shen C. Is face recognition really a Compressive Sensing problem? Computer Vision and Pattern Recognition 2011; 42: 553-560.
[16] Waqas J, Yi Z, Lei Z. Collaborative neighbor representation based classi cation using l2-minimization approach. Pattern Recogn Lett 2013; 34: 201-208.
[17] Yang W, Wang Z, Yin J, Sun C, Ricanek K. Image classi cation using kernel collaborative representation with regularized least square. Appl Math Comput 2013; 222: 13-28.
[18] Zhang L, Yang M, Feng X. Spares representation or collaborative representation: which helps face recognition? International Conference on Computer Vision 2011; 6669: 471-478.
[19] Wang D, Lu H, Yang MH. Kernel collaborative face recognition. Pattern Recogn 2015; 48: 3025-3037.
[20] Yang W, Ricanek K, Shen F. Image classi cation using local linear regression. Neural Comput Appl 2014; 25: 1913-1920.
[21] Dong Y, Tao D, Li X, Ma J, Pu J. Texture classi cation and retrieval using shearlets and linear regression. IEEE T Cybern 2015; 45: 358-369.
[22] Wu J, Yang H. Linear Regression-Based Efficient SVM Learning for Large-Scale classi cation. IEEE T Neural Networ 2015; 26: 2357-2369.
[23] Huang HF, Tai SC. Facial expression recognition using new feature extraction algorithm. Electronic Letters on Computer Vision and Image Analysis 2012; 11: 41-54.
[24] Nan D, Xu Z, Bian SQ. Face recognition based on multi-classi er weighted optimization and sparse representation. International Journal of Signal Processing Image Processing and Pattern Recognition 2013; 6: 423-436.
[25] Tian Y. Evaluation of face resolution for expression analysis. Conference on Computer Vision and Pattern Recog- nition Workshops 2004; 1: 82-82.