Skip to main content
SpringerLink
Log in

Discriminative graph regularized broad learning system for image recognition

  • Research Paper
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

Broad learning system (BLS) has been proposed as an alternative method of deep learning. The architecture of BLS is that the input is randomly mapped into series of feature spaces which form the feature nodes, and the output of the feature nodes are expanded broadly to form the enhancement nodes, and then the output weights of the network can be determined analytically. The most advantage of BLS is that it can be learned incrementally without a retraining process when there comes new input data or neural nodes. It has been proven that BLS can overcome the inadequacies caused by training a large number of parameters in gradient-based deep learning algorithms. In this paper, a novel variant graph regularized broad learning system (GBLS) is proposed. Taking account of the locally invariant property of data, which means the similar images may share similar properties, the manifold learning is incorporated into the objective function of the standard BLS. In GBLS, the output weights are constrained to learn more discriminative information, and the classification ability can be further enhanced. Several experiments are carried out to verify that our proposed GBLS model can outperform the standard BLS. What is more, the GBLS also performs better compared with other state-of-the-art image recognition methods in several image databases.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Feng S, Chen C L P. A fuzzy restricted boltzmann machine: novel learning algorithms based on the crisp possibilistic mean value of fuzzy numbers. IEEE Trans Fuzzy Syst, 2018, 26: 117–130

    Article  Google Scholar 

  2. Chen C L P, Zhang C Y, Chen L, et al. Fuzzy restricted boltzmann machine for the enhancement of deep learning. IEEE Trans Fuzzy Syst, 2015, 23: 2163–2173

    Article  Google Scholar 

  3. Cai S J, Zhang L, Zuo W M, et al. A probabilistic collaborative representation based approach for pattern classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016

    Google Scholar 

  4. Xie Z W, Zeng Z, Zhou G Y, et al. Topic enhanced deep structured semantic models for knowledge base question answering. Sci China Inf Sci, 2017, 60: 110103

    Article  Google Scholar 

  5. Qu W, Wang D L, Feng S, et al. A novel cross-modal hashing algorithm based on multimodal deep learning. Sci China Inf Sci, 2017, 60: 092104

    Article  Google Scholar 

  6. Pao Y H, Takefuji Y. Functional-link net computing: theory, system architecture, and functionalities. Computer, 1992, 25: 76–79

    Article  Google Scholar 

  7. Pao Y H, Phillips S M, Sobajic D J. Neural-net computing and the intelligent control of systems. Int J Control, 1992, 56: 263–289

    Article  MathSciNet  Google Scholar 

  8. Igelnik B, Pao Y H. Stochastic choice of basis functions in adaptive function approximation and the functional-link net. IEEE Trans Neural Netw, 1995, 6: 1320–1329

    Article  Google Scholar 

  9. Klassen M, Pao Y H, Chen V. Characteristics of the functional-link net: a higher order delta rule net. In: Proceedings of International Conference on Neural Networks, San Diego, 1988

    Google Scholar 

  10. Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Netw, 1991, 4: 251–257

    Article  Google Scholar 

  11. Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw, 1989, 2: 359–366

    Article  Google Scholar 

  12. Chen C L P. A rapid supervised learning neural network for function interpolation and approximation. IEEE Trans Neural Netw, 1996, 7: 1220–1230

    Article  Google Scholar 

  13. Chen C L P, LeClair S R, Pao Y H. An incremental adaptive implementation of functional-link processing for function approximation, time-series prediction, and system identification. Neurocomputing, 1998, 18: 11–31

    Article  Google Scholar 

  14. Chen C L P, Wan J Z. A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction. IEEE Trans Syst Man Cybern B, 1999, 29: 62–72

    Article  Google Scholar 

  15. Chen C L P, Zhang C Y. Data-intensive applications, challenges, techniques and technologies: a survey on big data. Inf Sci, 2014, 275: 314–347

    Article  Google Scholar 

  16. Chen C L P, Liu Z. Broad learning system: an effective and efficient incremental learning system without the need for deep architecture. IEEE Trans Neural Netw Learn Syst, 2018, 29: 10–24

    Article  MathSciNet  Google Scholar 

  17. Chen C L P, Liu Z L, Feng S. Universal approximation capability of broad learning system and its structural variations. IEEE Trans Neural Netw Learn Syst, 2018. doi: 10.1109/TNNLS.2018.2866622

    Google Scholar 

  18. Feng S, Chen C L P. Fuzzy broad learning system: a novel neuro-fuzzy model for regression and classification. IEEE Trans Cybern, 2018. doi: 10.1109/TCYB.2018.2857815

    Google Scholar 

  19. Miao S, Wang J, Gao Q X, et al. Discriminant structure embedding for image recognition. Neurocomputing, 2016, 174: 850–857

