Text Image Deblurring Using Text-Specific Properties

Hojin Cho1 Jue Wang2 Seungyong Lee1
1POSTECH 2Adobe

Proc. 12th European Conference on Computer Vision (ECCV 2012)


Synthetically blurred text image & PSF Our method's result
 
Real blurry text image Our method's result

Abstract

State-of-the-art blind image deconvolution approaches have difficulties when dealing with text images, since they rely on natural image statistics which do not respect the special properties of text images. On the other hand, previous document image restoring systems and the recently proposed black-andwhite document image deblurring method are limited, and cannot handle large motion blurs and complex background. We propose a novel text image deblurring method which takes into account the specific properties of text images. Our method extends the commonly used optimization framework for image deblurring to allow domain-specific properties to be incorporated in the optimization process. Experimental results show that our method can generate higher quality deblurring results on text images than previous approaches.

Paper
PDF(3.94MB)
Supp. Material (High Resolution)
PDF(96.1MB)
Supp. Material (Low Resolution)
PDF(52.1MB)

BibTex

@inproceedings{cho_eccv2012,
  author = {Hojin Cho and Jue Wang and Seungyong Lee},
  title = {Text Image Deblurring Using Text-Specific Properties},
  booktitle = {Proc. 12th European Conference on Computer Vision (ECCV 2012)},
  year = {2012}
}