chore: import upstream snapshot with attribution

2026-07-13 11:59:26 +08:00
commit e904b667c6
2490 changed files with 596352 additions and 0 deletions
@@ -0,0 +1,74 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# CT
+
+## 1. Introduction
+
+Paper:
+> [CentripetalText: An Efficient Text Instance Representation for Scene Text Detection](https://arxiv.org/abs/2107.05945)
+> Tao Sheng, Jie Chen, Zhouhui Lian
+> NeurIPS, 2021
+
+On the Total-Text dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+|CT|ResNet18_vd|[configs/det/det_r18_vd_ct.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r18_vd_ct.yml)|88.68%|81.70%|85.05%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r18_ct_train.tar)|
+
+## 2. Environment
+
+Please prepare your environment referring to [prepare the environment](../../ppocr/environment.en.md) and [clone the repo](../../ppocr/blog/clone.en.md).
+
+## 3. Model Training / Evaluation / Prediction
+
+The above CT model is trained using the Total-Text text detection public dataset. For the download of the dataset, please refer to [Total-Text-Dataset](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Dataset). PaddleOCR format annotation download link [train.txt](https://paddleocr.bj.bcebos.com/dataset/ct_tipc/train.txt), [test.txt](https://paddleocr.bj.bcebos.com/dataset/ct_tipc/test.txt).
+
+Please refer to [text detection training tutorial](../../ppocr/model_train/detection.en.md). PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models.
+
+## 4. Inference and Deployment
+
+### 4.1 Python Inference
+
+First, convert the model saved in the CT text detection training process into an inference model. Taking the model based on the Resnet18_vd backbone network and trained on the Total Text English dataset as example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r18_ct_train.tar)), you can use the following command to convert:
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r18_vd_ct.yml -o Global.pretrained_model=./det_r18_ct_train/best_accuracy  Global.save_inference_dir=./inference/det_ct
+```
+
+CT text detection model inference, you can execute the following command:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_ct/" --det_algorithm="CT"
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with `det_res`. Examples of results are as follows:
+
+![img](./images/det_res_img623_ct.jpg)
+
+### 4.2 C++ Inference
+
+Not supported
+
+### 4.3 Serving
+
+Not supported
+
+### 4.4 More
+
+Not supported
+
+## 5. FAQ
+
+## Citation
+
+```bibtex
+@inproceedings{sheng2021centripetaltext,
+    title={CentripetalText: An Efficient Text Instance Representation for Scene Text Detection},
+    author={Tao Sheng and Jie Chen and Zhouhui Lian},
+    booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},
+    year={2021}
+}
+```
@@ -0,0 +1,74 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# CT
+
+## 1. 算法简介
+
+论文信息：
+> [CentripetalText: An Efficient Text Instance Representation for Scene Text Detection](https://arxiv.org/abs/2107.05945)
+> Tao Sheng, Jie Chen, Zhouhui Lian
+> NeurIPS, 2021
+
+在Total-Text文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|CT|ResNet18_vd|[configs/det/det_r18_vd_ct.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r18_vd_ct.yml)|88.68%|81.70%|85.05%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r18_ct_train.tar)|
+
+## 2. 环境配置
+
+请先参考[《运行环境准备》](../../ppocr/environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](../../ppocr/blog/clone.md)克隆项目代码。
+
+## 3. 模型训练、评估、预测
+
+CT模型使用Total-Text文本检测公开数据集训练得到，数据集下载可参考 [Total-Text-Dataset](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Dataset), 我们将标签文件转成了paddleocr格式，转换好的标签文件下载参考[train.txt](https://paddleocr.bj.bcebos.com/dataset/ct_tipc/train.txt), [text.txt](https://paddleocr.bj.bcebos.com/dataset/ct_tipc/test.txt)。
+
+请参考[文本检测训练教程](../../ppocr/model_train/detection.md)。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+## 4. 推理部署
+
+### 4.1 Python推理
+
+首先将CT文本检测训练过程中保存的模型，转换成inference model。以基于Resnet18_vd骨干网络，在Total-Text英文数据集训练的模型为例（ [模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r18_ct_train.tar) )，可以使用如下命令进行转换：
