Advertisement

Artificial Intelligence Review

, Volume 51, Issue 1, pp 1–18 | Cite as

Dictionary learning feature space via sparse representation classification for facial expression recognition

  • Zhe Sun
  • Zheng-ping HuEmail author
  • Meng Wang
  • Shu-huan Zhao
Article

Abstract

Facial expression recognition (FER) plays a significant role in human-computer interaction. In this paper, adopting a dictionary learning feature space (DLFS) via sparse representation classification (SRC), we propose a method for FER. First, we obtain a difference dictionary (DD) from the feature space by indirectly using an auxiliary neutral training set. Next, we use a dictionary learning algorithm to train the DD; this algorithm considers the samples from the DD are approximately symmetrical structure. Finally, we use SRC to represent and determine the label of each query sample. We then verify out proposed method from the perspective of training samples, dimension reduction methods and Gaussian noise variances using a variety of public databases. In addition, we compare our DLFS_SRC approach with DLFS_CRC and DLFS_LRC approaches on the Extended Cohn-Kanade (CK+) database to analyze recognition results. Our simulation experiments show that our proposed method achieved satisfying performance levels for FER.

Keywords

Facial expression recognition Difference dictionary Dictionary learning Sparse representation classification 

Notes

Acknowledgements

This work was partially supported by the National Natural Science Foundation of China (No. 61071199) and the Natural Science Foundation of Hebei Province (No. F2016203422). In this paper, we also utilized four public databases. We therefore thank the providers of these databases.

Compliance with ethical standards

Conflict of interests

We declare that there is no conflict of interest regarding the publication of this paper.

