Advertisement

Signal, Image and Video Processing

, Volume 12, Issue 1, pp 25–31 | Cite as

Blind multi-image super-resolution based on combination of ANN learning and non-subsampled Contourlet directional image representation

  • Zhiyong Shi
  • Fengchun TianEmail author
  • Yande Wang
  • Jian Ran
Original Paper

Abstract

In image super-resolution technique, it is contradictory to keep the edge characteristics of the image while de-noising. In order to solve the above problem, we propose a blind multi-image super-resolution algorithm which is adaptive to the image content and does not need the fuzzy conditions of generating the low-resolution images. The initially estimated high-resolution image \(\left( \hat{H}\right) \) is firstly gotten through the traditional reconstruction algorithm. Afterward, the estimation differences of low-resolution images are utilized as the input of artificial neural network (ANN), and the band-pass directional sub-bands of non-subsampled Contourlet transform (NSCT) of the lost high-frequency components are outputted in ANN. With the inverse NSCT, we can get the estimated lost high-frequency components. Finally, the estimated lost high-frequency components and the adaptive weighted matrix generated from the image content are multiplied before being added to \(\hat{H}\). Experimental results show that the high-resolution images obtained through the proposed method can achieve favorable subjective and objective quality for different image contents. Meantime, it is superior to some of the state-of-the-art classical methods in terms of the performance.

Keywords

Multi-image super-resolution Blink image reconstruction Directional image representation Contourlet transform Artificial neural network 

Notes

Acknowledgements

This work was jointly supported by the National Natural Science Foundation of China (No. 61201347), Chongqing Foundation and Advanced Research Project (No. cstc2016jcyjA0103), the Natural Science Foundation Project of CQ CSTC (No. cstc2012jjA40011), and the Fundamental Research Funds for the Central Universities (No. CDJZR13185502). The support is gratefully acknowledged.

