Haha, that was actually me I believe. No one responded then. I had hoped someone would have chimed in. So I thought I'd try again.
On Sunday, September 22, 2013 2:54:52 PM UTC-6, Dovy Paukstys wrote: > > I've been testing tesseract-ocr for an open-source project I am doing. I > want users to be able to take a picture of a grave, try to recover the > birth/death info and maybe the name, but then ask them to correct the > information if wrong. > > The issue is Grave Markers are not a common font, common color, or shape. > Some zoning and image manipulation must occur before OCR can even be done. > > Does anyone have any concept of this? Would anyone like to toy with this > idea for a bit? > > Here are some example grave markers you could grab today: > > http://image2.findagrave.com/photos/2013/172/88552025_137193683625.jpg > http://image2.findagrave.com/photos/2013/246/116541132_137832680677.jpg > http://image2.findagrave.com/photos/2011/241/31714236_131474280838.jpg > > Maybe in the process we could users manually zone the text areas in some > way. > > Does anyone have any ideas? > -- -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- 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]. For more options, visit https://groups.google.com/groups/opt_out.
