International Journal of Computational Intelligence Systems

Volume 14, Issue 1, 2021, Pages 1315 - 1321

Blur2Sharp: A GAN-Based Model for Document Image Deblurring

Authors
Hala Neji1, 2, 3, *, ORCID, Mohamed Ben Halima2, Tarek M. Hamdani2, Javier Nogueras-Iso3, ORCID, Adel M. Alimi2, 4
1National Engineering School of Gabes (ENIG), University of Gabes, Gabes, Tunisia
2REGIM Lab (Research Groups in Intelligent Machines), University of Sfax, National Engineering School of Sfax (ENIS), Sfax, Tunisia
3Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain
4Department of Electrical and Electronic Engineering Science, Faculty of Engineering and the Built Environment, University of Johannesburg, Johannesburg, South Africa
*Corresponding author. Email: hala.neji@ieee.org
Corresponding Author
Hala Neji
Received 16 January 2021, Accepted 25 March 2021, Available Online 13 April 2021.
DOI
10.2991/ijcis.d.210407.001How to use a DOI?
Keywords
Generative adversarial network (GAN); Cycle-consistent generative adversarial network (CycleGAN); Document deblurring; Blind deconvolution; Motion blur; Out-of-focus blur
Abstract

The advances in mobile technology and portable cameras have facilitated enormously the acquisition of text images. However, the blur caused by camera shake or out-of-focus problems may affect the quality of acquired images and their use as input for optical character recognition (OCR) or other types of document processing. This work proposes an end-to-end model for document deblurring using cycle-consistent adversarial networks. The main novelty of this work is to achieve blind document deblurring, i.e., deblurring without knowledge of the blur kernel. Our method, named “Blur2Sharp CycleGAN,” generates a sharp image from a blurry one and shows how cycle-consistent generative adversarial networks (CycleGAN) can be used in document deblurring. Using only a blurred image as input, we try to generate the sharp image. Thus, no information about the blur kernel is required. In the evaluation part, we use peak signal to noise ratio (PSNR) and structural similarity index (SSIM) to compare the deblurring images. The experiments demonstrate a clear improvement in visual quality with respect to the state-of-the-art using a dataset of text images.

Copyright
© 2021 The Authors. Published by Atlantis Press B.V.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

Journal
International Journal of Computational Intelligence Systems
Volume-Issue
14 - 1
Pages
1315 - 1321
Publication Date
2021/04/13
ISSN (Online)
1875-6883
ISSN (Print)
1875-6891
DOI
10.2991/ijcis.d.210407.001How to use a DOI?
Copyright
© 2021 The Authors. Published by Atlantis Press B.V.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - JOUR
AU  - Hala Neji
AU  - Mohamed Ben Halima
AU  - Tarek M. Hamdani
AU  - Javier Nogueras-Iso
AU  - Adel M. Alimi
PY  - 2021
DA  - 2021/04/13
TI  - Blur2Sharp: A GAN-Based Model for Document Image Deblurring
JO  - International Journal of Computational Intelligence Systems
SP  - 1315
EP  - 1321
VL  - 14
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.210407.001
DO  - 10.2991/ijcis.d.210407.001
ID  - Neji2021
ER  -