We have updated annotations for both train and test set.

Train: 1000 images [images] [annos]

Additional point annotation for each character is included. Example can be referred to here.

wget -O train_images.zip https://universityofadelaide.box.com/shared/static/py5uwlfyyytbb2pxzq9czvu6fuqbjdh8.zip
wget -O train_labels.zip https://universityofadelaide.box.com/shared/static/jikuazluzyj4lq6umzei7m2ppmt3afyw.zip

Test: 500 images [images] [annos]

wget -O test_images.zip https://universityofadelaide.box.com/shared/static/t4w48ofnqkdw7jyc4t11nsukoeqk9c3d.zip
wget -O test_labels.zip https://cloudstor.aarnet.edu.au/plus/s/uoeFl0pCN9BOCN5/download

Note all Chinese texts are annotated with '###' (ignore) in this updated version, because the number of Chinese is too small for both training and testing purpose. ArT and LSVT two optional large-scale arbitrarily-shaped text benchmarks for both Chinese and English.

Original detection only evaluation script.

For both detection and end-to-end evaluation in the updated version, please refer to here. This scipt also includes evaluation example for Total-text.

The project is outdated and will not be maintained anymore. Original info is kept in OLD_README.md.

The SCUT-CTW1500 database is free to the academic community for research only.

For other purpose, please contact Dr. Lianwen Jin: eelwjin@scut.edu.cn