Low-resolution expression recognition based on central oblique average CS-LBP with adaptive threshold

Abstract

In order to solve the problem of low recognition rate of traditional feature extraction operators under low-resolution images, a novel algorithm of expression recognition is proposed, named central oblique average center-symmetric local binary pattern (CS-LBP) with adaptive threshold (ATCS-LBP). Firstly, the features of face images can be extracted by the proposed operator after pretreatment. Secondly, the obtained feature image is divided into blocks. Thirdly, the histogram of each block is computed independently and all histograms can be connected serially to create a final feature vector. Finally, expression classification is achieved by using support vector machine (SVM) classifier. Experimental results on Japanese female facial expression (JAFFE) database show that the proposed algorithm can achieve a recognition rate of 81.9% when the resolution is as low as 16×16, which is much better than that of the traditional feature extraction operators.

References

[1] XieE-m, LuoS-l, PanL-m. Journal of Computer-Aided Design & Computer Graphics, 2011, 23: 1442

[2] GuoM, HouX, MaY, WuX. Multimedia Tools & Applications, 2017, 76: 2995

[3] BoughraraH, ChtourouM, AmarC B, ChenL. Multimedia Tools and Applications, 2016, 75: 709

[4] GhimireD, JeongS, LeeJ, ParkS H. Multimedia Tools & Applications, 2016, 75: 1

[5] ShanC, GongS, McowanP W. Image & Vision Computing, 2009, 27: 803

[6] ChenJ, ChiZ, FuH. Facial Expression Recognition with Dynamic Gabor Volume Feature, 2016,

[7] OjalaT, PietikainenM, MaenpaaT. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 24: 971

[8] LuoY, WuC M, ZhangY. Optik-International Journal for Light and Electron Optics, 2013, 124: 2767

[9] CuiP, ZhangX-t. Journal of Optoelectronics ·Laser, 2016, 27: 421

[10] YueY-y, HuJ-b. Computer & Digital Engineering, 2013, 41: 1081

[11] ZhaoX-p, MengC-n, FengM-k, ChangS-j. Journal of Optoelectronics·Laser, 2017, 28: 497

[12] ShanC, GongS, McowanP W. Robust Facial Expression Recognition Using Local Binary Patterns, 2005,

[13] LiJ-d, ChenZ-x, LiuC-y. Journal of Optoelectronics·Laser, 2016, 27: 210

[14] NeeruN, KaurL. Face Recognition based on LBP and CS-LBP Technique under Different Emotions, 2016, 1

[15] JabidT, KabirM H, ChaeO. Local Directional Pattern (LDP) for Face Recognition, 2010, 329

[16] JabidT, KabirM H, ChaeO. Facial Expression Recognition using Local Directional Pattern (LDP), 2010, 1605

[17] DingY, ZhaoQ, LiB, YuanX. IEEE Access, 2017, 1

[18] GoyaniM M, PatelN. Electronic Letters on Computer Vision & Image Analysis, 2017, 16: 54

[19] OjalaT, PietikainenM, HarwoodD. Pattern Recognition, 1996, 29: 51

[20] HeikkiläM, PietikäinenM, SchmidC. Pattern Recognition, 2009, 42: 425

[21] GongQ, YeJ, HuaT. Computer Engineering and Applications, 2013, 49: 197

[22] ZhangJ-y, ZhaoH-p, ChenS. Journal of Electronics & Information Technology, 2014, 36: 1327