see attached image. have tried various things, including this config: tessedit_char_whitelist 0123456789:. load_system_dawg F load_freq_dawg F tessedit_write_images T tessedit_create_boxfile T
and playing around with the source image in various ways to get it in its attached form. also run it with -psm 7 (and have tried 8) to no avail. currently i get: "30:59" which is significantly better than what i was obtaining previously. based on the previous two posts and one i found on stackoverflow, it seems like tesseract has difficulty classifying "digital" font characters. any suggested preprocessing that would improve performance here? -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/30dcc5f5-d7f3-4916-8dc4-cc8ad08b3d6b%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
