Hi; I create a trainneddata for an Arabic font. I prepared the ara.training_text file to create synthetic data. I create image and box files with Text2Image. Then I create the Lstmf files. I start training. During training, the text lines are sorted from left to right. Is that normal?
GROUND TRUTH : هجبرع ردراو ىراثآ ردراو ىقارم هعبتت ردناقشلاچ رد ىكذ ردشمتيا تئشن ند هيبرح بتكم ىغيدلوا ىلشيريول ALIGNED TRUTH : هجبرع ردراو ىراثآ ردراو ىقارم هعبتت ردناقشلاچ رد ىكذ ردشمتيا تئشن ند هيبرح بتكم ىغيدلوا ىلشيريول BEST OCR TEXT : هجبرع ردراو ىراثآ ردراو ىقارم هعبگ ردناقشلاچ رد ىكن ردشمتيا تثشن ند هيبرح بتكم ىغيدلوا ىلشيريول Otherwise I need to sort each line of training text from left to right before training? Thanks in advance -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAA%3DdkuYk%2BR5UB0ywPzKFeAzrN2u0ebz2CRV7KTPSvTLugMA34Q%40mail.gmail.com.
