Simple thresholding should work. You'll have to use something like OpenCV or your own routine if you are daring. If you convert to gray, anything less than 64 (out of 255) goes to black, and anything above that goes to white.
On Tuesday, May 21, 2019 at 5:51:48 AM UTC-4, April Shar wrote: > > I'm using tesseract 3.0.2, seems like it cannot read text with very bright > background (see image). Is there a way to do so? Microsoft Azure works > better and can read the text. > -- 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/02a80cdd-cda4-4e23-9673-8530ce4ab064%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
