Hi, I have an appliance regulating chlore level in a pool. Very basic need to read 2 numbers like on the photo here below : [image: regu.jpg] A first experimentation shows that "733" has been properly discovered and returned. The "0%" however returned as "8%" [image: Tesseract-Run1.jpg]
So in summary : - no question of language, only digits and '%' to be recognized. (-c tessedit_char_whitelist=0123456789%) - is it correct that I only need to retrain for those characters 0123... ? - how to retrain : take as many photos as necessary of the appliance screen until I have all digits on a photo ? Then follow the process to prepare an increment of test data. Is this approach ok ? Welcomed any hint ! Thans you ! -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion visit https://groups.google.com/d/msgid/tesseract-ocr/609ff3c8-2c46-47bf-8a0a-eba80e89bc65n%40googlegroups.com.
