Hi, I'm training tesseract on my own dataset which only contains digits, comma, and period. During training phase, the printed output displays at most 3 lines for each text: GROUND TRUTH, ALIGNED TRUTH, BEST OCR TEXT. The below is an example:
I'm wondering what those ALIGNED TRUTH and BEST OCR TEXT exactly mean. The Wiki page says just " GROUND TRUTHfor the line is displayed in all cases. ALIGNED TRUTH and BEST OCR TEXT are displayed only when different from the GROUND TRUTH. " Is there anyone who know what they are? Thank you for your reply in advanced. -- 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/0db6e2d8-a4ae-4bf7-8f49-d4ae62d1426e%40googlegroups.com.
