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

TL;DR

DavarOCR is an open-source toolbox that integrates 19 advanced OCR and document understanding algorithms, supporting various sub-tasks and promoting development in academia and industry.

Contribution

It introduces a comprehensive, modular OCR toolbox with extensive task support and detailed resources, surpassing previous open-source solutions.

Findings

Supports 9 different task forms with 19 algorithms

Provides detailed usage instructions and trained models

Enhances modularity for cross-domain technology sharing

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.