References

  1. Blockmans B, Tamarozzi T, Naets F, Desmet W (2015) A nonlinear parametric model reduction method for efficient fear contact simulations. Int J Numer Methods Eng 102(5):1162–1191zbMATHGoogle Scholar
  2. Deng W, Hu J, Guo J (2012) Extended SRC: undersampled face recognition via intraclass variant dictionary. IEEE Trans Pattern Anal Mach Intell 34:1864–1870Google Scholar
  3. Fang Y, Chang L (2015) Multi-instance feature learning based on sparse representation for facial expression recognition. Lect Notes Comput Sci 8935:224–233Google Scholar
  4. Goeleven E, De Raedt R, Leyman L, Verschuere B (2008) The Karolinska directed emotional faces: a validation study. Cognit Emot 22(6):1094–1118Google Scholar
  5. Happy SL, Routray A (2015) Automatic facial expression recognition using features of salient facial patches. IEEE Trans Affect Comput 6(1):1–12Google Scholar
  6. Hegde G, Seetha M, Hegde N (2015) Facial expression recognition using entire Gabor filter matching score level fusion approach based on subspace methods. Lect Notes Comput Sci 9468:47–57Google Scholar
  7. Hoyer PO (2004) Non-negative matrix factorization with sparseness constraints. J Mach Learin Res 5(11):1457–1469MathSciNetzbMATHGoogle Scholar
  8. Huang MW, Wang ZW, Ying ZL (2010) A new method for facial expression recognition based on sparse representation plus LBP. Int Congr Image Signal Process 3:6826–6829Google Scholar
  9. Kapoor R, Gupta R (2015) Morphological mapping for non-linear dimensionality reduction. IET Comput Vis 9(2):226–232Google Scholar
  10. Kim SJ, Koh K, Lustig M, Boyed S, Gorinevsky D (2007) A method for large scale l1-regularized least squares. IEEE J Sel Top Signal Process 1(4):606–617Google Scholar
  11. Lee SH, Baddar WJ, Ro YM (2016) Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos. Pattern Recognit 54:52–67Google Scholar
  12. Le T, Sawides M (2015) A novel shape constrained feature-based active contour model for lips or mouth segmentation in the wild. Pattern Recognit 54:23–33Google Scholar
  13. Li X, Ruan Q, Yi J, An G, Zhao R (2015) Fully automatic 3D facial expression recognition using polytypic multi-block local binary patterns. Signal Process 108:297–308Google Scholar
  14. Little AC (2014) Domain specificity in human symmetry preferences: symmetry is most pleasant when looking at human faces. Symmetry 6(2):222–233Google Scholar
  15. Liu W, Lu L, Li H, Wang W, Zou Y (2015) A novel kernel collaborative representation approach for image classification. IEEE Int Conf Image Process 1:4241–4245Google Scholar
  16. Lucey P, Jeffrey FC, Kanade T, Saragih J, Ambadar Z, Matthews I (2010) The extended Cohn-Kanade dataset (CK+): a complete dataset for action unit and emotion-specified expression. In: IEEE computer society conference on computer vision and pattern recognition workshops, CVPRW. pp 94–101Google Scholar
  17. Luo Y, Zhang T, Zhang Y (2016) A novel fusion method of PCA and LDP for facial expression feature extraction. Optik 127(2):718–721Google Scholar
  18. Lyons M, Akamatsu S, Kamachi M, Gyoba J (1998) Coding facial expressions with Gabor wavelets. In: IEEE international conference on automatic face and gesture recognition. pp 200–205Google Scholar
  19. Ma D, Li M, Nian F, Kong C (2015) Facial expression recognition based on characteristics of block LGBP and sparse representation. J Comput Methods Sci Eng 15(3):537–547Google Scholar
  20. Martinez AM, Benavente R (1998) The AR face database. CVC technical report #24, June 1998Google Scholar
  21. Min X, Wang H, Yang Z, Ge S, Zhang J, Shao N (2015) Relevant component locally embedding dimensionality reduction for gene expression data analysis. Metall Min Ind 7(4):186–194Google Scholar
  22. Shao J, Gori l, Wan S, Aggarwal JK (2015) 3D dynamic facial expression recognition using low-resolution videos. Pattern Recognit Lett 65:157–162Google Scholar
  23. Shikkenawis G, Mitra SK (2016) On some variants of locality preserving projection. Neurocomputing 173:196–211Google Scholar
  24. Siddiqi MH, Ali R, Khan AM, Park YT, Lee S (2015) Human facial expression recognition using stepwise linear discriminant analysis and hidden conditional random fields. IEEE Trans Image Process 24(4):1386–1398MathSciNetGoogle Scholar
  25. Tariq U, Thomas J, Huang TS (2014) Supervised super-vector encoding for facial expression recognition. Pattern Recognit Lett 46(9):89–95Google Scholar
  26. Tian Y (2004) Evaluation of face resolution for expression analysis. IEEE Comput Soc Conf Comput Vis Pattern Workshops 1:82–82Google Scholar
  27. Wang S, Yan W, Zhao G, Fu X, Zhou C (2015) Micro-expression recognition using robust principle component analysis and local spatiotemporal directional features. Lect Notes Comput Sci 8925:325–338Google Scholar
  28. Wang Z, Ruan Q, An G (2016) Facial expression recognition using sparse local Fisher discriminant analysis. Neurocomputing 174:756–766Google Scholar
  29. Wang Z, Ying Z (2012) Facial expression recognition based on local phase quantization and sparse representation. In: International conference on computation. pp 222–225Google Scholar
  30. Wang Q, Ying Z (2014) Facial expression recognition algorithm based on Gabor texture features and Adaboost selection via sparse representation. Appl Mech Mater 4:433–436Google Scholar
  31. Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31:210–227Google Scholar
  32. Xu X, Quan C, Ren F (2015) Facial expression recognition based on Gabor Wavelet transform and histogram of oriented gradients. IEEE Int Conf Mechatron Autom 9:2117–2122Google Scholar
  33. Yazdani R, Fallah HR, Hajimahmoodzadeh M (2014) Reconstruction of two interfering wavefronts using Zernike polynomials and stochastic parallel gradient descent algorithm. Opt Lett 39(6):1505–1508Google Scholar
  34. Yu J, Ko K, Sim K (2016) Facial point classifier using convolution neural network and cascade facial point detector. J Inst Control Robot Syst 22(3):241–246Google Scholar
  35. Yurtkan K, Demirel H (2014) Feature selection for improved 3D facial expression recognition. Pattern Recognit Lett 38(3):26–33Google Scholar
  36. Yusuf R, Sharma DG, Tanev I, Shimohara K (2016) Evolving an emotion recognition module for an intelligent agent using genetic programming and a genetic algorithm. Artif Life Robot 21(1):85–90Google Scholar
  37. Zhang S, Zhao X, Lei B (2012) Facial expression recognition using sparse representation. WSEAS Trans Syst 11(8):440–452Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2017

Authors and Affiliations

  • Zhe Sun
    • 1
  • Zheng-ping Hu
    • 1
    Email author
  • Meng Wang
    • 1
    • 2
  • Shu-huan Zhao
    • 1
  1. 1.School of Information Science and EngineeringYanshan UniversityQinhuangdaoChina
  2. 2.School of Physics and Electronic EngineeringTaishan UniversityTai’anChina

Personalised recommendations