Optoelectronics Letters, Volume. 15, Issue 2, 156(2019)

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

Jian-wen ZHAO... Qi-ping YUAN*, Juan QIN, Xiao-ping YANG and Zhi-hong CHEN |Show fewer author(s)
Author Affiliations
  • Tianjin Key Laboratory of Film Electronic and Communication Devices, School of Electrical and Electronic Engi-neering, Tianjin University of Technology, Tianjin 300384, China
  • show less

    In order to improve the super-resolution reconstruction effect of the single image, a novel multiple dictionaries learn-ing 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 im-age 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. Ex-periment 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 pro-posed method visually outperforms several algorithms.

    Tools

    Get Citation

    Copy Citation Text

    ZHAO Jian-wen, YUAN Qi-ping, QIN Juan, YANG Xiao-ping, CHEN Zhi-hong. Single image super-resolution reconstruction usingmultiple dictionaries and improved iterative back-projection[J]. Optoelectronics Letters, 2019, 15(2): 156

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: --

    Accepted: --

    Published Online: Apr. 16, 2019

    The Author Email: Qi-ping YUAN (Yqp1962@163.com)

    DOI:10.1007/s11801-019-8138-x

    Topics