DocEnTr: An End-to-End Document Image Enhancement Transformer

Document Type

Conference Article

Publication Title

Proceedings - International Conference on Pattern Recognition

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.

First Page

1699

Last Page

1705

DOI

10.1109/ICPR56361.2022.9956101

Publication Date

1-1-2022

Comments

Open Access, Green

This document is currently not available here.

Share

COinS