Introduction

Official Pytorch implementations of PSENet [1].

[1] W. Wang, E. Xie, X. Li, W. Hou, T. Lu, G. Yu, and S. Shao. Shape robust text detection with progressive scale expansion network. In Proc. IEEE Conf. Comp. Vis. Patt. Recogn., pages 9336–9345, 2019.

Recommended environment

Python 3.6+
Pytorch 1.1.0
torchvision 0.3
mmcv 0.2.12
editdistance
Polygon3
pyclipper
opencv-python 3.4.2.17
Cython

Install

pip install -r requirement.txt
./compile.sh

Training

CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py ${CONFIG_FILE}

For example:

CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py config/psenet/psenet_r50_ic15_736.py

Test

python test.py ${CONFIG_FILE} ${CHECKPOINT_FILE}

For example:

python test.py config/psenet/psenet_r50_ic15_736.py checkpoints/psenet_r50_ic15_736/checkpoint.pth.tar

Speed

python test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --report_speed

For example:

python test.py config/psenet/psenet_r50_ic15_736.py checkpoints/psenet_r50_ic15_736/checkpoint.pth.tar --report_speed

Evaluation

Introduction

The evaluation scripts of ICDAR 2015 (IC15), Total-Text (TT) and CTW1500 (CTW) datasets.

ICDAR 2015

Text detection

./eval_ic15.sh

Total-Text

Text detection

./eval_tt.sh

CTW1500

Text detection

./eval_ctw.sh

Benchmark

Results

ICDAR 2015

Method	Backbone	Short_Size	Config	Precision (%)	Recall (%)	F-measure (%)	Model
PseNet	ResNet50	736	psenet_r50_ic15_736.py	83.6	74.0	78.5	Google Drive
PseNet	ResNet50	1024	psenet_r50_ic15_1024.py	84.4	76.3	80.2	Google Drive
PseNet(paper)	ResNet50	1024	-	81.5	79.7	80.6	-

CTW1500 | Method | Backbone | Config | Precision (%) | Recall (%) | F-measure (%) | Model | | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | | PseNet | ResNet50 | psenet_r50_ctw.py | 82.6 | 76.4 | 79.4 | Google Drive | | PseNet(paper) | ResNet50 | - | 80.6 | 75.6 | 78 | - |

Total-Text | Method | Backbone | Config | Precision (%) | Recall (%) | F-measure (%) | Model | | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | | PseNet | ResNet50 | psenet_r50_tt.py | 87.3 | 77.9 | 82.3 | Google Drive | | PseNet(paper) | ResNet50 | - | 81.8 | 75.1 | 78.3 | - |

Citation

@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 Conference on Computer Vision and Pattern Recognition},
  pages={9336--9345},
  year={2019}
}

License

This project is released under the Apache 2.0 license.