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r18_vd_ct.yml -o Global.pretrained_model=./det_r18_ct_train/best_accuracy  Global.save_inference_dir=./inference/det_ct
+```
+
+CT文本检测模型推理，可以执行如下命令：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_ct/" --det_algorithm="CT"
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为`det_res`。结果示例如下：
+
+![img](./images/det_res_img623_ct.jpg)
+
+### 4.2 C++推理
+
+暂不支持
+
+### 4.3 Serving服务化部署
+
+暂不支持
+
+### 4.4 更多推理部署
+
+暂不支持
+
+## 5. FAQ
+
+## 引用
+
+```bibtex
+@inproceedings{sheng2021centripetaltext,
+    title={CentripetalText: An Efficient Text Instance Representation for Scene Text Detection},
+    author={Tao Sheng and Jie Chen and Zhouhui Lian},
+    booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},
+    year={2021}
+}
+```
@@ -0,0 +1,98 @@
+---
+comments: true
+---
+
+# DB && DB++
+
+## 1. Introduction
+
+Paper:
+> [Real-time Scene Text Detection with Differentiable Binarization](https://arxiv.org/abs/1911.08947)
+> Liao, Minghui and Wan, Zhaoyi and Yao, Cong and Chen, Kai and Bai, Xiang
+> AAAI, 2020
+
+> [Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion](https://arxiv.org/abs/2202.10304)
+> Liao, Minghui and Zou, Zhisheng and Wan, Zhaoyi and Yao, Cong and Bai, Xiang
+> TPAMI, 2022
+
+On the ICDAR2015 dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+|DB|ResNet50_vd|[configs/det/det_r50_vd_db.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_db.yml)|86.41%|78.72%|82.38%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)|
+|DB|MobileNetV3|[configs/det/det_mv3_db.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_mv3_db.yml)|77.29%|73.08%|75.12%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)|
+|DB++|ResNet50|[configs/det/det_r50_db++_icdar15.yml](https://github.com/PaddlePaddle/PaddleOCR/blob/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_db++_icdar15.yml)|90.89%|82.66%|86.58%|[pretrained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/ResNet50_dcn_asf_synthtext_pretrained.pdparams)/[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_db%2B%2B_icdar15_train.tar)|
+
+On the TD_TR dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+|DB++|ResNet50|[configs/det/det_r50_db++_td_tr.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_db++_td_tr.yml)|92.92%|86.48%|89.58%|[pretrained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/ResNet50_dcn_asf_synthtext_pretrained.pdparams)/[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_db%2B%2B_td_tr_train.tar)|
+
+## 2. Environment
+
+Please prepare your environment referring to [prepare the environment](../../ppocr/environment.en.md) and [clone the repo](../../ppocr/blog/clone.en.md).
+
+## 3. Model Training / Evaluation / Prediction
+
+Please refer to [text detection training tutorial](../../ppocr/model_train/detection.en.md). PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models.
+
+## 4. Inference and Deployment
+
+### 4.1 Python Inference
+
+First, convert the model saved in the DB text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)), you can use the following command to convert:
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_db.yml -o Global.pretrained_model=./det_r50_vd_db_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_db
+```
+
+DB text detection model inference, you can execute the following command:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_db/"
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with `det_res`. Examples of results are as follows:
+
+![img](./images/det_res_img_10_db.jpg)
+
+**Note**: Since the ICDAR2015 dataset has only 1,000 training images, mainly for English scenes, the above model has very poor detection result on Chinese text images.
+
+### 4.2 C++ Inference
+
+With the inference model prepared, refer to the [cpp infer](../../../version2.x/legacy/cpp_infer.en.md) tutorial for C++ inference.
+
+### 4.3 Serving
+
+With the inference model prepared, refer to the [pdserving](../../../version2.x/legacy/paddle_server.en.md) tutorial for service deployment by Paddle Serving.
+
+### 4.4 More
+
+More deployment schemes supported for DB:
+
+- Paddle2ONNX: with the inference model prepared, please refer to the [paddle2onnx](../../../version2.x/legacy/paddle2onnx.en.md) tutorial.
