Reputation: 11
I want to use Paddle to OCR a really fancy custom font. It's good but i know it could be better if I fine tuned it. I've run into this tutorial on Medium but it assuems the reader already has training dataset.
I have some experience with creating datasets for Tesseract using its text2image utility, could I somehow reuse it with Paddle?
If no, is there another automated way of creating the dataset for Paddle?
Upvotes: 1
Views: 410