Thought it would be useful:
a post I’ve wrote about my experiences and experiments with OCR
Thought it would be useful:
a post I’ve wrote about my experiences and experiments with OCR
This blog post from Dropbox is also very useful. It explains how they applied deep learning for OCR. They generated training samples with GAN which is excellent idea. https://blogs.dropbox.com/tech/2017/04/creating-a-modern-ocr-pipeline-using-computer-vision-and-deep-learning/