Skip to main content
Springer Nature Link
Log in

A novel construction method of convolutional neural network model based on data-driven

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The convolutional neural network (CNN) is an excellent method for image recognition. However, there are some problems in the construction process of CNN model, such as network structure setting depends on experience knowledge, network parameters selection is difficult, and there is a lack of relevance between network model and training data. To overcome the shortcomings of CNN model construction theory, in this paper, we develop a new construction approach, named adaptive deep CNN network model based on data-driven. In our method, we first set up the initial CNN model in a simple way, and the initial model only contains one feature map in the convolution layer and pooling layer. And then, the network is adaptively constructed by using the idea of learning parameters and expanding network. In network expansion, the convergence rate of CNN model is used as evaluation index of global expansion, and some global branches are added to the network model. After global expansion, the CNN is controlled to local expansion according to the recognition rate of cross validation samples. The local network learning is stopped until the recognition rate reaches the expected value. Finally, the adaptive incremental learning of network structure is realized by expanding some new branches for new samples. Experimental results on two benchmark face databases, CMU-PIE face database and MIT-CBCL face database, demonstrate the effectiveness of the proposed method.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Abdel-Hamid O, Mohamed AR, Jiang H, Deng L (2014) Convolutional Neural Networks for Speech Recognition[C]. IEEE/ACM Transactions on Audio, Speech, and Language Processing 22(10):1533–1545

    Article  Google Scholar 

  2. Arel I, Rose DC, Karnowski TP (2010) Deep machine learning: a new frontier in artificial intelligence research [J]. IEEE Comput Intell Mag 5(4):13–18

    Article  Google Scholar 

  3. Bengio Y, Delalleau O (2011) On the expressive power of deep architectures [C] Proc. of the 14th International Conference on Discovery Science:18-36

  4. Dong Y, Wu Y (2015) Adaptive Cascade Deep Convolutional Neural Networks for face alignment[J]. Computer Standards & Interfaces 42:105–112

    Article  Google Scholar 

  5. Garcia C, Delakis M (2002) A neural architecture for fast and robust face detection[C], in: proc. 16th International Conference on Pattern Recognition, Canada 2: 44-47

  6. Hamester D, Barros P, Wermter S (2015) Face Expression Recognition with a 2-Channel Convolutional Neural Network[C]. International Joint Conference on Neural Networks(IJCNN):1–8

  7. He Y, Kavukcuoglu K, Wang Y, Szlam A, Qi Y (2014) Unsupervised feature learning by deep sparse coding, To be published on International Conference on Learning Representations:1-9

  8. Hinton G, Salakhutdinov R (2006) Reducing the dimensionality of data with neural networks [J]. Science 5786(313):504–507

    Article  MathSciNet  Google Scholar 

  9. Hinton GE, Osindero S, Teh Y (2006) A fast learning algorithm for deep belief nets [J]. Neural Comput 18(7):1527–1554

    Article  MathSciNet  Google Scholar 

  10. Huang Y, Huang K, Tao D, Tan T, Li X (2011) Enhanced biologically inspired model for object recognition [J]. IEEE Trans Syst Man Cybern B Cybern 41(6):1668–1680

    Article  Google Scholar 

  11. Huang K-Q, Ren W-Q, Tan T-N (2014) A Review on Image Object Classification and Detection[J]. Chinese journal of computer 37(6):1225–1240

    Google Scholar 

  12. Kang L, Kumar J, Ye P, Li Y, Doermann D (2014) Convolutional Neural Networks for Document Image Classification[C]. International Conference on Pattern Recognition(ICPR):3168–3172

  13. Kang L, Ye P, Li Y, Doermann D (2014) Convolutional Neural Networks for No-Reference Image Quality Assessment[J]. Computer Vision & Pattern Recognition(CVPR):1733–1740

  14. Kim LW, Asaad S, Linsker R (2014) A fully pipelined FPGA architecture of a factored restricted boltzmann machine artificial neural network [J]. ACM Transactions on Reconfigurable Technology and Systems 7(1):104–104

    Article  Google Scholar 

  15. Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks [C] Proc. of the Advances in Neural Information Processing Systems (NPIS):1106-1114

  16. Lawrence S, Giles CL, Tsoi AC, Back AD (1997) Face recognition: a convolutional neural-network approach[J]. IEEE Trans Neural Netw 8(1):98–113

    Article  Google Scholar 

  17. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Back propagation applied to hand written zip code recognition [J]. Neural Comput 1(4):541–551

    Article  Google Scholar 

  18. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-Based Learning Applied to Document Recognition[J]. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  19. Li H, Lin Z, Shen X, Brandt J, Hua G (2015) A Convolutional Neural Network Cascade for Face Detection[C], The IEEE Conference on Computer Vision and Pattern Recognition (CVPR):5325-5334.

