In my OCR situation, Tesseract can not identify rows properly. Please see the attach box image below. (Blue squares are boxes found by Tesseract and red areas are marked as problematic area by me)
[image: qq 20160615195248] <https://cloud.githubusercontent.com/assets/3959938/16078734/118747c2-3333-11e6-890a-5eeaac13f217.png> It seems that Tesseract is not able to find the baseline correctly when the row spacing is small and the image is a little skew --- two chars in two rows are mistakenly vertically merged. Therefore, the OCR quality in "crowded" space is really poor. How could I imporve the OCR quality in this situation? Are there any params can be used 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 https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/ed881af0-f4bf-42e1-8106-1bafd50f3702%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
