I am using a web service to read image files and return me some text on it using Tesseract.
As we know Tesseract/Tess4j supports languages input in the ISO 639-3 format (ie: eng, spa, deu, ara, etc...) but the language I get from the mobile device comes in this format: en-gb, pt-br,...
My user can be using any language and request a picture reading.
My question is: anybody has any ideia how to solve this?
And more, if I don't set any language, does it guess/find the language on the image?