Can you share your dataset that mentioned in the article?

[hcnhatnam]

"Our model was trained on 3,000 natural images, including 229 images
from the ICDAR 2013 training set. We collected the other images ourselves and
manually labelled them with text line bounding boxes".

[tianzhi0549]

I am sorry. These images cannot be released due to their licenses. But we think today you can download enough scene text training data from the internet.