+
+## 5. FAQ
+
+## Citation
+
+```bibtex
+@inproceedings{liao2020real,
+  title={Real-time scene text detection with differentiable binarization},
+  author={Liao, Minghui and Wan, Zhaoyi and Yao, Cong and Chen, Kai and Bai, Xiang},
+  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
+  volume={34},
+  number={07},
+  pages={11474--11481},
+  year={2020}
+}
+
+@article{liao2022real,
+  title={Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion},
+  author={Liao, Minghui and Zou, Zhisheng and Wan, Zhaoyi and Yao, Cong and Bai, Xiang},
+  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+  year={2022},
+  publisher={IEEE}
+}
+```
@@ -0,0 +1,99 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# DB与DB++
+
+## 1. 算法简介
+
+论文信息：
+> [Real-time Scene Text Detection with Differentiable Binarization](https://arxiv.org/abs/1911.08947)
+> Liao, Minghui and Wan, Zhaoyi and Yao, Cong and Chen, Kai and Bai, Xiang
+> AAAI, 2020
+
+> [Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion](https://arxiv.org/abs/2202.10304)
+> Liao, Minghui and Zou, Zhisheng and Wan, Zhaoyi and Yao, Cong and Bai, Xiang
+> TPAMI, 2022
+
+在ICDAR2015文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|DB|ResNet50_vd|[configs/det/det_r50_vd_db.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_db.yml)|86.41%|78.72%|82.38%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)|
+|DB|MobileNetV3|[configs/det/det_mv3_db.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_mv3_db.yml)|77.29%|73.08%|75.12%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)|
+|DB++|ResNet50|[configs/det/det_r50_db++_icdar15.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_db++_icdar15.yml)|90.89%|82.66%|86.58%|[合成数据预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/ResNet50_dcn_asf_synthtext_pretrained.pdparams)/[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_db%2B%2B_icdar15_train.tar)|
+
+在TD_TR文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|DB++|ResNet50|[configs/det/det_r50_db++_td_tr.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_db++_td_tr.yml)|92.92%|86.48%|89.58%|[合成数据预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/ResNet50_dcn_asf_synthtext_pretrained.pdparams)/[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_db%2B%2B_td_tr_train.tar)|
+
+## 2. 环境配置
+
+请先参考[《运行环境准备》](../../ppocr/environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](../../ppocr/blog/clone.md)克隆项目代码。
+
+## 3. 模型训练、评估、预测
+
+请参考[文本检测训练教程](../../ppocr/model_train/detection.md)。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+## 4. 推理部署
+
+### 4.1 Python推理
+
+首先将DB文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例（ [模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar) )，可以使用如下命令进行转换：
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_db.yml -o Global.pretrained_model=./det_r50_vd_db_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_db
+```
+
+DB文本检测模型推理，可以执行如下命令：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_db/" --det_algorithm="DB"
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为`det_res`。结果示例如下：
+
+![img](./images/det_res_img_10_db.jpg)
+
+**注意**：由于ICDAR2015数据集只有1000张训练图像，且主要针对英文场景，所以上述模型对中文文本图像检测效果会比较差。
+
+### 4.2 C++推理
+
+准备好推理模型后，参考[cpp infer](../../../version2.x/legacy/cpp_infer.md)教程进行操作即可。
+
+### 4.3 Serving服务化部署
+
+准备好推理模型后，参考[pdserving](../../../version2.x/legacy/paddle_server.md)教程进行Serving服务化部署，包括Python Serving和C++ Serving两种模式。
+
+### 4.4 更多推理部署
+
+DB模型还支持以下推理部署方式：
+
+- Paddle2ONNX推理：准备好推理模型后，参考[paddle2onnx](../../../version2.x/legacy/paddle2onnx.md)教程操作。
+
+## 5. FAQ
+
+## 引用
+
+```bibtex
+@inproceedings{liao2020real,
+  title={Real-time scene text detection with differentiable binarization},
+  author={Liao, Minghui and Wan, Zhaoyi and Yao, Cong and Chen, Kai and Bai, Xiang},
+  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
+  volume={34},
+  number={07},
+  pages={11474--11481},
+  year={2020}
+}
+
+@article{liao2022real,
+  title={Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion},
+  author={Liao, Minghui and Zou, Zhisheng and Wan, Zhaoyi and Yao, Cong and Bai, Xiang},
+  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+  year={2022},
+  publisher={IEEE}
+}
+```
@@ -0,0 +1,61 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# DRRG
+
+## 1. Introduction
+
+Paper:
+> [Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection](https://arxiv.org/abs/2003.07493)
+> Zhang, Shi-Xue and Zhu, Xiaobin and Hou, Jie-Bo and Liu, Chang and Yang, Chun and Wang, Hongfa and Yin, Xu-Cheng
+> CVPR, 2020
+
+On the CTW1500 dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+| DRRG | ResNet50_vd | [configs/det/det_r50_drrg_ctw.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_drrg_ctw.yml)| 89.92%|80.91%|85.18%|[trained model](https://paddleocr.bj.bcebos.com/contribution/det_r50_drrg_ctw_train.tar)|
+
+## 2. Environment
+
+Please prepare your environment referring to [prepare the environment](../../ppocr/environment.en.md) and [clone the repo](../../ppocr/blog/clone.en.md).
+
+## 3. Model Training / Evaluation / Prediction
+
+The above DRRG model is trained using the CTW1500 text detection public dataset. For the download of the dataset, please refer to [ocr_datasets](../../../datasets/ocr_datasets.en.md).
+
+After the data download is complete, please refer to [Text Detection Training Tutorial](../../ppocr/model_train/detection.en.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models.
+
+## 4. Inference and Deployment
+
+### 4.1 Python Inference
+
+Since the model needs to be converted to Numpy data for many times in the forward, DRRG dynamic graph to static graph is not supported.
