Hugging Face's logo

Spaces:
topdu
/
OpenOCR-UniRec-Demo
Sleeping

App Files Community
OpenOCR-UniRec-Demo / README_ch.md
duyongkun
update app
5de2f8f
preview code
|
Raw
History Blame Contribute Delete
22.8 kB

A newer version of the Gradio SDK is available: 6.28.0

Upgrade

OpenOCR: A general OCR system with accuracy and efficiency

如果您觉得本项目有帮助，请为我们点亮Star🌟

license PyPI

🚀 快速开始 | 简体中文 | English

我们致力于构建场景文本检测与识别模型的统一训练评估基准。基于此基准，我们推出了兼顾精度与效率的通用OCR系统——OpenOCR。本仓库同时作为复旦大学FVL实验室OCR团队的官方代码库。

我们诚挚欢迎研究者推荐OCR相关算法，并指出潜在的事实性错误或代码缺陷。收到建议后，我们将及时评估并严谨复现。期待与您携手推进OpenOCR发展，持续为OCR社区贡献力量！

核心特性

自研STR算法

  • SVTRv2 (Yongkun Du, Zhineng Chen*, Hongtao Xie, Caiyan Jia, Yu-Gang Jiang. SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition, ICCV 2025. Doc, Paper)
  • IGTR (Yongkun Du, Zhineng Chen*, Yuchen Su, Caiyan Jia, Yu-Gang Jiang. Instruction-Guided Scene Text Recognition, TPAMI 2025. Doc, Paper)
  • CPPD (Yongkun Du, Zhineng Chen*, Caiyan Jia, Xiaoting Yin, Chenxia Li, Yuning Du, Yu-Gang Jiang. Context Perception Parallel Decoder for Scene Text Recognition, TPAMI 2025. PaddleOCR Doc, Paper)
  • SMTR&FocalSVTR (Yongkun Du, Zhineng Chen*, Caiyan Jia, Xieping Gao, Yu-Gang Jiang. Out of Length Text Recognition with Sub-String Matching, AAAI 2025. Doc, Paper)
  • DPTR (Shuai Zhao, Yongkun Du, Zhineng Chen*, Yu-Gang Jiang. Decoder Pre-Training with only Text for Scene Text Recognition, ACM MM 2024. Paper)
  • CDistNet (Tianlun Zheng, Zhineng Chen*, Shancheng Fang, Hongtao Xie, Yu-Gang Jiang. CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition, IJCV 2024. Paper)
  • MRN (Tianlun Zheng, Zhineng Chen*, Bingchen Huang, Wei Zhang, Yu-Gang Jiang. MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition, ICCV 2023. Paper, Code)
  • TPS++ (Tianlun Zheng, Zhineng Chen*, Jinfeng Bai, Hongtao Xie, Yu-Gang Jiang. TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition, IJCAI 2023. Paper, Code)
  • SVTR (Yongkun Du, Zhineng Chen*, Caiyan Jia, Xiaoting Yin, Tianlun Zheng, Chenxia Li, Yuning Du, Yu-Gang Jiang. SVTR: Scene Text Recognition with a Single Visual Model, IJCAI 2022 (Long). PaddleOCR Doc, Paper)
  • NRTR (Fenfen Sheng, Zhineng Chen, Bo Xu. NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition, ICDAR 2019. Paper)

近期更新

快速开始

注意: OpenOCR支持ONNX和PyTorch双框架推理，环境相互独立。使用ONNX推理时无需安装PyTorch，反之亦然。

1. ONNX推理

安装OpenOCR及依赖: 

pip install openocr-python
pip install onnxruntime

使用示例: 

from openocr import OpenOCR
onnx_engine = OpenOCR(backend='onnx', device='cpu')
img_path = '/path/img_path or /path/img_file'
result, elapse = onnx_engine(img_path)

2. PyTorch推理

环境依赖: 

conda create -n openocr python==3.8
conda activate openocr
# 安装GPU版本
conda install pytorch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 pytorch-cuda=11.8 -c pytorch -c nvidia
# 或CPU版本
conda install pytorch torchvision torchaudio cpuonly -c pytorch

2.1 Python包安装

安装OpenOCR:

pip install openocr-python

使用示例:

from openocr import OpenOCR
engine = OpenOCR()
img_path = '/path/img_path or /path/img_file'
result, elapse = engine(img_path)

# Server模式
# engine = OpenOCR(mode='server')

2.2 源码安装 

git clone https://github.com/Topdu/OpenOCR.git
cd OpenOCR
pip install -r requirements.txt
wget https://github.com/Topdu/OpenOCR/releases/download/develop0.0.1/openocr_det_repvit_ch.pth
wget https://github.com/Topdu/OpenOCR/releases/download/develop0.0.1/openocr_repsvtr_ch.pth
# Server识别模型
# wget https://github.com/Topdu/OpenOCR/releases/download/develop0.0.1/openocr_svtrv2_ch.pth

