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

Author:

Souibgui Mohamed Ali1,Biswas Sanket1,Jemni Sana Khamekhem2,Kessentini Yousri3,Fornes Alicia4,Llados Josep4,Pal Umapada5

Affiliation:

1. Universitat Autònoma de Barcelona,Computer Vision Center,Barcelona,Spain

2. University of Sfax,Digital Research Center of Sfax MIRACL Laboratory,Sfax,Tunisia

3. Digital Research Center of Sfax,SM@RTS Laboratory,Sfax,Tunisia

4. Universitat Autònoma de Barcelona,Computer Vision Center,Computer Science Dept.,Barcelona,Spain

5. Indian Statistical Institute,CVPR Unit,Kolkata,India

Funder

Generalitat de Catalunya

Publisher

IEEE

Reference44 articles.

1. H-DIBCO 2010 - Handwritten Document Image Binarization Competition

2. ICFHR 2018 Competition on Handwritten Document Image Binarization (H-DIBCO 2018)

3. Doc-former: End-to-end transformer for document understanding;appalaraju;ICCV,2021

4. Layoutlmv2: Multi-modal pre-training for visually-rich document understanding;xu,2020

5. A conditional gan based approach for distorted camera captured documents recovery;souibgui;In Mediterranean Conference on Pattern Recognition and Artificial Intelligence,2020

Cited by 21 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. GDB: Gated Convolutions-based Document Binarization;Pattern Recognition;2024-02

2. Enhancement of Old Historical Document by Image Processing from Gray scale to RGB Scale Conversion;International Journal of Advanced Research in Science, Communication and Technology;2023-11-17

3. A Lightweight NUet Model for Document Image Restoration;2023 16th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI);2023-10-28

4. DocDiff: Document Enhancement via Residual Diffusion Models;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26

5. Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction;2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW);2023-10-02

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3