@InProceedings{MohamedAliSouibgui2022,
author="Mohamed Ali Souibgui
and Sanket Biswas
and Sana Khamekhem Jemni
and Yousri Kessentini
and Alicia Fornes
and Josep Llados
and Umapada Pal",
title="DocEnTr: An End-to-End Document Image Enhancement Transformer",
booktitle="26th International Conference on Pattern Recognition",
year="2022",
pages="1699--1705",
optkeywords="Degradation",
optkeywords="Head",
optkeywords="Optical character recognition",
optkeywords="Self-supervised learning",
optkeywords="Benchmark testing",
optkeywords="Transformers",
optkeywords="Magnetic heads",
abstract="Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The encoder operates directly on the pixel patches with their positional information without the use of any convolutional layers, while the decoder reconstructs a clean image from the encoded patches. Conducted experiments show a superiority of the proposed model compared to the state-of the-art methods on several DIBCO benchmarks. Code and models will be publicly available at: https://github.com/dali92002/DocEnTR",
optnote="DAG; 600.121; 600.162; 602.230; 600.140",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3730), last updated on Thu, 27 Apr 2023 14:52:16 +0200",
doi="10.1109/ICPR56361.2022.9956101",
file=":http://refbase.cvc.uab.es/files/SBJ2022.pdf:PDF"
}