I'm pretty new to tessnet2. So I'm using Tessnet2 because I'm using OCR in C# language. So I add tessnet_32.dll to the reference to make OCR works. However, I faced a issue.
Since tessnet2 is tesseract2.0, I can't use all the language file which are in the tesseract github. Therefore my question is :
1) Is it possible that I can extract lang.traineddata and get all 8 files that can be used in tessnet2? 2) If not, can anyone please explain me how to train a data to add new language? (such as Korean or Japanese)? I know that https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract2 has all the steps. But when I use the command line, I don't get anything. In other words, I'm stuck in making a box. If anyone can explain me how to train a data from installing the tesseract 2.0, it would be great.
Thank you for helping me.
