Publication Details

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

KODYM Oldřich and HRADIŠ Michal. TG2: text-guided transformer GAN for restoring document readability and perceived quality. International Journal on Document Analysis and Recognition (IJDAR), vol. 2021, no. 1, pp. 1-14. ISSN 1433-2825. Available from: https://link.springer.com/article/10.1007/s10032-021-00387-z
Czech title
TG2: vylepšení čitelnosti digitalizovaných dokumentů pomocí modelů transformer GAN s přepisem
Type
journal article
Language
english
Authors
URL
Keywords

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

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.

Published
2021
Pages
1-14
Journal
International Journal on Document Analysis and Recognition (IJDAR), vol. 2021, no. 1, ISSN 1433-2825
Book
International Journal on Document Analysis and Recognition
Publisher
Springer Verlag
DOI
UT WoS
000698372200001
EID Scopus
BibTeX
@ARTICLE{FITPUB12333,
   author = "Old\v{r}ich Kodym and Michal Hradi\v{s}",
   title = "TG2: text-guided transformer GAN for restoring document readability and perceived quality",
   pages = "1--14",
   booktitle = "International Journal on Document Analysis and Recognition",
   journal = "International Journal on Document Analysis and Recognition (IJDAR)",
   volume = 2021,
   number = 1,
   year = 2021,
   publisher = "Springer Verlag",
   ISSN = "1433-2825",
   doi = "10.1007/s10032-021-00387-z",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12333"
}
Back to top