+
+### 4.2 C++ Inference
+
+Not supported
+
+### 4.3 Serving
+
+Not supported
+
+### 4.4 More
+
+Not supported
+
+## 5. FAQ
+
+## Citation
+
+```bibtex
+@inproceedings{zhang2020deep,
+  title={Deep relational reasoning graph network for arbitrary shape text detection},
+  author={Zhang, Shi-Xue and Zhu, Xiaobin and Hou, Jie-Bo and Liu, Chang and Yang, Chun and Wang, Hongfa and Yin, Xu-Cheng},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={9699--9708},
+  year={2020}
+}
+```
@@ -0,0 +1,61 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# DRRG
+
+## 1. 算法简介
+
+论文信息：
+> [Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection](https://arxiv.org/abs/2003.07493)
+> Zhang, Shi-Xue and Zhu, Xiaobin and Hou, Jie-Bo and Liu, Chang and Yang, Chun and Wang, Hongfa and Yin, Xu-Cheng
+> CVPR, 2020
+
+在CTW1500文本检测公开数据集上，算法复现效果如下：
+
+| 模型  |骨干网络|配置文件|precision|recall|Hmean|下载链接|
+|-----| --- | --- | --- | --- | --- | --- |
+| DRRG | ResNet50_vd | [configs/det/det_r50_drrg_ctw.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_drrg_ctw.yml)| 89.92%|80.91%|85.18%|[训练模型](https://paddleocr.bj.bcebos.com/contribution/det_r50_drrg_ctw_train.tar)|
+
+## 2. 环境配置
+
+请先参考[《运行环境准备》](../../ppocr/environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](../../ppocr/blog/clone.md)克隆项目代码。
+
+## 3. 模型训练、评估、预测
+
+上述DRRG模型使用CTW1500文本检测公开数据集训练得到，数据集下载可参考 [ocr_datasets](../../../datasets/ocr_datasets.md)。
+
+数据下载完成后，请参考[文本检测训练教程](../../ppocr/model_train/detection.md)进行训练。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+## 4. 推理部署
+
+### 4.1 Python推理
+
+由于模型前向运行时需要多次转换为Numpy数据进行运算，因此DRRG的动态图转静态图暂未支持。
+
+### 4.2 C++推理
+
+暂未支持
+
+### 4.3 Serving服务化部署
+
+暂未支持
+
+### 4.4 更多推理部署
+
+暂未支持
+
+## 5. FAQ
+
+## 引用
+
+```bibtex
+@inproceedings{zhang2020deep,
+  title={Deep relational reasoning graph network for arbitrary shape text detection},
+  author={Zhang, Shi-Xue and Zhu, Xiaobin and Hou, Jie-Bo and Liu, Chang and Yang, Chun and Wang, Hongfa and Yin, Xu-Cheng},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={9699--9708},
+  year={2020}
+}
+```
@@ -0,0 +1,76 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# EAST
+
+## 1. Introduction
+
+Paper:
+> [EAST: An Efficient and Accurate Scene Text Detector](https://arxiv.org/abs/1704.03155)
+> Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, Jiajun Liang
+> CVPR, 2017
+
+On the ICDAR2015 dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+|EAST|ResNet50_vd| [det_r50_vd_east.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_east.yml)|88.71%|    81.36%|    84.88%|    [model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)|
+|EAST|MobileNetV3|[det_mv3_east.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_mv3_east.yml) | 78.20%|    79.10%|    78.65%|    [model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)|
+
+## 2. Environment
+
+Please prepare your environment referring to [prepare the environment](../../ppocr/environment.en.md) and [clone the repo](../../ppocr/blog/clone.en.md).
+
+## 3. Model Training / Evaluation / Prediction
+
+The above EAST model is trained using the ICDAR2015 text detection public dataset. For the download of the dataset, please refer to [ocr_datasets](../../../datasets/ocr_datasets.en.md).
+
+After the data download is complete, please refer to [Text Detection Training Tutorial](../../ppocr/model_train/detection.en.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models.
+
+## 4. Inference and Deployment
+
+### 4.1 Python Inference
+
+First, convert the model saved in the EAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)), you can use the following command to convert:
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_east.yml -o Global.pretrained_model=./det_r50_vd_east_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_r50_east/
+```
+
+For EAST text detection model inference, you need to set the parameter --det_algorithm="EAST", run the following command:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_r50_east/" --det_algorithm="EAST"
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with `det_res`.
+
+![img](./images/det_res_img_10_east.jpg)
+
+### 4.2 C++ Inference
+
+Since the post-processing is not written in CPP, the EAST text detection model does not support CPP inference.
