What would be the best way to implement this service and make it available through an api? Would I need to train a machine learning algorithm or is it there a more simpler solution?
Who knows if there is any free service which would take a pdf with images and translate it to text that could be consumed by a web server?
I'm about to finish a Coursera course about Machine Learning, I know a bit about tensorFlow, but I'm not certainly an expert on machine learning.
I do know a lot about web development.
Many thanks.