Text image deblurring using kernel sparsity prior

Xianyong Fang, Qiang Zhou, Jianbing Shen, Christian Jacquemin, Ling Shao

Research output: Contribution to journalArticlepeer-review

14 Citations (Scopus)
9 Downloads (Pure)


Previous methods on text image motion deblurring seldom consider the sparse characteristics of the blur kernel. This paper proposes a new text image motion deblurring method by exploiting the sparse properties of both text image itself and kernel. It incorporates the L₀-norm for regularizing the blur kernel in the deblurring model, besides the L₀ sparse priors for the text image and its gradient. Such a L₀-norm-based model is efficiently optimized by half-quadratic splitting coupled with the fast conjugate descent method. To further improve the quality of the recovered kernel, a structure-preserving kernel denoising method is also developed to filter out the noisy pixels, yielding a clean kernel curve. Experimental results show the superiority of the proposed method. The source code and results are available at: https://github.com/shenjianbing/text-image-deblur.
Original languageEnglish
Pages (from-to)997-1008
Number of pages12
JournalIEEE Transactions on Cybernetics
Issue number3
Early online date5 Nov 2018
Publication statusPublished - Mar 2020


  • L₀-norm
  • motion deblurring
  • text image
  • L-0-norm

Cite this