+
+### 4.3 Serving
+
+Not supported
+
+### 4.4 More
+
+Not supported
+
+## 5. FAQ
+
+## Citation
+
+```bibtex
+@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}
+}
+```
@@ -0,0 +1,76 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# EAST
+
+## 1. 算法简介
+
+论文信息：
+> [EAST: An Efficient and Accurate Scene Text Detector](https://arxiv.org/abs/1704.03155)
+> Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, Jiajun Liang
+> CVPR, 2017
+
+在ICDAR2015文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|EAST|ResNet50_vd| [det_r50_vd_east.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_east.yml)|88.71%|    81.36%|    84.88%|    [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)|
+|EAST|MobileNetV3|[det_mv3_east.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_mv3_east.yml) | 78.20%|    79.10%|    78.65%|    [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)|
+
+## 2. 环境配置
+
+请先参考[《运行环境准备》](../../ppocr/environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](../../ppocr/blog/clone.md)克隆项目代码。
+
+## 3. 模型训练、评估、预测
+
+上表中的EAST训练模型使用ICDAR2015文本检测公开数据集训练得到，数据集下载可参考 [ocr_datasets](../../../datasets/ocr_datasets.md)。
+
+数据下载完成后，请参考[文本检测训练教程](../../ppocr/model_train/detection.md)进行训练。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+## 4. 推理部署
+
+### 4.1 Python推理
+
+首先将EAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例（[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar))，可以使用如下命令进行转换：
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_east.yml -o Global.pretrained_model=./det_r50_vd_east_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_r50_east/
+```
+
+EAST文本检测模型推理，需要设置参数--det_algorithm="EAST"，执行预测：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_r50_east/" --det_algorithm="EAST"
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为`det_res`。
+
+![img](./images/det_res_img_10_east.jpg)
+
+### 4.2 C++推理
+
+由于后处理暂未使用CPP编写，EAST文本检测模型暂不支持CPP推理。
+
+### 4.3 Serving服务化部署
+
+暂未支持
+
+### 4.4 更多推理部署
+
+暂未支持
+
+## 5. FAQ
+
+## 引用
+
+```bibtex
+@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}
+}
+```
@@ -0,0 +1,86 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# FCENet
+
+## 1. Introduction
+
+Paper:
+> [Fourier Contour Embedding for Arbitrary-Shaped Text Detection](https://arxiv.org/abs/2104.10442)
+> Yiqin Zhu and Jianyong Chen and Lingyu Liang and Zhanghui Kuang and Lianwen Jin and Wayne Zhang
+> CVPR, 2021
+
+On the CTW1500 dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+| FCE | ResNet50_dcn | [configs/det/det_r50_vd_dcn_fce_ctw.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_dcn_fce_ctw.yml)| 88.39%|82.18%|85.27%|[trained model](https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar)|
+
+## 2. Environment
+
+Please prepare your environment referring to [prepare the environment](../../ppocr/environment.en.md) and [clone the repo](../../ppocr/blog/clone.en.md).
+
+## 3. Model Training / Evaluation / Prediction
+
+The above FCE model is trained using the CTW1500 text detection public dataset. For the download of the dataset, please refer to [ocr_datasets](../../../datasets/ocr_datasets.en.md).
+
+After the data download is complete, please refer to [Text Detection Training Tutorial](../../ppocr/model_train/detection.en.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models.
+
+## 4. Inference and Deployment
+
+### 4.1 Python Inference
+
+First, convert the model saved in the FCE text detection training process into an inference model. Taking the model based on the Resnet50_vd_dcn backbone network and trained on the CTW1500 English dataset as example ([model download link](https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar)), you can use the following command to convert:
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_dcn_fce_ctw.yml -o Global.pretrained_model=./det_r50_dcn_fce_ctw_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_fce
+```
+
+FCE text detection model inference, to perform non-curved text detection, you can run the following commands:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_fce/" --det_algorithm="FCE" --det_fce_box_type=quad
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
+
+![img](./images/det_res_img_10_fce.jpg)
+
+If you want to perform curved text detection, you can execute the following command:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_fce/" --det_algorithm="FCE" --det_fce_box_type=poly
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
+
+![img](./images/det_res_img623_fce.jpg)
+
+**Note**: Since the CTW1500 dataset has only 1,000 training images, mainly for English scenes, the above model has very poor detection result on Chinese or curved text images.
+
+### 4.2 C++ Inference
+
+Since the post-processing is not written in CPP, the FCE text detection model does not support CPP inference.
