Low-resolution expression recognition based on central oblique average CS-LBP with adaptive threshold
CSTR:
Author:
Affiliation:

Key Laboratory of Photo-Electronics Thin Film Devices and Technique of Tianjin, Key Laboratory of Opto-electronic Information Science and Technology, Ministry of Education, Institute of Photo-electronics Thin Film Devices and Technique, Nankai University, Tianjin 300071, China

  • Article
  • | |
  • Metrics
  • |
  • Reference [23]
  • |
  • Related [20]
  • | | |
  • Comments
    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.

    Reference
    [1] Xie Er-man, Luo Sen-lin and Pan Li-min, Journal of Computer-Aided Design & Computer Graphics 23, 1442 (2011). (in Chinese)
    [2] Guo M, Hou X, Ma Y and Wu X, Multimedia Tools & Applications 76, 2995 (2017).
    [3] Boughrara H, Chtourou M, Amar C B and Chen L, Multimedia Tools and Applications 75, 709 (2016).
    [4] Ghimire D, Jeong S, Lee J and Park S H, Multimedia Tools & Applications 75, 1 (2016).
    [5] Shan C, Gong S and Mcowan P W, Image & Vision Computing 27, 803 (2009).
    [6] Chen J, Chi Z and Fu H, Facial Expression Recognition with Dynamic Gabor Volume Feature, International Workshop on Multimedia Signal Processing, 2016.
    [7] Ojala T, Pietikainen M and Maenpaa T, IEEE Transactions on Pattern Analysis & Machine Intelligence 24, 971 (2002).
    [8] Luo Y, Wu C M and Zhang Y, Optik-International Journal for Light and Electron Optics 124, 2767 (2013).
    [9] Cui Peng and Zhang Xue-ting, Journal of Optoelectronics
    .Laser 27, 421 (2016). (in Chinese)
    [10] Yue Ying-ying and Hu Jing-bo, Computer & Digital Engineering 41, 1081 (2013). (in Chinese)
    [11] Zhao Xue-peng, Meng Chun-ning, Feng Ming-kui and Chang Sheng-jiang, Journal of Optoelectronics.Laser 28, 497 (2017). (in Chinese)
    [12] Shan C, Gong S and Mcowan P W, Robust Facial Expression Recognition Using Local Binary Patterns, IEEE International Conference on Image Processing, II-370-3 (2005).
    [13] Li Jia-di, Chen Zhen-xue and Liu Chen-yun, Journal of Optoelectronics.Laser 27, 210 (2016). (in Chinese)
    [14] Neeru N and Kaur L, Face Recognition based on LBP and CS-LBP Technique under Different Emotions, IEEE International Conference on Computational Intelligence and Computing Research, 1 (2016).
    [15] Jabid T, Kabir M H and Chae O, Local Directional Pattern (LDP) for Face Recognition, IEEE Digest of Technical Papers International Conference on Consumer Electronics, 329 (2010).
    [16] Jabid T, Kabir M H and Chae O, Facial Expression Recognition using Local Directional Pattern (LDP), IEEE International Conference on Image Processing, 1605 (2010).
    [17] Y. Ding, Q. Zhao, B. Li and X. Yuan, IEEE Access, 1-1 (2017).
    [18] Goyani M M and Patel N, Electronic Letters on Computer Vision & Image Analysis 16, 54 (2017).
    [19] Ojala T, Pietikainen M and Harwood D, Pattern Recognition 29, 51 (1996).
    [20] Heikkil? M, Pietik?inen M and Schmid C, Pattern Recognition 42, 425 (2009).
    [21] Gong Qu, Ye Jianying and Hua Taotao, Computer Engineering and Applications 49, 197 (2013). (in Chinese)
    [22] Zhang Jie-yu, Zhao Hong-ping and Chen Shu, Journal of Electronics & Information Technology 36, 1327 (2014). (in Chinese)
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

HAN Sheng, XI Shi-qiong, GENG Wei-dong. Low-resolution expression recognition based on central oblique average CS-LBP with adaptive threshold[J]. Optoelectronics Letters,2017,13(6):444-447

Copy
Share
Article Metrics
  • Abstract:3974
  • PDF: 0
  • HTML: 0
  • Cited by: 0
History
  • Received:July 19,2017
  • Revised:August 18,2017
  • Online: November 17,2017
Article QR Code