DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding

Liang Qiao, Hui Jiang, Ying Chen, Can Li, Pengfei Li +7 more
7/14/2022
cs.CV

Official code: hikopensource/DAVAR-Lab-OCR (762 stars, Apache-2.0, last commit 2023-11-16).

Abstract

This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms. DavarOCR provides detailed usage instructions and the trained models for each algorithm. Compared with the previous opensource OCR toolbox, DavarOCR has relatively more complete support for the sub-tasks of the cutting-edge technology of document understanding. In order to promote the development and application of OCR technology in academia and industry, we pay more attention to the use of modules that different sub-domains of technology can share. DavarOCR is publicly released at https://github.com/hikopensource/Davar-Lab-OCR.

View on arXivView PDF

Code Implementations(1)

hikopensource/DAVAR-Lab-OCROfficial100%
Apache-2.0

OCR toolbox from Davar-Lab

762152C++, ShellDec 30, 20202 years agoApache-2.0
darocr

Similar Papers

DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond

83% match1 repo1.8k2023

PDFVQA: A New Dataset for Real-World VQA on PDF Documents

81% match2023

DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models

81% match2024

Workshop on Document Intelligence Understanding

81% match2023

Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration

80% match2026

Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding

80% match2026

Cite this paper

@article{qiao2022davarocr,
  title  = {DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding},
  author = {Liang Qiao and Hui Jiang and Ying Chen and Can Li and Pengfei Li and Zaisheng Li and Baorui Zou and Dashan Guo and Yingda Xu and Yunlu Xu and Zhanzhan Cheng and Yi Niu},
  year   = {2022},
  eprint = {2207.06695},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.06695v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.06695.svg)](https://codeofpaper.com/paper/2207.06695)

Discussion