Advertisement

Optoelectronics Letters

, Volume 15, Issue 2, pp 156–160 | Cite as

Single image super-resolution reconstruction using multiple dictionaries and improved iterative back-projection

  • Jian-wen Zhao (赵建雯)
  • Qi-ping Yuan (袁其平)Email author
  • Juan Qin (秦娟)
  • Xiao-ping Yang (杨晓苹)
  • Zhi-hong Chen (陈志宏)
Article
  • 14 Downloads

Abstract

In order to improve the super-resolution reconstruction effect of the single image, a novel multiple dictionaries learning via support vector regression (SVR) and improved iterative back-projection (IBP) are proposed. To characterize the image structure, the low-frequency dictionary is constructed from the normalized brightness of low-frequency image patches in a discrete-cosine-transform (DCT) domain. Pixels determined by Gaussian weighting are added to the input vector to restore more high-frequency information when training the high-frequency image patch dictionary in the space domain. During post-processing, the improved IBP is employed to reduce regression errors each time. Experiment results show that the peak signal-to-noise ratio (PSNR)and structural similarity (SSIM) of the proposed method are enhanced by 1.6%–5.5% and 1.5%–13.1% compared with those of bicubic interpolation, and the proposed method visually outperforms several algorithms.

Document code

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Liu Chanzi, Chen Qingchun and Li Hengchao, Multimedia Tools and Applications 76, 14759 (2017).CrossRefGoogle Scholar
  2. [2]
    Yang Qi, Zhang Yanzhu, Zhao Tiebiao and Chen Yangquan, ISA Transactions 82, 163 (2017).Google Scholar
  3. [3]
    Zhang Xiang-jun and Wu Xiao-lin, IEEE Transactions on Image Processing 17, 887 (2008).MathSciNetCrossRefGoogle Scholar
  4. [4]
    Kourosh Jafari-Khouzani, IEEE Transactions on Medical Imaging 33, 1969 (2014)CrossRefGoogle Scholar
  5. [5]
    Dai Shao-sheng, Liu Jin-song, Xiang Hai-yan, Du Zhi-hui and Liu Qin, Optoelectronics Letters 10, 313 (2014).ADSCrossRefGoogle Scholar
  6. [6]
    Yang J., Wang Z., Lin Z., Cohen S. and Huang T., IEEE Transactions on Image Processing 21, 3467 (2012).ADSMathSciNetCrossRefGoogle Scholar
  7. [7]
    Wang Zhang-yang, Yang Ying-zhen, Wang Zhao-wen, Chang Shi-yu, Han Wei, Yang Jian-chao and Thomas S. Huang, Self-Tuned Deep Super Resolution, IEEE Conference on Computer Vision and Pattern Recognition Workshops, 1 (2015).Google Scholar
  8. [8]
    Huang Yuan-fei, Li Jie, Gao Xin-bo, He Li-huo and Lu Wen, IEEE Transactions on Image Processing 27, 5904 (2018).ADSMathSciNetCrossRefGoogle Scholar
  9. [9]
    Huang De-tian, Huang Wei-qin, Huang Hui and Zheng Li-xin, Optoelectronics Letters 13, 439 (2017).ADSCrossRefGoogle Scholar
  10. [10]
    Radu Timofte, Vincent De Smet and Luc Van Gool, A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution, Asian Conference on Computer Vision, 111 (2014).Google Scholar
  11. [11]
    Wang Hong, Lu Fang-fang and Li Jian-wu, Journal of Image and Graphics 21, 986 (2016). (in Chinese)Google Scholar
  12. [12]
    Yuan Qi-ping, Lin Hai-jie, Chen Zhi-hong and Yang Xiao-ping, Optics and Precision Engineering 24, 2302 (2016). (in Chinese)CrossRefGoogle Scholar
  13. [13]
    Ni K. S. and Nguyen T. Q., IEEE Transactions on Image Processing 16, 1596 (2007).ADSMathSciNetCrossRefGoogle Scholar
  14. [14]
    Liu Zhi-zhou, Dictionary Learning Based Super-Resolution Image Reconstruction, Xian University of Electronic Technology, 2011. (in Chinese)Google Scholar
  15. [15]
    Liu Feng-lain, Sun Meng-yao and Cai Wen-na, Optoelectronics Letters 13, 237 (2017).ADSCrossRefGoogle Scholar
  16. [16]
    Chang Chih-chung and Lin Chih-jen, ACM Transactions on Intelligent Systems and Technology 2, 27 (2011).Google Scholar
  17. [17]
    Chao Dong, Chen Change Loy, Kaiming He and Xiaoou Tang, IEEE Transactions on Pattern Analysis and Machine Intelligence 38, 295 (2016).CrossRefGoogle Scholar

Copyright information

© Tianjin University of Technology and Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Jian-wen Zhao (赵建雯)
    • 1
  • Qi-ping Yuan (袁其平)
    • 1
    Email author
  • Juan Qin (秦娟)
    • 1
  • Xiao-ping Yang (杨晓苹)
    • 1
  • Zhi-hong Chen (陈志宏)
    • 1
  1. 1.Tianjin Key Laboratory of Film Electronic and Communication Devices, School of Electrical and Electronic EngineeringTianjin University of TechnologyTianjinChina

Personalised recommendations