Hello, I using successfully tesseract v5.0.0-alpha.20200223 (windows) but sometime it will totally fail, but it should not.
Try these two steps: 1) Try to recognize text from my image: tesseract.exe e:\resized1.bmp - myconfig myconfig contains: tessedit_char_whitelist abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ .,-"':$?! tessedit_write_images true Result is nonsense: CBee em ene he eke And it will create also debug image of same picture: tessinput.tif 2) Try to recognize text from that tessinput.tif (which should be already used in situation 1) tesseract.exe tessinput.tif - Result is correct: We'll head up this way. Why? Images: http://www.aaagames.cz/ocr/resized1.bmp http://www.aaagames.cz/ocr/tessinput.tif <http://www.aaagames.cz/tessinput.tif> Regards, Miroslav Šanc -- 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/acf4294b-4df5-40f8-9f26-54b72e587ebf%40googlegroups.com.
