Hi there, I'm having some trouble training tesseract. I've programatically created a tif training file and a boxfile to try and teach tesseract how to recognize a small screen font for purposes of being able to read this font from screenshots of my screen. I've checked the boxfile through bbTesseract.exe and everything looks good, but I keep getting errors:
APPLY_BOXES: boxfile 1/1/T ((0,316),(8,326)): FAILURE! box overlaps no blobs or blobs in multiple rows APPLY_BOXES: boxfile 1/2/h ((12,316),(18,327)): FAILURE! box overlaps no blobs or blobs in multiple rows APPLY_BOXES: boxfile 1/3/e ((23,315),(29,324)): FAILURE! box overlaps no blobs or blobs in multiple rows (etc, and:) APPLY_BOXES: More than one block?? APPLY_BOXES: FATALITY - 0 labelled samples of "T" - target is 5: T:[54] APPLY_BOXES: FATALITY - 0 labelled samples of "h" - target is 14: h:[68] APPLY_BOXES: FATALITY - 0 labelled samples of "e" - target is 28: (etc.) The files I'm running through tesseract can be found at http://tedpearson.com/test333.tif and http://tedpearson.com/test333.box I'm wondering if tesseract is unable to read the image file due to the font being too small or something? Anyone have any pointers for getting this to work? Thanks. --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en -~----------~----~----~----~------~----~------~--~---