+
+### 4.3 Serving
+
+Not supported
+
+### 4.4 More
+
+Not supported
+
+## 5. FAQ
+
+## Citation
+
+```bibtex
+@InProceedings{zhu2021fourier,
+  title={Fourier Contour Embedding for Arbitrary-Shaped Text Detection},
+  author={Yiqin Zhu and Jianyong Chen and Lingyu Liang and Zhanghui Kuang and Lianwen Jin and Wayne Zhang},
+  year={2021},
+  booktitle = {CVPR}
+}
+```
@@ -0,0 +1,86 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# FCENet
+
+## 1. 算法简介
+
+论文信息：
+> [Fourier Contour Embedding for Arbitrary-Shaped Text Detection](https://arxiv.org/abs/2104.10442)
+> Yiqin Zhu and Jianyong Chen and Lingyu Liang and Zhanghui Kuang and Lianwen Jin and Wayne Zhang
+> CVPR, 2021
+
+在CTW1500文本检测公开数据集上，算法复现效果如下：
+
+| 模型  |骨干网络|配置文件|precision|recall|Hmean|下载链接|
+|-----| --- | --- | --- | --- | --- | --- |
+| FCE | ResNet50_dcn | [configs/det/det_r50_vd_dcn_fce_ctw.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_dcn_fce_ctw.yml)| 88.39%|82.18%|85.27%|[训练模型](https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar)|
+
+## 2. 环境配置
+
+请先参考[《运行环境准备》](../../ppocr/environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](../../ppocr/blog/clone.md)克隆项目代码。
+
+## 3. 模型训练、评估、预测
+
+上述FCE模型使用CTW1500文本检测公开数据集训练得到，数据集下载可参考 [ocr_datasets](../../../datasets/ocr_datasets.md)。
+
+数据下载完成后，请参考[文本检测训练教程](../../ppocr/model_train/detection.md)进行训练。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+## 4. 推理部署
+
+### 4.1 Python推理
+
+首先将FCE文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd_dcn骨干网络，在CTW1500英文数据集训练的模型为例（ [模型下载地址](https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar) )，可以使用如下命令进行转换：
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_dcn_fce_ctw.yml -o Global.pretrained_model=./det_r50_dcn_fce_ctw_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_fce
+```
+
+FCE文本检测模型推理，执行非弯曲文本检测，可以执行如下命令：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_fce/" --det_algorithm="FCE" --det_fce_box_type=quad
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
+
+![img](./images/det_res_img_10_fce.jpg)
+
+如果想执行弯曲文本检测，可以执行如下命令：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_fce/" --det_algorithm="FCE" --det_fce_box_type=poly
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
+
+![img](./images/det_res_img623_fce.jpg)
+
+**注意**：由于CTW1500数据集只有1000张训练图像，且主要针对英文场景，所以上述模型对中文文本图像检测效果会比较差。
+
+### 4.2 C++推理
+
+由于后处理暂未使用CPP编写，FCE文本检测模型暂不支持CPP推理。
+
+### 4.3 Serving服务化部署
+
+暂未支持
+
+### 4.4 更多推理部署
+
+暂未支持
+
+## 5. FAQ
+
+## 引用
+
+```bibtex
+@InProceedings{zhu2021fourier,
+  title={Fourier Contour Embedding for Arbitrary-Shaped Text Detection},
+  author={Yiqin Zhu and Jianyong Chen and Lingyu Liang and Zhanghui Kuang and Lianwen Jin and Wayne Zhang},
+  year={2021},
+  booktitle = {CVPR}
+}
+```
@@ -0,0 +1,89 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+
+# PSENet
+
+## 1. Introduction
+
+Paper:
+> [Shape robust text detection with progressive scale expansion network](https://arxiv.org/abs/1903.12473)
+> Wang, Wenhai and Xie, Enze and Li, Xiang and Hou, Wenbo and Lu, Tong and Yu, Gang and Shao, Shuai
+> CVPR, 2019
+
+On the ICDAR2015 dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+|PSE| ResNet50_vd | [configs/det/det_r50_vd_pse.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_pse.yml)| 85.81%    |79.53%|82.55%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)|
+|PSE| MobileNetV3| [configs/det/det_mv3_pse.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_mv3_pse.yml) | 82.20%    |70.48%|75.89%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)|
+
+## 2. Environment
+
+Please prepare your environment referring to [prepare the environment](../../ppocr/environment.en.md) and [clone the repo](../../ppocr/blog/clone.en.md).
+
+## 3. Model Training / Evaluation / Prediction
+
+The above PSE model is trained using the ICDAR2015 text detection public dataset. For the download of the dataset, please refer to [ocr_datasets](../../../datasets/ocr_datasets.en.md).
+
+After the data download is complete, please refer to [Text Detection Training Tutorial](../../ppocr/model_train/detection.en.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models.
+
+## 4. Inference and Deployment
+
+### 4.1 Python Inference
+
+First, convert the model saved in the PSE text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)), you can use the following command to convert:
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_pse.yml -o Global.pretrained_model=./det_r50_vd_pse_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_pse
+```
+
+PSE text detection model inference, to perform non-curved text detection, you can run the following commands:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_pse/" --det_algorithm="PSE" --det_pse_box_type=quad
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
+
+![img](./images/det_res_img_10_pse.jpg)
+
+If you want to perform curved text detection, you can execute the following command:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_pse/" --det_algorithm="PSE" --det_pse_box_type=poly
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
+
+![](./images/det_res_img_10_pse_poly.jpg)
+
+**Note**: Since the ICDAR2015 dataset has only 1,000 training images, mainly for English scenes, the above model has very poor detection result on Chinese or curved text images.
