This is a PyTorch implementation of "SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervisionand Dynamic Self-Training"

The paper propose a novel text detection system termed SelfText Beyond Polygon(SBP) with Bounding Box Supervision(BBS) and Dynamic Self Training~(DST), where training a polygon-based text detector with only a limited set of upright bounding box annotations. As shown in the Figure, SBP achieves the same performance as strong supervision while saving huge data annotation costs.

From more details,please refer to our arXiv paper

• python 3
• torch = 1.1.0
• torchvision
• Pillow
• numpy

• Release code(BBS)
• Release code(DST)
• Document for Installation
• Document for testing and training
• Evaluation
• Demo script
• re-organize and clean the parameters

Supported:

• ICDAR15
• ICDAR17MLI
• sythtext800K
• TotalText
• MSRA-TD500
• CTW1500

Supported text detection:

• EAST EAST: An Efficient and Accurate Scene Text Detector
• Psenet Shape Robust Text Detection with Progressive Scale Expansion Network
• DB

The training strategy includes three steps: (1) training SASN with synthetic data (2) generating pseudo label on real data based on bounding box annotation with SASN (3) training the detectors(EAST and PSENet) with the pseudo label

(TDB)

(TDB)

(TDB)

for example (batchsize=2)

(TDB)

(TDB)

for example (batchsize=2)

(TDB)

The visualization of bounding-box annotation and the pseudo labels generated by BBS on Total-Text

https://github.com/SakuraRiven/EAST

https://github.com/WenmuZhou/PSENet.pytorch

For academic use, this project is licensed under the Apache License - see the LICENSE file for details. For commercial use, please contact the authors.

Please consider citing our paper in your publications if the project helps your research.

Eamil: [email protected]