    Article  Google Scholar 

  20. Fang Y Q, Wang R L, Dai B, et al. Graph-based learning via auto-grouped sparse regularization and kernelized extension. IEEE Trans Knowl Data Eng, 2015, 27: 142–154

    Article  Google Scholar 

  21. Yan S C, Xu D, Zhang B Y, et al. Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intel, 2007, 29: 40–51

    Article  Google Scholar 

  22. Liao Y Y, Wang Y, Liu Y. Graph regularized auto-encoders for image representation. IEEE Trans Image Process, 2017, 26: 2839–2852

    Article  MathSciNet  Google Scholar 

  23. Gao Q X, Ma J J, Zhang H L, et al. Stable orthogonal local discriminant embedding for linear dimensionality reduction. IEEE Trans Image Process, 2013, 22: 2521–2531

    Article  Google Scholar 

  24. Xue H, Chen S C, Yang Q. Discriminatively regularized least-squares classification. Pattern Recogn, 2009, 42: 93–104

    Article  Google Scholar 

  25. Peng Y, Wang S H, Long X Z, et al. Discriminative graph regularized extreme learning machine and its application to face recognition. Neurocomputing, 2015, 149: 340–353

    Article  Google Scholar 

  26. Huang G B, Mattar M, Berg T, et al. Labeled faces in the wild: a database forstudying face recognition in unconstrained environments. In: Proceedings of Workshop on Faces in ‘Real-Life’ Images: Detection, Alignment, and Recognition, Marseille, 2008

    Google Scholar 

  27. Guo P, Chen C L P, Lyu M R. Cluster number selection for a small set of samples using the Bayesian Ying-Yang model. IEEE Trans Neural Netw, 2002, 13: 757–763

    Article  Google Scholar 

  28. Guo P, Lyu M R, Chen C L P. Regularization parameter estimation for feedforward neural networks. IEEE Trans Syst Man Cybern B, 2003, 33: 35–44

    Article  Google Scholar 

  29. Naseem I, Togneri R, Bennamoun M. Linear regression for face recognition. IEEE Trans Pattern Anal Mach Intel, 2010, 32: 2106–2112

    Article  Google Scholar 

  30. Wright J, Yang A Y, Ganesh A, et al. Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intel, 2009, 31: 210–227

    Article  Google Scholar 

  31. Zhang L, Yang M, Feng X C. Sparse representation or collaborative representation: which helps face recognition? In: Proceedings of International Conference on Computer Vision, Barcelona, 2011

    Google Scholar 

  32. Peng X, Zhang L, Yi Z, et al. Learning locality-constrained collaborative representation for robust face recognition. Pattern Recogn, 2014, 47: 2794–2806

    Article  Google Scholar 

  33. Yao B P, Jiang X Y, Khosla A, et al. Human action recognition by learning bases of action attributes and parts. In: Proceedings of International Conference on Computer Vision, Barcelona, 2011

    Google Scholar 

  34. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. ArXiv:1409.1556

    Google Scholar 

  35. Chi Y, Porikli F. Classification and boosting with multiple collaborative representations. IEEE Trans Pattern Anal Mach Intel, 2014, 36: 1519–1531

    Article  Google Scholar 

  36. Diba A, Mohammad A, Pirsiavash H, et al. Deepcamp: deep convolutional action & attribute mid-level patterns. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 2016

    Google Scholar 

  37. Wang L M, Qiao Y, Tang X O, et al. Actionness estimation using hybrid fully convolutional networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016

    Google Scholar 

  38. Razavian A S, Azizpour H, Sullivan J, et al. CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, 2014

    Google Scholar 

  39. Chatfield K, Simonyan K, Vedaldi A, et al. Return of the devil in the details: delving deep into convolutional nets. 2014. ArXiv:1405.3531v4

    Google Scholar 

  40. Cimpoi M, Maji S, Vedaldi A. Deep filter banks for texture recognition and segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 2015

    Google Scholar 

Download references

Acknowledgements

This work was supported in part by National Natural Science Foundation of China (Grant No. 61572540), Macau Science and Technology Development Fund (FDCT) (Grant Nos. 019/2015/A, 024/2015/AMJ, 079/2017/A2), and the University Macau MYR Grants.

Author information

Authors and Affiliations

  1. Faculty of Science and Technology, University of Macau, Macau, 999078, China

    Junwei Jin, Zhulin Liu & C. L. Philip Chen

  2. Dalian Maritime University, Dalian, 116026, China

    C. L. Philip Chen

  3. State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100080, China

    C. L. Philip Chen

Authors
  1. Junwei Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhulin Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. C. L. Philip Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to C. L. Philip Chen.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jin, J., Liu, Z. & Chen, C.L.P. Discriminative graph regularized broad learning system for image recognition. Sci. China Inf. Sci. 61, 112209 (2018). https://doi.org/10.1007/s11432-017-9421-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11432-017-9421-3

Keywords

Search

Navigation