+
+### 4.2 C++ Inference
+
+Since the post-processing is not written in CPP, the PSE text detection model does not support CPP inference.
+
+### 4.3 Serving
+
+Not supported
+
+### 4.4 More
+
+Not supported
+
+## 5. FAQ
+
+## Citation
+
+```bibtex
+@inproceedings{wang2019shape,
+  title={Shape robust text detection with progressive scale expansion network},
+  author={Wang, Wenhai and Xie, Enze and Li, Xiang and Hou, Wenbo and Lu, Tong and Yu, Gang and Shao, Shuai},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={9336--9345},
+  year={2019}
+}
+```
@@ -0,0 +1,88 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# PSENet
+
+## 1. 算法简介
+
+论文信息：
+> [Shape robust text detection with progressive scale expansion network](https://arxiv.org/abs/1903.12473)
+> Wang, Wenhai and Xie, Enze and Li, Xiang and Hou, Wenbo and Lu, Tong and Yu, Gang and Shao, Shuai
+> CVPR, 2019
+
+在ICDAR2015文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|PSE| ResNet50_vd | [configs/det/det_r50_vd_pse.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_pse.yml)| 85.81%    |79.53%|82.55%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)|
+|PSE| MobileNetV3| [configs/det/det_mv3_pse.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_mv3_pse.yml) | 82.20%    |70.48%|75.89%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)|
+
+## 2. 环境配置
+
+请先参考[《运行环境准备》](../../ppocr/environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](../../ppocr/blog/clone.md)克隆项目代码。
+
+## 3. 模型训练、评估、预测
+
+上述PSE模型使用ICDAR2015文本检测公开数据集训练得到，数据集下载可参考 [ocr_datasets](../../../datasets/ocr_datasets.md)。
+
+数据下载完成后，请参考[文本检测训练教程](../../ppocr/model_train/detection.md)进行训练。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+## 4. 推理部署
+
+### 4.1 Python推理
+
+首先将PSE文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例（ [模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar) )，可以使用如下命令进行转换：
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_pse.yml -o Global.pretrained_model=./det_r50_vd_pse_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_pse
+```
+
+PSE文本检测模型推理，执行非弯曲文本检测，可以执行如下命令：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_pse/" --det_algorithm="PSE" --det_pse_box_type=quad
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
+
+![img](./images/det_res_img_10_pse.jpg)
+
+如果想执行弯曲文本检测，可以执行如下命令：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_pse/" --det_algorithm="PSE" --det_pse_box_type=poly
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
+
+![img](./images/det_res_img_10_pse_poly.jpg)
+
+**注意**：由于ICDAR2015数据集只有1000张训练图像，且主要针对英文场景，所以上述模型对中文或弯曲文本图像检测效果会比较差。
+
+### 4.2 C++推理
+
+由于后处理暂未使用CPP编写，PSE文本检测模型暂不支持CPP推理。
+
+### 4.3 Serving服务化部署
+
+暂未支持
+
+### 4.4 更多推理部署
+
+暂未支持
+
+## 5. FAQ
+
+## 引用
+
+```bibtex
+@inproceedings{wang2019shape,
+  title={Shape robust text detection with progressive scale expansion network},
+  author={Wang, Wenhai and Xie, Enze and Li, Xiang and Hou, Wenbo and Lu, Tong and Yu, Gang and Shao, Shuai},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={9336--9345},
+  year={2019}
+}
+```
@@ -0,0 +1,101 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# SAST
+
+## 1. Introduction
+
+Paper:
+> [A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning](https://arxiv.org/abs/1908.05498)
+> 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
+> ACM MM, 2019
+
+On the ICDAR2015 dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+|SAST|ResNet50_vd|[configs/det/det_r50_vd_sast_icdar15.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_sast_icdar15.yml)|91.39%|83.77%|87.42%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
+
+On the Total-text dataset, the text detection result is as follows:
+
+|Model|Backbone|Configuration|Precision|Recall|Hmean|Download|
+| --- | --- | --- | --- | --- | --- | --- |
+|SAST|ResNet50_vd|[configs/det/det_r50_vd_sast_totaltext.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_sast_totaltext.yml)|89.63%|78.44%|83.66%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
+
+## 2. Environment
+
+Please prepare your environment referring to [prepare the environment](../../ppocr/environment.en.md) and [clone the repo](../../ppocr/blog/clone.en.md).
+
+## 3. Model Training / Evaluation / Prediction
+
+Please refer to [text detection training tutorial](../../ppocr/model_train/detection.en.md). PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models.
