Go to file
dyning 4b57f052de fix img bug 2020-05-15 22:53:50 +08:00
configs Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleOCR into develop 2020-05-15 15:21:52 +08:00
doc fix img bug 2020-05-15 22:53:50 +08:00
ppocr valid det inference 2020-05-15 14:22:57 +08:00
tools Update utility.py 2020-05-15 22:46:06 +08:00
.pre-commit-config.yaml upload PaddleOCR code 2020-05-10 16:26:57 +08:00
.style.yapf upload PaddleOCR code 2020-05-10 16:26:57 +08:00
LICENSE Initial commit 2020-05-08 18:38:17 +08:00
README.md Merge pull request #42 from dyning/develop 2020-05-15 22:32:37 +08:00
requirments.txt update doc and requirments 2020-05-11 21:18:39 +08:00

README.md

简介

PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库助力使用者训练出更好的模型并应用落地。

特性

  • 超轻量级中文OCR总模型仅8.6M
    • 单模型支持中英文数字组合识别、竖排文本识别、长文本识别
    • 检测模型DB4.1M+识别模型CRNN4.5M
  • 多种文本检测训练算法EAST、DB
  • 多种文本识别训练算法Rosetta、CRNN、STAR-Net、RARE

超轻量级中文OCR体验

上图是超轻量级中文OCR模型效果展示更多效果图请见文末效果展示

1.环境配置

请先参考快速安装配置PaddleOCR运行环境。

2.模型下载

# 下载inference模型文件包
wget https://paddleocr.bj.bcebos.com/inference.tar
# inference模型文件包解压
tar -xf inference.tar

3.单张图像或者图像集合预测

以下代码实现了文本检测、识别串联推理在执行预测时需要通过参数image_dir指定单张图像或者图像集合的路径、参数det_model_dir指定检测inference模型的路径和参数rec_model_dir指定识别inference模型的路径。可视化识别结果默认保存到 ./inference_results 文件夹里面。

# 设置PYTHONPATH环境变量
export PYTHONPATH=.

# 预测image_dir指定的单张图像
python3 tools/infer/predict_system.py --image_dir="./doc/imgs/11.jpg" --det_model_dir="./inference/det/"  --rec_model_dir="./inference/rec/"

# 预测image_dir指定的图像集合
python3 tools/infer/predict_system.py --image_dir="./doc/imgs/" --det_model_dir="./inference/det/"  --rec_model_dir="./inference/rec/"

# 如果想使用CPU进行预测执行命令如下
python3 tools/infer/predict_system.py --image_dir="./doc/imgs/11.jpg" --det_model_dir="./inference/det/"  --rec_model_dir="./inference/rec/" --use_gpu=False

更多的文本检测、识别串联推理使用方式请参考文档教程中基于预测引擎推理

文档教程

文本检测算法

PaddleOCR开源的文本检测算法列表

在ICDAR2015文本检测公开数据集上算法效果如下

模型 骨干网络 Hmean 下载链接
EAST ResNet50_vd 85.85% 下载链接
EAST MobileNetV3 79.08% 下载链接
DB ResNet50_vd 83.30% 下载链接
DB MobileNetV3 73.00% 下载链接

PaddleOCR文本检测算法的训练和使用请参考文档教程中文本检测模型训练/评估/预测

文本识别算法

PaddleOCR开源的文本识别算法列表

参考DTRB文字识别训练和评估流程使用MJSynth和SynthText两个文字识别数据集训练在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估算法效果如下

模型 骨干网络 Avg Accuracy 模型存储命名 下载链接
Rosetta Resnet34_vd 80.24% rec_r34_vd_none_none_ctc 下载链接
Rosetta MobileNetV3 78.16% rec_mv3_none_none_ctc 下载链接
CRNN Resnet34_vd 82.20% rec_r34_vd_none_bilstm_ctc 下载链接
CRNN MobileNetV3 79.37% rec_mv3_none_bilstm_ctc 下载链接
STAR-Net Resnet34_vd 83.93% rec_r34_vd_tps_bilstm_ctc 下载链接
STAR-Net MobileNetV3 81.56% rec_mv3_tps_bilstm_ctc 下载链接
RARE Resnet34_vd 84.90% rec_r34_vd_tps_bilstm_attn 下载链接
RARE MobileNetV3 83.32% rec_mv3_tps_bilstm_attn 下载链接

PaddleOCR文本识别算法的训练和使用请参考文档教程中文本识别模型训练/评估/预测

端到端OCR算法

效果展示

参考文献

1. EAST:
@inproceedings{zhou2017east,
  title={EAST: an efficient and accurate scene text detector},
  author={Zhou, Xinyu and Yao, Cong and Wen, He and Wang, Yuzhi and Zhou, Shuchang and He, Weiran and Liang, Jiajun},
  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
  pages={5551--5560},
  year={2017}
}

2. DB:
@article{liao2019real,
  title={Real-time Scene Text Detection with Differentiable Binarization},
  author={Liao, Minghui and Wan, Zhaoyi and Yao, Cong and Chen, Kai and Bai, Xiang},
  journal={arXiv preprint arXiv:1911.08947},
  year={2019}
}

3. DTRB:
@inproceedings{baek2019wrong,
  title={What is wrong with scene text recognition model comparisons? dataset and model analysis},
  author={Baek, Jeonghun and Kim, Geewook and Lee, Junyeop and Park, Sungrae and Han, Dongyoon and Yun, Sangdoo and Oh, Seong Joon and Lee, Hwalsuk},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={4715--4723},
  year={2019}
}

4. SAST:
@inproceedings{wang2019single,
  title={A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning},
  author={Wang, Pengfei and Zhang, Chengquan and Qi, Fei and Huang, Zuming and En, Mengyi and Han, Junyu and Liu, Jingtuo and Ding, Errui and Shi, Guangming},
  booktitle={Proceedings of the 27th ACM International Conference on Multimedia},
  pages={1277--1285},
  year={2019}
}

5. SRN:
@article{yu2020towards,
  title={Towards Accurate Scene Text Recognition with Semantic Reasoning Networks},
  author={Yu, Deli and Li, Xuan and Zhang, Chengquan and Han, Junyu and Liu, Jingtuo and Ding, Errui},
  journal={arXiv preprint arXiv:2003.12294},
  year={2020}
}

6. end2end-psl:
@inproceedings{sun2019chinese,
  title={Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning},
  author={Sun, Yipeng and Liu, Jiaming and Liu, Wei and Han, Junyu and Ding, Errui and Liu, Jingtuo},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={9086--9095},
  year={2019}
}

许可证书

本项目的发布受Apache 2.0 license许可认证。

版本更新

如何贡献代码

我们非常欢迎你为PaddleOCR贡献代码也十分感谢你的反馈。