News

Python3 implementations of PSENet [1], PAN [2] and PAN++ [3] are released at https://github.com/whai362/pan_pp.pytorch.

[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.
[2] W. Wang, E. Xie, X. Song, Y. Zang, W. Wang, T. Lu, G. Yu, and C. Shen. Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In Proc. IEEE Int. Conf. Comp. Vis., pages 8440–8449, 2019.
[3] Paper is in preparation.

Shape Robust Text Detection with Progressive Scale Expansion Network

Requirements

• Python 2.7
• PyTorch v0.4.1+
• pyclipper
• Polygon2
• OpenCV 3.4 (for c++ version pse)
• opencv-python 3.4

Introduction

Progressive Scale Expansion Network (PSENet) is a text detector which is able to well detect the arbitrary-shape text in natural scene.

Training

CUDA_VISIBLE_DEVICES=0,1,2,3 python train_ic15.py

Testing

CUDA_VISIBLE_DEVICES=0 python test_ic15.py --scale 1 --resume [path of model]

Eval script for ICDAR 2015 and SCUT-CTW1500

cd eval
sh eval_ic15.sh
sh eval_ctw1500.sh

Performance (new version paper)

ICDAR 2015

SCUT-CTW1500

Performance (old version paper)

ICDAR 2015 (training with ICDAR 2017 MLT)

ICDAR 2017 MLT

SCUT-CTW1500

ICPR MTWI 2018 Challenge 2

Results

Figure 3: The results on ICDAR 2015, ICDAR 2017 MLT and SCUT-CTW1500

Paper Link

[new version paper] https://arxiv.org/abs/1903.12473

[old version paper] https://arxiv.org/abs/1806.02559

Other Implements

[tensorflow version (thanks @liuheng92)] https://github.com/liuheng92/tensorflow_PSENet

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}
}