Advertisement

Regularized Super-Resolution Reconstruction Based on Edge Prior

  • Zhenzhao Luo
  • Dongfang Chen
  • Xiaofeng Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10956)

Abstract

Considering that there is no edge constraint in general regularized algorithms, an improved super-resolution algorithm with additional regularization is presented. The Difference Curvature (DC) regularization which containing the image edge information is joined into the cost function, for further preserving the edge details at image reconstruction procedure. In each iteration, the DC regularization will extract the edge of high-resolution prediction frame and low-resolution observation frame. And the error between them is used to compensate the edge loss which may be smoothed by existing regularization. The reconstructed result is approximated to the original image by constraining the error between them. Then the optimum solution will be worked out by utilizing the steepest descent method. This approach is intended to constrain the edges of the image directly rather than simply avoiding the edge being smoothed. Comparing with other single regularization algorithms, experiment results indicate that the proposed algorithm can restore the edge details of reconstructed image well. And it also shows that various prior knowledge are important to image reconstruction process.

Keywords

Image reconstruction Super-resolution Edge Prior 

References

  1. 1.
    Tian, J., Ma, K.K.: A survey on super-resolution imaging. Signal Image Video Process. 5(3), 329–342 (2011)CrossRefGoogle Scholar
  2. 2.
    Tsai, R.Y., Huang, T.S.: Multiframe image restoration and registration. In: Advances in Computer Vision and Image Processing, vol. 1 (1984)Google Scholar
  3. 3.
    Yu, X., Cen, X.: An image reconstruction approach in discrete cosine transform domain. In: International Congress on Image and Signal Processing, vol. 57, pp. 587–591. IEEE (2013)Google Scholar
  4. 4.
    Lama, R.K., Shin, S., Kang, M., Kwon, G.R., Choi, M.R.: Interpolation using wavelet transform and discrete cosine transform for high resolution display. In: IEEE International Conference on Consumer Electronics, pp. 184–186. IEEE (2016)Google Scholar
  5. 5.
    Nazren, A.R.A., Yaakob, S.N., Ngadiran, R., Hisham, M.B., Wafi, N.M.: Improving iterative back projection super resolution model via anisotropic diffusion edge enhancement. In: International Conference on Robotics, Automation and Sciences, pp. 1–4. IEEE (2017)Google Scholar
  6. 6.
    Tang, Z., Deng, M., Xiao, C., Yu, J.: Projection onto convex sets super-resolution image reconstruction based on wavelet bi-cubic interpolation. In: International Conference on Electronic and Mechanical Engineering and Information Technology, vol. 175, pp. 351–354. IEEE (2011)Google Scholar
  7. 7.
    Shen, H., Zhang, L., Huang, B., Li, P.: A map approach for joint motion estimation, segmentation, and super resolution. IEEE Trans. Image Process. 16(2), 479–490 (2007)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Irani, M., Peleg, S.: Improving resolution by image registration. Cvgip Graph. Models Image Process. 53(3), 231–239 (1991)CrossRefGoogle Scholar
  9. 9.
    Stark, H., Oskoui, P.: High-resolution image recovery from image-plane arrays, using convex projections. J. Optical Soc. Am. Opt. Image Sci. 6(11), 1715 (1989)CrossRefGoogle Scholar
  10. 10.
    Shao, W.Z., Wei, Z.H.: Super-resolution reconstruction based on generalized Huber-MRF image modeling. J. Softw. 18(10), 2434–2444 (2007)CrossRefGoogle Scholar
  11. 11.
    Shao, W.Z., Deng, H.S., Wei, Z.H.: A posterior mean approach for MRF-based spatially adaptive multi-frame image super-resolution. Signal Image Video Process. 9(2), 437–449 (2015)CrossRefGoogle Scholar
  12. 12.
    Zhang, X., Lam, E.Y., Wu, E.X., Wong, K.K.Y.: Application of Tikhonov regularization to super-resolution reconstruction of brain MRI images. In: Gao, X., Müller, H., Loomes, Martin J., Comley, R., Luo, S. (eds.) MIMI 2007. LNCS, vol. 4987, pp. 51–56. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-79490-5_8CrossRefGoogle Scholar
  13. 13.
    Liu, W., Chen, Z., Chen, Y., Yao, R.: An ℓ1/2-BTV regularization algorithm for super-resolution. In: International Conference on Computer Science and Network Technology, pp. 1274–1281. IEEE (2016)Google Scholar
  14. 14.
    Mofidi, M., Hajghassem, H., Afifi, A.: An adaptive parameter estimation in a btv regularized image super-resolution reconstruction. Adv. Electr. Comput. Eng. 17(3), 3–10 (2017)CrossRefGoogle Scholar
  15. 15.
    Chen, Q., Montesinos, P., Sun, Q.S., Peng, A.H., Xia, D.S.: Adaptive total variation denoising based on difference curvature. Image Vis. Comput. 28(3), 298–306 (2010)CrossRefGoogle Scholar
  16. 16.
    Bai, X.B., Wang, K.Q., Wang, H.: Research on the classification of wood texture based on Gray Level Co-occurrence Matrix. J. Harbin Inst. Technol. 12, 021 (2005)Google Scholar
  17. 17.
    Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: International Conference on Pattern Recognition, pp. 2366–2369. IEEE (2010)Google Scholar
  18. 18.
    Silvestre-Blanes, J.: Structural similarity image quality reliability: determining parameters and window size. Signal Process. 91(4), 1012–1020 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.College of Computer Science and TechnologyWuhan University of Science and TechnologyWuhanChina
  2. 2.Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time IndustrialWuhanChina

Personalised recommendations