Today I resume my work in the Doc Translator project, its goal is to be capable of getting data from images via OCR (with tesseract library) and then translate it via Google Translator, it’s also a perfect excuse for me to start developing for android devices. :-)

A couple of weeks ago a friend told me this functionality is already implemented in Google Goggles, but it’s not really useful with documents. I have the same problem with Google Translator functionality, good for signs or small sentences, but not good for documents, so I will try to use the tesseract library and we’ll see if we could make any progress in this field.

I’ve been playing around with buttons and the Camera API, nothing serious yet but you can follow the development in github.