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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU142892" target="_blank" >RIV/00216305:26230/21:PU142892 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s10032-021-00387-z" target="_blank" >https://link.springer.com/article/10.1007/s10032-021-00387-z</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10032-021-00387-z" target="_blank" >10.1007/s10032-021-00387-z</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

International Journal on Document Analysis and Recognition

ISSN

1433-2833

e-ISSN

1433-2825

Svazek periodika

2021

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

14

Strana od-do

1-14

Kód UT WoS článku

000698372200001

EID výsledku v databázi Scopus

2-s2.0-85115335316