Hi, Are there any tips to improve quality of text recognition from screen-captured images besides re-scaling them to 300 DPI?
Any preference to image formats for a capture that could be helpful for tesseract? Yet another question is how to handle i.e. "step-by-step" with two hyphens that are recognized as letter 'r' somehow? Well, a similar case is some text with "Menu->Edit" and how to handle underlined web-links i.e. from PDF docs? Thank you in advance for sharing of your ideas! Hypo -- 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/228d9d8a-0ba8-4bc2-aa6e-0556be470b84%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