References

  1. 1.
    Yao, P., Xue, J.X., Dai, G.Z.: An overview on super-resolution images processing. Bandaoti Guangdian/Semicond. Optoelection. 30(4), 492–497 (2009)Google Scholar
  2. 2.
    Zhou, Y., Tang, Z., Hu, X.: Fast single image super resolution reconstruction via image separation. J. Netw. 9(7), 1811–1818 (2014)Google Scholar
  3. 3.
    Xiong, Z., Xu, D., Sun, X., et al.: Example-based super-resolution with soft information and decision. IEEE Trans. Multimed. 15(6), 1458–1465 (2013)CrossRefGoogle Scholar
  4. 4.
    Kim, W.H., Lee, J.S.: Blind single image super resolution with low computational complexity. Multimed. Tools Appl. (2016). doi: 10.1007/s11042-016-3396-0 Google Scholar
  5. 5.
    Anver, J., Abdulla, P.: Single-image super-resolution using kernel recursive least squares. Signal Image Video Process. 10(8), 1–8 (2016)CrossRefGoogle Scholar
  6. 6.
    Cha, Y., Kim, S.: Edge-forming methods for color image zooming. IEEE Trans. Image Process. 15(8), 2315–2323 (2006)CrossRefGoogle Scholar
  7. 7.
    Stark, H., Oskoui, P.: High resolution image recovery from image-plane arrays, using convex projections. J. Opt. Soc. Am. A 6(11), 1715–1726 (1989)CrossRefGoogle Scholar
  8. 8.
    Irani, M., Peleg, S.: Improving resolution by image registration. Comput. Vis. Graph. Image Process. Graph. Models Image Process. 53, 231–239 (1991)Google Scholar
  9. 9.
    Schulz, R.R., Stevenson, R.L.: A Bayesian approach to image expansion for improved definition. IEEE Trans. Image Process. 3(3), 233–242 (1994)CrossRefGoogle Scholar
  10. 10.
    Nguyen, N., Milanfar, P., Golub, G.: A computationally efficient superresolution image reconstruction algorithm. IEEE Trans. Image Process. 10(4), 573–583 (2001)CrossRefzbMATHGoogle Scholar
  11. 11.
    Dong, W., Zhang, D., Shi, G., et al.: Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans. Image Process. 20(7), 1838–1857 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Maiseli, B.J., Elisha, O.A., Gao, H.: A multi-frame super-resolution method based on the variable-exponent nonlinear diffusion regularizer. Eurasip J. Image Video Process. 2015(1), 1–16 (2015)CrossRefGoogle Scholar
  13. 13.
    Ren, Z., He, C., Zhang, Q.: Fractional order total variation regularization for image super-resolution. Signal Process. 93(9), 2408–2421 (2013)CrossRefGoogle Scholar
  14. 14.
    Tsai, R.Y., Huang, T.S.: Multiple frame image restoration and registration. In: Huang, T. S Advances in Computer Vision and Image Processing, pp. 317–339. JAI Press, Greenwich (1984)Google Scholar
  15. 15.
    Kim, S.P., Su, W.Y.: Recursive high-resolution reconstruction of blurred multi-frame images. IEEE Trans. Image Process. 2(4), 534–539 (1993)CrossRefGoogle Scholar
  16. 16.
    Rhee, S.H., Kang, M.G.: Discrete cosine transform-based regularized high-resolution image reconstruction algorithm. Opt. Eng. 38(8), 1348–1356 (1999)CrossRefGoogle Scholar
  17. 17.
    Vandewalle, P., Ssstrunk, S., Vetterli, M.: A frequency domain approach to registration of aliased images with application to super-resolution. Eurasip J. Appl. Signal Process. 2006(1), 1–14 (2006). (Special issue on super-resolution)Google Scholar
  18. 18.
    Shin, D.K., Moon, Y.S.: Super-resolution image reconstruction using wavelet based patch and discrete wavelet transform. J. Signal Process. Syst. 81(1), 71–81 (2015)CrossRefGoogle Scholar
  19. 19.
    Suryanarayana, G., Dhuli, R.: Shock filter based image super-resolution using dual-tree complex wavelet transform and singular value decomposition. Int. J. Comput. Math. Electr. Electron. Eng. 35(3), 1162–1178 (2016)CrossRefGoogle Scholar
  20. 20.
    Shah, A.J., Makwana, R., Gupta, S.B.: Single image super-resolution via non sub-sample Contourlet transform based learning and a Gabor prior. Int. J. Comput. Appl. 64(18), 32–38 (2013)Google Scholar
  21. 21.
    Kumar, N., Sethi, A.: Fast learning-based single image super-resolution. IEEE Trans. Multimed. 18(8), 1504–1515 (2016)CrossRefGoogle Scholar
  22. 22.
    Li, J., Wu, J., Deng, H.P., et al.: A self-learning image super-resolution method via sparse representation and non-local similarity. Neurocomputing 184, 196–206 (2016)CrossRefGoogle Scholar
  23. 23.
    Shah, A.J., Gupta, S.B.: Adaptive directional decomposition in non sub sample Contourlet transform domain for single image super resolution. Multimed. Tools Appl. 75(14), 8443–8467 (2016)CrossRefGoogle Scholar
  24. 24.
    Da, C.A., Zhou, J., Do, M.N.: The nonsubsampled Contourlet transform: theory, design, and applications. IEEE Trans. Image Process. 15(10), 3089–3101 (2006)CrossRefGoogle Scholar
  25. 25.
    Selvi, G.U.V., Nadarajan, R.: CT and MRI image compression using wavelet-based Contourlet transform and binary array technique. J. Real-Time Image Proc. (2014). doi: 10.1007/s11554-014-0400-7 Google Scholar
  26. 26.
    Yan, C., Zhang, K., Qi, Y.: Image denoising using modified nonsubsampled Contourlet transform combined with Gaussian scale mixtures model. In: Intelligence Science and Big Data Engineering. Image and Video Data Engineering, LNCS 9242, pp. 196–207. Springer, Amsterdam (2015)Google Scholar
  27. 27.
    Sonwane, M.K.R., Chuhan, M.B.: Multimodality image fusion by using activity level measurement and counterlet transform. Int. J. Recent Innov. Trends Comput. Commun. 2(3), 612–616 (2014)Google Scholar
  28. 28.
    Verma, S., Gupta, H.: Comparative result analysis of novel algorithm based on RBF network for image enhancement. Int. J. Adv. Comput. Res. 3(10), 17–23 (2013)Google Scholar
  29. 29.
    Saito, Y., Osana, Y.: Identification of artifacts in scenery images using color and line information by RBF network and k-means. Antimicrob. Agents Chemother. 57(8), 1065–1072 (2009)Google Scholar
  30. 30.
    Wang, Z., Bovik, A.C., Sheikh, H.R., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefGoogle Scholar
  31. 31.
    Panda, S.S., Prasad, M.S.R.S., Jena, G.: POCS based super-resolution image reconstruction using an adaptive regularization parameter. Int. J. Comput. Sci. Issues 8(5), 155–158 (2011)Google Scholar
  32. 32.
    Maiseli, B.J., Liu, Q., Elisha, O.A., et al.: Adaptive Charbonnier super-resolution method with robust edge preservation capabilities. J. Electron. Imaging 22(22), 451–459 (2013)Google Scholar
  33. 33.
    ITU Study Group 12: Series P: telephone transmission quality (methods for objective and subjective assessment of quality) methods for subjective determination of transmission quality. ITU-T P.800 (1996)Google Scholar

Copyright information

© Springer-Verlag London 2017

Authors and Affiliations

  • Zhiyong Shi
    • 1
    • 2
  • Fengchun Tian
    • 1
    Email author
  • Yande Wang
    • 2
  • Jian Ran
    • 1
  1. 1.College of Communication EngineeringChongqing UniversityChongqingChina
  2. 2.Chongqing Communication InstituteChongqingChina

Personalised recommendations