Optoelectronics Letters

, Volume 13, Issue 6, pp 439–443 | Cite as

Application of regularization technique in image super-resolution algorithm via sparse representation

  • De-tian Huang (黄德天)
  • Wei-qin Huang (黄炜钦)
  • Hui Huang (黄辉)
  • Li-xin Zheng (郑力新)


To make use of the prior knowledge of the image more effectively and restore more details of the edges and structures, a novel sparse coding objective function is proposed by applying the principle of the non-local similarity and manifold learning on the basis of super-resolution algorithm via sparse representation. Firstly, the non-local similarity regularization term is constructed by using the similar image patches to preserve the edge information. Then, the manifold learning regularization term is constructed by utilizing the locally linear embedding approach to enhance the structural information. The experimental results validate that the proposed algorithm has a significant improvement compared with several super-resolution algorithms in terms of the subjective visual effect and objective evaluation indices.

Document code


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Yang J, Wright J, Huang T S and Ma Y, IEEE Transactions on Image Processing 19, 2861 (2010).ADSMathSciNetCrossRefGoogle Scholar
  2. [2]
    Zeyde R, Elad M and Protter M, On Single Image Scale-Up Using Sparse-Representations, International Conference on Curves and Surfaces, 711 (2010).MATHGoogle Scholar
  3. [3]
    Timofte R, De V and Van Gool L, Anchored Neighborhood Regression for Fast Example-Based Super-Resolution, IEEE International Conference on Computer Vision, 1920 (2013).Google Scholar
  4. [4]
    Timofte R, Smet V D and Gool L V, A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution, Asian Conference on Computer Vision Springer International Publishing, 111 (2014).Google Scholar
  5. [5]
    Roy S and Chaudhuri S S, International Journal of Modern Education and Computer Science 8, 46 (2016).CrossRefGoogle Scholar
  6. [6]
    Ma J, Wang X Y, Zhang Z W and Liu Y L, Optoelectronics ·Laster 27, 87 (2016). (in Chinese)Google Scholar
  7. [7]
    Dong W S, Zhang L, Lukac R and Shi G, IEEE Transactions on Image Processing 22, 1382 (2013)ADSMathSciNetCrossRefGoogle Scholar
  8. [8]
    Zheng X T, Yuan Y and Lu X Q, Acta Optica Sinica 37, 57 (2017). (in Chinese)Google Scholar
  9. [9]
    Donoho D L, Communications on Pure and Applied Mathematics 59, 907 (2010).CrossRefGoogle Scholar
  10. [10]
    Chen Y, Hou C P and Zhou Y, Journal of Optoelectronics ·Laster 26, 1618 (2015). (in Chinese)Google Scholar
  11. [11]
    Roweis S T and Saul L K, Science 290, 2323 (2000).ADSCrossRefGoogle Scholar
  12. [12]
    Chang H, Yeung D Y and Xiong Y, Super-Resolution Through Neighbor Embedding, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 275 (2004).Google Scholar
  13. [13]
    Li X F, Zeng L, Xu J and Ma S Q, Journal of University of Electronic Science & Technology of China 44, 22 (2015).Google Scholar
  14. [14]
    Huang D T, Huang W Q, Gu P T, Liu P Z and Luo Y M, Infrared Physics & Technology 83, 103 (2017).ADSCrossRefGoogle Scholar
  15. [15]
    Martin B D, Charless F, Doron T and Malik J, A Database of human Segmented Natural Images and Its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics, IEEE International Conference on Computer Vision, 416 (2001).Google Scholar

Copyright information

© Tianjin University of Technology and Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  • De-tian Huang (黄德天)
    • 1
    • 2
    • 3
  • Wei-qin Huang (黄炜钦)
    • 1
  • Hui Huang (黄辉)
    • 2
  • Li-xin Zheng (郑力新)
    • 1
    • 3
  1. 1.College of EngineeringHuaqiao UniversityQuanzhouChina
  2. 2.College of Mechanical Engineering and AutomationHuaqiao UniversityXiamenChina
  3. 3.University Engineering Research Center of Fujian Province Industrial Intelligent Technology and SystemsHuaqiao UniversityQuanzhouChina

Personalised recommendations