使用命令:

# 端到端OCR系统: 检测+识别
python tools/infer_e2e.py --img_path=/path/img_path or /path/img_file
# 单独检测模型
python tools/infer_det.py --c ./configs/det/dbnet/repvit_db.yml --o Global.infer_img=/path/img_path or /path/img_file
# 单独识别模型
python tools/infer_rec.py --c ./configs/rec/svtrv2/repsvtr_ch.yml --o Global.infer_img=/path/img_path or /path/img_file
导出ONNX模型 
pip install onnx
python tools/toonnx.py --c configs/rec/svtrv2/repsvtr_ch.yml --o Global.device=cpu
python tools/toonnx.py --c configs/det/dbnet/repvit_db.yml --o Global.device=cpu
ONNXRuntime推理 
pip install onnxruntime
# 端到端OCR系统
python tools/infer_e2e.py --img_path=/path/img_path or /path/img_file --backend=onnx --device=cpu
# 检测模型
python tools/infer_det.py --c ./configs/det/dbnet/repvit_db.yml --o Global.backend=onnx Global.device=cpu Global.infer_img=/path/img_path or /path/img_file
# 识别模型
python tools/infer_rec.py --c ./configs/rec/svtrv2/repsvtr_ch.yml --o Global.backend=onnx Global.device=cpu Global.infer_img=/path/img_path or /path/img_file

本地Demo 

pip install gradio==4.20.0
wget https://github.com/Topdu/OpenOCR/releases/download/develop0.0.1/OCR_e2e_img.tar
tar xf OCR_e2e_img.tar
# 启动Demo
python demo_gradio.py

算法复现计划

场景文本识别(STR)

方法 会议/期刊 训练支持 评估支持 贡献者
CRNN TPAMI 2016 ✅ ✅
ASTER TPAMI 2019 ✅ ✅ pretto0
NRTR ICDAR 2019 ✅ ✅
SAR AAAI 2019 ✅ ✅ pretto0
MORAN PR 2019 ✅ ✅
DAN AAAI 2020 ✅ ✅
RobustScanner ECCV 2020 ✅ ✅ pretto0
AutoSTR ECCV 2020 ✅ ✅
SRN CVPR 2020 ✅ ✅ pretto0
SEED CVPR 2020 ✅ ✅
ABINet CVPR 2021 ✅ ✅ YesianRohn
VisionLAN ICCV 2021 ✅ ✅ YesianRohn
PIMNet ACM MM 2021 TODO
SVTR IJCAI 2022 ✅ ✅
PARSeq ECCV 2022 ✅ ✅
MATRN ECCV 2022 ✅ ✅
MGP-STR ECCV 2022 ✅ ✅
LPV IJCAI 2023 ✅ ✅
MAERec(Union14M) ICCV 2023 ✅ ✅
LISTER ICCV 2023 ✅ ✅
CDistNet IJCV 2024 ✅ ✅ YesianRohn
BUSNet AAAI 2024 ✅ ✅
DCTC AAAI 2024 TODO
CAM PR 2024 ✅ ✅
OTE CVPR 2024 ✅ ✅
CFF IJCAI 2024 TODO
DPTR ACM MM 2024 fd-zs
VIPTR ACM CIKM 2024 TODO
IGTR TPAMI 2025 ✅ ✅
SMTR AAAI 2025 ✅ ✅
CPPD TPAMI 2025 ✅ ✅
FocalSVTR-CTC AAAI 2025 ✅ ✅
SVTRv2 ICCV 2025 ✅ ✅
ResNet+Trans-CTC ✅ ✅
ViT-CTC ✅ ✅

核心贡献者

复旦大学FVL实验室的Yiming Lei (pretto0), Xingsong Ye (YesianRohn), and Shuai Zhao (fd-zs)在Zhineng Chen老师(个人主页)指导下完成了主要算法复现工作，感谢他们的贡献。

场景文本检测(STD)

开发中

端到端文本识别(Text Spotting)

开发中

引用

如果我们的工作对您的研究有所帮助，请引用：

@inproceedings{Du2024SVTRv2,
      title={SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition},
      author={Yongkun Du and Zhineng Chen and Hongtao Xie and Caiyan Jia and Yu-Gang Jiang},
      booktitle={ICCV},
      year={2025}
}

致谢

本代码库基于PaddleOCR、PytorchOCR和MMOCR构建，感谢他们的出色工作！