logo

SCIENTIA SINICA Informationis, Volume 51 , Issue 8 : 1270(2021) https://doi.org/10.1360/SSI-2020-0364

Rational polynomial image magnification based on edge and distance constraints

More info
  • ReceivedNov 25, 2020
  • AcceptedFeb 27, 2021
  • PublishedAug 9, 2021

Abstract


Funded by

山东省高等学校青创科技支持计划(2019KJN042)

国家自然科学基金(U1609218,62007017)


References

[1] Sung Cheol Park , Min Kyu Park , Moon Gi Kang . Super-resolution image reconstruction: a technical overview. IEEE Signal Process Mag, 2003, 20: 21-36 CrossRef ADS Google Scholar

[2] Hsieh Hou , Andrews H. Cubic splines for image interpolation and digital filtering. IEEE Trans Acoust Speech Signal Process, 1978, 26: 508-517 CrossRef Google Scholar

[3] Munoz A, Blu T, Unser M. Least-squares image resizing using finite differences. IEEE Trans Image Process, 2001, 10: 1365-1378 CrossRef PubMed ADS Google Scholar

[4] Lei Zhang , Xiaolin Wu . An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans Image Process, 2006, 15: 2226-2238 CrossRef PubMed ADS Google Scholar

[5] Xin Li , Orchard M T. New edge-directed interpolation. IEEE Trans Image Process, 2001, 10: 1521-1527 CrossRef PubMed ADS Google Scholar

[6] Zhou D, Dong W, Shen X. Image zooming using directional cubic convolution interpolation. IET Image Processing, 2012, 6: 627-634 CrossRef Google Scholar

[7] Wu L, Liu Y, Brekhna Y. High-resolution images based on directional fusion of gradient. Comp Visual Media, 2016, 2: 31-43 CrossRef Google Scholar

[8] Zhang C, Zhang X, Li X, et al. Cubic surface fitting to image with edges as constraints. In: Proceedings of IEEE International Conference on Image Processing, Melbourne, 2013. 1046-1050. Google Scholar

[9] Zhang F, Zhang X, Qin X Y. Enlarging Image by Constrained Least Square Approach with Shape Preserving. J Comput Sci Technol, 2015, 30: 489-498 CrossRef Google Scholar

[10] Ji L, Wang P, Zhang Y. Bicubic Image Magnification Based on local interpolation. J Graph, 2019, 40(1): 143-149. Google Scholar

[11] Liu Y, Li X, Zhang X. Image enlargement method based on cubic surfaces with local features as constraints. Signal Processing, 2020, 166: 107266 CrossRef Google Scholar

[12] Ding N, Liu Y P, Fan L W. Single Image Super-Resolution via Dynamic Lightweight Database with Local-Feature Based Interpolation. J Comput Sci Technol, 2019, 34: 537-549 CrossRef Google Scholar

[13] Zhang Y, Wang P, Bao F. A Single-Image Super-Resolution Method Based on Progressive-Iterative Approximation. IEEE Trans Multimedia, 2020, 22: 1407-1422 CrossRef Google Scholar

[14] Jianchao Yang , Wright J, Huang T S. Image Super-Resolution Via Sparse Representation. IEEE Trans Image Process, 2010, 19: 2861-2873 CrossRef PubMed ADS Google Scholar

[15] Tang Y, Yuan Y, Yan P. Greedy regression in sparse coding space for single-image super-resolution. J Visual Communication Image Representation, 2013, 24: 148-159 CrossRef Google Scholar

[16] Dong W, Zhang L, Lukac R. Sparse Representation Based Image Interpolation With Nonlocal Autoregressive Modeling. IEEE Trans Image Process, 2013, 22: 1382-1394 CrossRef PubMed ADS Google Scholar

[17] Bevilacqua M, Roumy A, Guillemot C. Single-Image Super-Resolution via Linear Mapping of Interpolated Self-Examples. IEEE Trans Image Process, 2014, 23: 5334-5347 CrossRef PubMed ADS Google Scholar

[18] Huang J B, A Singh, N Ahuja. Single image super-resolution from transformed self-exemplars. In: Proceedings of IEEE Conference on Computer Vision & Pattern Recognition, Boston, 2015. 5197-5206. Google Scholar

[19] Zhang M, Desrosiers C. High-quality Image Restoration Using Low-Rank Patch Regularization and Global Structure Sparsity. IEEE Trans Image Process, 2019, 28: 868-879 CrossRef PubMed ADS Google Scholar

[20] Liu J, Xie Y, Song H, et al. Residual Attention Network for Wavelet Domain Super-Resolution. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, 2020. 2033-2037. Google Scholar

[21] Xu H, Yan J, Persson N, et al. Fractal dimension invariant filtering and its CNN-based implementation, In: Proceedings of IEEE Conference on Computer Vision & Pattern Recognition, Hawaii, 2017. 3825-3833. Google Scholar

[22] Xu H, Zhai G, Yang X. Single Image Super-resolution With Detail Enhancement Based on Local Fractal Analysis of Gradient. IEEE Trans Circuits Syst Video Technol, 2013, 23: 1740-1754 CrossRef Google Scholar

[23] Zhang Y, Fan Q, Bao F, et al. Single-image super-resolution based on rational fractal interpolation. IEEE Trans Image Process, 2018, 22(8): 3782-3797. Google Scholar

[24] Zhang X, Liu Q, Li X. Non?łocal feature back?projection for image super?resolution. IET Image Processing, 2016, 10: 398-408 CrossRef Google Scholar

[25] Bevilacqua M, Roumy A, Guillemot C, et al. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of British Machine Vision Conference, Surrey, 2012. 135.1-135.10. Google Scholar

[26] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations. In: Proceedings of International Conference on Curves and Surfaces, Avignon, 2010. 711-730. Google Scholar

[27] Martin D, Fowlkes C, Tal D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics, In: Proceedings of Eighth IEEE International Conference on Computer Vision, Vancouver, 2001. 416-423. Google Scholar

[28] Tai Y, Yang J, Liu X. Image super-resolution via deep recursive residual network. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 2017. 2790-2798. Google Scholar

[29] Kaplan C S. Aliasing artifacts and accidental algorithmic art. In: Proceedings of the Renaissance Banff: Bridges 2005: Mathematical Connections in Art, Music and Science, Banff, 2005. 349-356. Google Scholar

  • Figure 1

    (Color online) Curve sampling

  • Figure 4

    (Color online) Surface constructed by three methods. (a) The new method; (b) least squares; (c) biquadratic interpolation

  • Table 1   PSNR and SSIM values of Set5 images magnified by 8 methods
  • Table 2   PSNR and SSIM values of Set14 images magnified by 8 methods
  • Table 3   Average PSNR and SSIM values of BSD100 and Urban100 images magnified by 8 methods
  • Table 4   Average time to magnify the images of $256\times~256$ by 8 methods
    Bicubic NARM SISRRFI DCC SRPIA IECSLFC IRLRGSS New
    Time (s) 0.009 393.374 320.068 1.908 283.563 67.250 188.385 0.016
  • Table 5   Average PSNR and SSIM values of Set5 and Aliasing15 images magnified by two methods
qqqq

Contact and support