If you crop the image to the “box” containing the text and numbers, and convert it to a black and white image, the numbers seem to be picked up as well. There are tools, like opencv, that would help extract blobs if the positioning of scoreboard in the display can’t be predicted, though you could probably extrapolate regions based on the clusters of text. Tesseract will give coordinates for words, you could use those to extract rectangles on the left and right sides of the text and then re-OCR for the numbers.
art From: [email protected] [mailto:[email protected]] On Behalf Of Adam Winster Sent: Saturday, October 14, 2017 9:13 PM To: tesseract-ocr <[email protected]> Subject: [tesseract-ocr] Numbers not recognized Hello, I am trying to perform OCR on the attached file. It is recognizing 95% of the words but isn't picking up any of the numbers. Anyone have a solution? 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]<mailto:[email protected]>. To post to this group, send email to [email protected]<mailto:[email protected]>. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/aee73e69-e99c-4b6d-ad3e-be3cd21113e4%40googlegroups.com<https://groups.google.com/d/msgid/tesseract-ocr/aee73e69-e99c-4b6d-ad3e-be3cd21113e4%40googlegroups.com?utm_medium=email&utm_source=footer>. For more options, visit https://groups.google.com/d/optout. -- 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 post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/YTOPR0101MB209128E8EC4F044B58F7EB8DDC4F0%40YTOPR0101MB2091.CANPRD01.PROD.OUTLOOK.COM. For more options, visit https://groups.google.com/d/optout.
