Advertisement

Image Super-Resolution Reconstruction Based on Multi-scale Convolutional Neural Network

  • Jianqiao Song
  • Feng WangEmail author
Conference paper
  • 30 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1107)

Abstract

For image super-resolution based on convolutional neural network, there are many problems such as large amount of calculation, many parameters, and unresolved images. This paper proposes an image super-resolution reconstruction algorithm based on multi-scale convolutional neural network. The multi-scale convolution kernel method is introduced into convolutional neural networks. Multi-scale feature extraction is achieved for different sizes of convolutional layers, at the same time, the learning parameters are improved and the network parameters are reduced. Maxout is used as an activation function to introduce competing elements. At the same time, the Skip Connection in the residual network is added to the network model to accelerate the training of deep neural networks. Experiments show that the subjective visual and objective evaluation of this algorithm has been improved to a certain extent. The edge effect of the reconstructed high-resolution image is more clear when reducing the number of network parameters, and more detailed image information is recovered.

Keywords

Convolutional neural network Deep learning Super-resolution reconstruction Multi-scale features 

References

  1. 1.
    Maheta, N.D.: A comparative study of image super resolution approaches. In: International Conference on Electronics Computer Technology, pp. 129–133. IEEE (2011)Google Scholar
  2. 2.
    Harris, J.L.: Diffraction and resolving power. J. Opt. Soc. Am. (1917–1983) 54, 931–933 (1964)CrossRefGoogle Scholar
  3. 3.
    Goodman, J.W., Cox, M.E.: Introduction to Fourier Optics. McGraw-Hill, New York (1968)Google Scholar
  4. 4.
    Shen, H.F., Li, P.X., Zhang, L.P., et al.: Overview on super resolution image reconstruction. Opt. Tech. 35(2), 194–199+203 (2009)Google Scholar
  5. 5.
    Huang, T.S.: Advances in Computer Vision and Image Processing. Jai Press (1986)Google Scholar
  6. 6.
    Kim, S.P., Bose, N.K., Valenzuela, H.M.: Recursive reconstruction of high resolution image from noisy undersampled multiframes. IEEE Trans. Acoust. Speech Signal Process. 38(6), 1013–1027 (1990)CrossRefGoogle Scholar
  7. 7.
    Wen, Y.S., Kim, S.P.: High-resolution restoration of dynamic image sequences. Int. J. Imaging Syst. Technol. 5(4), 330–339 (2010)Google Scholar
  8. 8.
    Stark, H., Oskoui, P.: High-resolution image recovery from image-plane arrays, using convex projections. J. Opt. Soc. Am. A Opt. Image Sci. 6(11), 1715 (1989)CrossRefGoogle Scholar
  9. 9.
    Wernick, M.N., Chen, C.T.: Method of recovering tomographic signal elements in a projection profile or image by solving linear equations: US, US 5323007 A (1994)Google Scholar
  10. 10.
    Stark, H., Olsen, E.T.: Projection-based image restoration. J. Opt. Soc. Am. A 9(9), 1914–1919 (1992)CrossRefGoogle Scholar
  11. 11.
    Xie, T.: Super-resolution image restoration using improved POCS algorithm. Electron. Des. Eng. 21(18), 142–144 (2013)Google Scholar
  12. 12.
    Irani, M., Peleg, S.: Improving resolution by image registration. CVGIP: Graph. Models Image Process. 53(3), 231–239 (1991)Google Scholar
  13. 13.
    Rasti, P., Demirel, H., Anbarjafari, G.: Improved iterative back projection for video super-resolution. In: Signal Processing and Communications Applications Conference, pp. 552–555. IEEE (2014)Google Scholar
  14. 14.
    Dai, S., Han, M., Wu, Y., et al.: Bilateral back-projection for single image super resolution. In: IEEE International Conference on Multimedia and Expo, pp. 1039–1042. IEEE (2007)Google Scholar
  15. 15.
    Tom, B.C., Katsaggelos, A.K.: Reconstruction of a high-resolution image by simultaneous registration, restoration, and interpolation of low-resolution images. In: 1995 Proceedings of the International Conference on Image Processing, p. 2539. IEEE (1995)Google Scholar
  16. 16.
    Schultz, R.R., Stevenson, R.L.: Extraction of high-resolution frames from video sequences. IEEE Trans. Image Process. 5(6), 996–1011 (1996). A Publication of the IEEE Signal Processing SocietyCrossRefGoogle Scholar
  17. 17.
    Schultz, R.R., Stevenson, R.L.: Motion-compensated scan conversion of interlaced video sequences. In: Proceedings of SPIE - The International Society for Optical Engineering (1996)Google Scholar
  18. 18.
    Hardie, R.C., Barnard, K.J., Armstrong, E.E.: Joint MAP registration and high-resolution image estimation using a sequence of undersampled images. IEEE Trans. Image Process. 6(12), 1621–1633 (2002)CrossRefGoogle Scholar
  19. 19.
    Zhang, L., Yang, J., Xuebin: Improved maximum posterior probability estimation method for single image super-resolution reconstruction. Prog. Laser Optoelectron. 48(1), 78–85 (2011)Google Scholar
  20. 20.
    Xujin: Research on Image Super Resolution Reconstruction Based on MAP Technology. Ocean University of China (2007)Google Scholar
  21. 21.
    Elad, M., Feuer, A.: Restoration of single super-resolution image from several blurred. IEEE Trans. Image Process. 6, 1646–1658 (1997)CrossRefGoogle Scholar
  22. 22.
    Ouwerkerk, J.D.V.: Image super-resolution survey. Image Vis. Comput. 24(10), 1039–1052 (2006)CrossRefGoogle Scholar
  23. 23.
    Dong, C., Chen, C.L., He, K., et al.: Learning a deep convolutional network for image super-resolution, vol. 8692, pp. 184–199 (2014)Google Scholar
  24. 24.
    Kim, J., Lee, J.K., Lee, K.M.: Deeply-recursive convolutional network for image super-resolution. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1637–1645. IEEE Computer Society (2016)Google Scholar
  25. 25.
    Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. arXiv Preprint arXiv:1301.3557 (2013)
  26. 26.
    He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition, pp. 770–778 (2015)Google Scholar
  27. 27.
    Lecun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.College of Information and Computer ScienceTaiyuan University of TechnologyTaiyuanChina

Personalised recommendations