+
+## 4. Inference and Deployment
+
+### 4.1 Python Inference
+
+#### (1). Quadrangle text detection model (ICDAR2015)
+
+First, convert the model saved in the SAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as an example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)), you can use the following command to convert:
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_sast_icdar15.yml -o Global.pretrained_model=./det_r50_vd_sast_icdar15_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_ic15
+```
+
+**For SAST quadrangle text detection model inference, you need to set the parameter `--det_algorithm="SAST"`**, run the following command:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_sast_ic15/"
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
+
+![img](./images/det_res_img_10_sast.jpg)
+
+#### (2). Curved text detection model (Total-Text)
+
+First, convert the model saved in the SAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the Total-Text English dataset as an example ([model download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)), you can use the following command to convert:
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.pretrained_model=./det_r50_vd_sast_totaltext_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_tt
+```
+
+For SAST curved text detection model inference, you need to set the parameter `--det_algorithm="SAST"` and `--det_box_type=poly`, run the following command:
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_sast_tt/" --det_box_type='poly'
+```
+
+The visualized text detection results are saved to the `./inference_results` folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
+
+![img](./images/det_res_img623_sast.jpg)
+
+**Note**: SAST post-processing locality aware NMS has two versions: Python and C++. The speed of C++ version is obviously faster than that of Python version. Due to the compilation version problem of NMS of C++ version, C++ version NMS will be called only in Python 3.5 environment, and python version NMS will be called in other cases.
+
+### 4.2 C++ Inference
+
+Not supported
+
+### 4.3 Serving
+
+Not supported
+
+### 4.4 More
+
+Not supported
+
+## 5. FAQ
+
+## Citation
+
+```bibtex
+@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}
+}
+```
@@ -0,0 +1,101 @@
+---
+typora-copy-images-to: images
+comments: true
+---
+
+# SAST
+
+## 1. 算法简介
+
+论文信息：
+> [A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning](https://arxiv.org/abs/1908.05498)
+> 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
+> ACM MM, 2019
+
+在ICDAR2015文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|SAST|ResNet50_vd|[configs/det/det_r50_vd_sast_icdar15.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_sast_icdar15.yml)|91.39%|83.77%|87.42%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
+
+在Total-text文本检测公开数据集上，算法复现效果如下：
+
+|模型|骨干网络|配置文件|precision|recall|Hmean|下载链接|
+| --- | --- | --- | --- | --- | --- | --- |
+|SAST|ResNet50_vd|[configs/det/det_r50_vd_sast_totaltext.yml](https://github.com/PaddlePaddle/PaddleOCR/tree/{{PADDLEOCR_GITHUB_REF}}/configs/det/det_r50_vd_sast_totaltext.yml)|89.63%|78.44%|83.66%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
+
+## 2. 环境配置
+
+请先参考[《运行环境准备》](../../ppocr/environment.md)配置PaddleOCR运行环境，参考[《项目克隆》](../../ppocr/blog/clone.md)克隆项目代码。
+
+## 3. 模型训练、评估、预测
+
+请参考[文本检测训练教程](../../ppocr/model_train/detection.md)。PaddleOCR对代码进行了模块化，训练不同的检测模型只需要**更换配置文件**即可。
+
+## 4. 推理部署
+
+### 4.1 Python推理
+
+#### (1). 四边形文本检测模型（ICDAR2015）
+
+首先将SAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例([模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar))，可以使用如下命令进行转换：
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_sast_icdar15.yml -o Global.pretrained_model=./det_r50_vd_sast_icdar15_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_ic15
+```
+
+**SAST文本检测模型推理，需要设置参数`--det_algorithm="SAST"`**，可以执行如下命令：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img_10.jpg" --det_model_dir="./inference/det_sast_ic15/"
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
+
+![img](./images/det_res_img_10_sast.jpg)
+
+#### (2). 弯曲文本检测模型（Total-Text）
+
+首先将SAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在Total-Text英文数据集训练的模型为例（[模型下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar))，可以使用如下命令进行转换：
+
+```bash linenums="1"
+python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.pretrained_model=./det_r50_vd_sast_totaltext_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_tt
+```
+
+SAST文本检测模型推理，需要设置参数`--det_algorithm="SAST"`，同时，还需要增加参数`--det_box_type=poly`，可以执行如下命令：
+
+```bash linenums="1"
+python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_sast_tt/" --det_box_type='poly'
+```
+
+可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下：
+
+![img](./images/det_res_img623_sast.jpg)
+
+**注意**：本代码库中，SAST后处理Locality-Aware NMS有python和c++两种版本，c++版速度明显快于python版。由于c++版本nms编译版本问题，只有python3.5环境下会调用c++版nms，其他情况将调用python版nms。
+
+### 4.2 C++推理
+
+暂未支持
+
+### 4.3 Serving服务化部署
+
+暂未支持
+
+### 4.4 更多推理部署
+
+暂未支持
+
+## 5. FAQ
+
+## 引用
+
+```bibtex
+@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}
+}
+```