MCPcopy Index your code
hub / github.com/Topdu/OpenOCR

github.com/Topdu/OpenOCR @main

Chat with this repo
repository ↗ · DeepWiki ↗ · + Follow
2,347 symbols 5,764 edges 218 files 464 documented · 20%
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications

如果您觉得本项目有帮助,请为我们点亮Star🌟

license PyPI

简体中文 | English


OpenOCR 是由复旦大学FVL实验室姜育刚教授陈智能教授指导的OCR团队打造的开源平台,面向「文字检测与识别」、「公式与表格识别」、「文档解析和理解」等通用 OCR 任务。平台集成了统一的训练与评测基准、商用级 OCR 与文档解析系统,以及众多学术论文的核心代码复现。

OpenOCR 致力于构建一个为学术研究与实际应用搭建桥梁的通用 OCR 开源生态,推动 OCR 技术在研究前沿和产业场景中的协同发展与广泛落地。欢迎研究者、开发者和企业使用和提建议。

🚀 快速开始

核心特性

  • 🔥OpenDoc-0.1B: Ultra-Lightweight Document Parsing System with 0.1B Parameters

  • ⚡[快速开始] HuggingFace ModelScope [本地Demo]

    • 仅有0.1B参数的超轻量文档解析系统
    • 两阶段:版面分析PP-DocLayoutV2 + 文本、公式和表格统一识别自研模型UniRec-0.1B
    • 在UniRec-0.1B的原始版本中,仅支持文本和公式识别。在OpenDoc-0.1B中,我们重建了UniRec-0.1B,使其支持文本、公式和表格识别
    • 支持中、英文文档解析
    • OmniDocBench (v1.5)上指标为90.57%,超越众多基于多模态大模型的文档解析模型
  • 🔥UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters

  • ⚡[使用文档] arXiv HuggingFace ModelScope [本地Demo] [HuggingFace模型下载] [ModelScope模型下载] [UniRec40M Dataset]

    • 识别纯文本(单词、行、段落)、公式(单行、多行)、以及文本与公式混合的内容
    • 0.1B 参数量
    • 在 4000 万数据(UniRec40M)上从零开始训练,不使用任何预训练
    • 支持中文和英文文本/公式识别
  • 🔥OpenOCR: A general OCR system with accuracy and efficiency

  • ⚡[快速开始] [![HuggingFace](https://img.shields.io/badge/OpenOCR-_Demo_on_HuggingFace-yellow?logo=data:image/png;base64,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

Core symbols most depended-on inside this repo

get
called by 286
tools/utils/stats.py
encode
called by 62
openrec/preprocess/dptr_label_encode.py
decode
called by 30
tools/infer_unirec_onnx.py
merge_dict
called by 26
tools/engine/config.py
update
called by 25
tools/utils/stats.py
apply
called by 24
openrec/preprocess/cmer_label_encode.py
transform
called by 23
opendet/preprocess/__init__.py
parse_args
called by 21
tools/utility.py

Shape

Method 1,448
Class 474
Function 424
Route 1

Languages

Python100%

Modules by API surface

openrec/modeling/decoders/dptr_parseq_clip_b_decoder.py81 symbols
openrec/preprocess/auto_augment.py69 symbols
openrec/preprocess/cmer_label_encode.py49 symbols
openrec/preprocess/resize.py46 symbols
openrec/modeling/encoders/svtrv2_lnconv_two33.py45 symbols
openrec/modeling/cmer_modeling/modeling_cmer.py44 symbols
openrec/modeling/encoders/svtrv2_lnconv.py42 symbols
openrec/preprocess/abinet_aug.py41 symbols
openrec/modeling/encoders/cam_encoder.py35 symbols
openrec/modeling/decoders/robustscanner_decoder.py35 symbols
tools/utils/opendoc_onnx_utils/utils.py34 symbols
openrec/optimizer/lr.py34 symbols

For agents

$ claude mcp add OpenOCR \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact