Publication detail

TG2: text-guided transformer GAN for restoring document readability and perceived quality

KODYM, O. HRADIŠ, M.

Original Title

TG2: text-guided transformer GAN for restoring document readability and perceived quality

Type

journal article in Web of Science

Language

English

Original Abstract

Most image enhancement methods focused on restoration of digitized textual documents are limited to cases where the text information is still preserved in the input image, which may often not be the case. In this work, we propose a novel generative document restoration method which allows conditioning the restoration on a guiding signal in form of target text transcription and which does not need paired high- and low-quality images for training. We introduce a neural network architecture with an implicit text-to-image alignment module. We demonstrate good results on inpainting, debinarization and deblurring tasks, and we show that the trained models can be used to manually alter text in document images.A user study shows that that human observers confuse the outputs of the proposed enhancement method with reference high-quality images in as many as 30% of cases.

Keywords

Generative adversarial networks, Attention neural networks, Textual document restoration, Text inpainting

Authors

KODYM, O.; HRADIŠ, M.

Released

22. 9. 2021

Publisher

Springer Verlag

ISBN

1433-2825

Periodical

International Journal on Document Analysis and Recognition

Year of study

2021

Number

1

State

Federal Republic of Germany

Pages from

1

Pages to

14

Pages count

14

URL

https://link.springer.com/article/10.1007/s10032-021-00387-z

BibTex

@article{BUT175769,
  author="Oldřich {Kodym} and Michal {Hradiš}",
  title="TG2: text-guided transformer GAN for restoring document readability and perceived quality",
  journal="International Journal on Document Analysis and Recognition",
  year="2021",
  volume="2021",
  number="1",
  pages="1--14",
  doi="10.1007/s10032-021-00387-z",
  issn="1433-2825",
  url="https://link.springer.com/article/10.1007/s10032-021-00387-z"
}