  20. Lian Z, Jing X, Sun S et al (2016) Multi-Scale convolutional neural network model with multilayer maxout networks[J]. Journal of Beijing University of Posts and Telecommunications 39(5):1–5

    Google Scholar 

  21. Ouyang WL, Wang XG, Zeng XY et al (2015) DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR):2403–2412

  22. Pattabhi Ramaiah N, Ijjina EP, Mohan CK (2015) Illumination invariant face recognition using convolutional neural network[C], 2015 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems:1-4.

  23. Pinheiro P, Collobert R (2014) Recurrent convolutional neural networks for scene labeling [C] Proc. of The 31st International Conference on Machine Learning:82-90

  24. Rui T, Zou J, Zhou Y et al (2017) Convolutional neural network feature maps selection based on LDA[J]. Multimedia Tools & Applications 6:1–15

    Google Scholar 

  25. Sun Y, Wang X, Tang X (2013) Hybrid deep learning for face verification [C] Proc. of IEEE International Conference on Computer Vision (ICCV 2013):1489-1496

  26. Wolfshaar JVD, Karaaba MF, Wiering MA (2015) Deep Convolutional Neural Networks and Support Vector Machines for Gender Recognition[C]. Proceedings - 2015 IEEE Symposium Series on Computational Intelligence:188-195.

  27. Xiong C, Zhao X, Tang D, Jayashree K (2015) Conditional Convolutional Neural Network for Modality-aware Face Recognition[C]. IEEE International Conference on Computer Vision(CVPR):3667–3675

  28. Xu C, Yang J, Lai H et al. (2017) UP-CNN: Un-pooling augmented convolutional neural network[J], Pattern Recogn Lett:1-7

  29. Yu K, Jia L, Chen Y, Xu W (2013) Deep Learning: Yesterday, Today and Tomorrow[J]. Journal of computer research and development 50(9):1799–1804

    Google Scholar 

  30. Zhang S, Yang H, Yin Z (2015) Multiple deep convolutional neural networks averaging for face alignment[J]. Journal of Electronic Imaging 24(3):1–13

    Article  Google Scholar 

  31. Zhang Y, Zhao D, Sun J, Zou G, Li W (2016) Adaptive Convolutional Neural Network and Its Application in Face Recognition[J]. Neural Process Lett 43(2):389–399

    Article  Google Scholar 

  32. Zou J, Wu Q, Tan Y, Wu F (2015) Analysis Range of Coefficients in Learning Rate Methods of Convolution Neural Network[J]. International Symposium on Distributed Computing & Applications for Business Engineering & Science(DCABES):513–517

Download references

Acknowledgments

This research is supported by Natural Science Foundation of Shandong Province of China (No.ZR2015FL029, ZR2016FL14); National Natural Science Foundation of China (No. 61601266); China Postdoctoral Science Foundation (No. 2017M612306); Key Research and Development Program of Shandong Province (No.2017GGX10125); The Shandong University of Technology and Zibo City Integration Development Project (No.2016ZBXC097, No. 2016ZBXC142).

Author information

Authors and Affiliations

  1. College of Electrical and Electronic Engineering, Shandong University of Technology, Zhang Zhou road, NO.12, Zhangdian District, Zibo, 255049, Shandong Province, China

    Guo-feng Zou, Gui-xia Fu, Ming-liang Gao, Jin Shen & Li-ju Yin

  2. School of Information Science and Engineering, Shandong University, Jinan, 250100, China

    Xian-ye Ben

Authors
  1. Guo-feng Zou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gui-xia Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ming-liang Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jin Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Li-ju Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xian-ye Ben
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Guo-feng Zou.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zou, Gf., Fu, Gx., Gao, Ml. et al. A novel construction method of convolutional neural network model based on data-driven. Multimed Tools Appl 78, 6969–6987 (2019). https://doi.org/10.1007/s11042-018-6449-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6449-8

Keywords