Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
KODYM, O. HRADIŠ, M.
Originální název
TG2: text-guided transformer GAN for restoring document readability and perceived quality
Typ
článek v časopise ve Web of Science, Jimp
Jazyk
angličtina
Originální abstrakt
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.
Klíčová slova
Generative adversarial networks, Attention neural networks, Textual document restoration, Text inpainting
Autoři
KODYM, O.; HRADIŠ, M.
Vydáno
22. 9. 2021
Nakladatel
Springer Verlag
ISSN
1433-2825
Periodikum
International Journal on Document Analysis and Recognition
Ročník
2021
Číslo
1
Stát
Spolková republika Německo
Strany od
Strany do
14
Strany počet
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" }