Skip to main content
SpringerLink
Log in

Sparse representation optimization of image Gaussian mixture features based on a convolutional neural network

  • S.I. :Machine Learning based semantic representation and analytics for multimedia application
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

This paper analyzes the inherent relationship between convolutional neural networks and sparse representation and proposes an improved convolutional neural network model for image synthesis in response to problems with current methods. In the testing phase, the calculation of the sparse coefficients involves the solution of complex optimization problems, which greatly reduce the operating efficiency, inspired by the successful application of convolutional neural networks in the field of image reconstruction. Compared with the traditional image portrait synthesis method, this model not only has an end-to-end closed form but also does not need to solve complex optimization problems in the synthesis stage. The synthesis experiment on an image dataset shows that this method not only improves the synthesis effect but also improves the efficiency of the traditional method by one to two orders of magnitude, demonstrating its potential application value. Blocking processing is a common method for sparse domain image modeling. It improves the computational efficiency but also decreases the global structure of the image, which is difficult to compensate for through the aggregation and overlap of image blocks. In response to this problem, this paper proposes a low-rank image inpainting method based on a Gaussian mixture model. This method embeds the local statistical characteristics of image blocks into the kernel norm model and not only uses the Gaussian mixture model to maintain the local details of the image but also describes the global low-rank structure of the image through the kernel norm, thus restoring a class of image data with a potential low-rank structure and theoretically revealing the structured sparse nature of the Gaussian mixture model. This paper optimizes the strategy based on random hidden neuron nodes and proposes a dropout anti-overfitting strategy based on sparsity. The experiments show that this strategy can effectively improve the convergence speed while ensuring good performance and can effectively prevent overfitting.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Sekaran K, Chandana P, Krishna NM et al (2020) Deep learning convolutional neural network (CNN) With Gaussian mixture model for predicting pancreatic cancer. Multimed Tools Appl 79(15):10233–10247

    Article  Google Scholar 

  2. Islam MT, Rahman SMM, Ahmad MO et al (2018) Mixed Gaussian-impulse noise reduction from images using convolutional neural network. Signal Process Image Commun 68:26–41

    Article  Google Scholar 

  3. Sezavar A, Farsi H, Mohamadzadeh S (2019) Content-based image retrieval by combining convolutional neural networks and sparse representation. Multimed Tools Appl 78(15):20895–20912

    Article  Google Scholar 

  4. Flores E, Zortea M, Scharcanski J (2019) Dictionaries of deep features for land-use scene classification of very high spatial resolution images. Pattern Recogn 89:32–44

    Article  Google Scholar 

  5. Fan Y, Wen G, Li D et al (2002) Video anomaly detection and localization via gaussian mixture fully convolutional variational autoencoder. Comput Vis Image Underst 195:102920

    Article  Google Scholar 

  6. Li Y, Cui W, Luo M et al (2018) Epileptic seizure detection based on time-frequency images of EEG signals using Gaussian mixture model and gray level co-occurrence matrix features. Int J Neural Syst 28(07):1850003

    Article  Google Scholar 

  7. Acharya UR, Oh SL, Hagiwara Y et al (2018) Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput Biol Med 100:270–278

    Article  Google Scholar 

  8. Yang L, Cheung NM, Li J et al (2019) Deep clustering by gaussian mixture variational autoencoders with graph embedding. IEEE Comput Vis 2:6440–6449

    Google Scholar 

  9. Zhang C, Qiao K, Wang L et al (2018) Constraint-free natural image reconstruction from fMRI signals based on convolutional neural network. Front Hum Neurosci 12:242

    Article  Google Scholar 

  10. Sabokrou M, Fayyaz M, Fathy M et al (2018) Deep-anomaly: fully convolutional neural network for fast anomaly detection in crowded scenes. Comput Vis Image Underst 172:88–97

    Article  Google Scholar 

  11. Abdel-Hamid O, Mohamed A, Jiang H et al (2020) Convolutional neural networks for speech recognition. IEEE/ACM Trans Audio Speech Lang Process 22(10):1533–1545

    Article  Google Scholar 

  12. Yang A, Yang X, Wu W et al (2019) Research on feature extraction of tumor image based on convolutional neural network. IEEE Access 7:24204–24213

    Article  Google Scholar 

  13. Tang P, Wang X, Shi B et al (2018) Deep fishernet for image classification. IEEE Trans Neural Netw Learn Syst 30(7):2244–2250

    Article  MathSciNet  Google Scholar 

  14. Ma J, Jiang X, Jiang J et al (2019) Feature-guided Gaussian mixture model for image matching. Pattern Recogn 92:231–245

    Article  Google Scholar 

  15. Rasti R, Rabbani H, Mehridehnavi A et al (2019) Macular OCT classification using a multi-scale convolutional neural network ensemble. IEEE Trans Med Imaging 37(4):1024–1034

    Article  Google Scholar 

  16. Xing Y, Tang J, Liu H, Lv C, Cao D, Velenis E, Wang FY (2018) End-to-end driving activities and secondary tasks recognition using deep convolutional neural network and transfer learning. In 2018 IEEE intelligent vehicles symposium (IV) vol 5, pp 1626–1632

  17. Tavanaei A, Maida AS (2019) Multi-layer unsupervised learning in a spiking convolutional neural network. IEEE Neural Netw 6:2023–2030

    Google Scholar 

  18. Liu J, Xie H, Zhang S et al (2019) Multi-sequence myocardium segmentation with cross-constrained shape and neural network-based initialization. Comput Med Imaging Graph 71:49–57

    Article  Google Scholar 

  19. Hu K, Chen K, He X, Zhang Y, Chen Z, Li X, Gao X (2020) Automatic segmentation of intracerebral hemorrhage in CT images using encoder-decoder convolutional neural network. Inf Process Manag 57(6):102352

    Article  Google Scholar 

  20. Hemanth DJ, Deperlioglu O, Kose U (2020) An enhanced diabetic retinopathy detection and classification approach using deep convolutional neural network. Neural Comput Appl 32:707–721

    Article  Google Scholar 

  21. Chang Y, Yan L, Fang H et al (2018) HSI-DeNet: hyperspectral image restoration via convolutional neural network. IEEE Trans Geosci Remote Sens 57(2):667–682

    Article  Google Scholar 

  22. Lei J, Li G, Zhang J et al (2016) Continuous action segmentation and recognition using hybrid convolutional neural network-hidden Markov model model. IET Comput Vis 10(6):537–544

    Article  Google Scholar 

Download references

Acknowledgements

The study was supported by the Joint Fund of the Zhejiang Natural Science Foundation Committee and Zhejiang Society of Mathematical Medicine, China (No. LSY19F010001) and special funds for basic scientific research in Provincial Universities from Zhejiang Shuren University (2021).

Author information

Authors and Affiliations

  1. School of Information and Science Technology, Zhejiang Shuren University, Hangzhou , 310015, Zhejiang, China

    Fangfang Ye, Tiaojuan Ren & Zhangquan Wang

  2. College of Information Science and Technology, Nanjing Forestry University, Nanjing , 210037, Jiangsu, China

    Ting Wang

Authors
  1. Fangfang Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tiaojuan Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhangquan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ting Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fangfang Ye.

Ethics declarations

Conflict of interest

The author declares that there is no conflict of interest.

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

Ye, F., Ren, T., Wang, Z. et al. Sparse representation optimization of image Gaussian mixture features based on a convolutional neural network. Neural Comput & Applic 34, 12427–12437 (2022). https://doi.org/10.1007/s00521-021-06521-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06521-6

Keywords

Search

Navigation