Hi everybody,
I haven't done any code in a while but I have a project in mind and will definitely give opencv a go. Basically I would need to recognize text on images and be able to manipulate it as a string. The best case would be to be able to have a string array with all the words present on the picture which could be in any form.
I'll most likely go with java since the target will be android and that I find java productivity way better than c++.
The question now - I have been browsing the documentation and the forums lately but I still can't find out where to get started. Is there any sample code somewhere or general explanation about the whole library ? I understand that nothing is automated and that we have different algorithms to play with and do all sort of treatment on pictures. Some algorithms require the picture to have a certain form ( grayscale, etc ).
Also, I am quite unsure about how to connect it to tesseract for text recognition, or is tesseract integrated and encapsulated in openCV ?
Any hint would be much appreciated !
Thanks, Arnaud