Python/C++/Java: Is there a library that will reco

问题:

I've looked into PyTesser/Tesseract and as far I as I can tell, it only gives me a string once I input an image.

However, I'd like to receive, instead, the coordinates/bounding rectangle of each character it recognized. The string itself might be useful for me later on, but right now that's now what I need.

Assuming PyTesser/Tesseract don't offer me that functionality, is there something freely available (ie, not Matlab or something similar) that does?

回答1:

According to this mailing list thread, you can do this with Tesseract. However, I don't know of Python wrapper that will grant you access to that data.

回答2:

Have a look at a similar question recently posted to tesseract google group: http://groups.google.com/group/tesseract-ocr/browse_thread/thread/70ad57cb37edabe0/

回答3:

Maybe you should try "ocropus":

http://code.google.com/p/ocropus/