Tesseract isn't really suitable for your problem, especially as you seem to want rotation invariance. You might be better off using Leptoinca, but you might find other computer vision libraries that are more suitable. Ray.
On Sat, Oct 24, 2009 at 12:56 AM, JerryPu <[email protected]> wrote: > > Here I have problems on determining whether printed words on ICs are > similar. For examples: > > words "EH86" are in pic 1, > words "EH86" are in pic 2, > words "t1Ag" are in pic 3, > of course I can tessercat pic1, then pic2, and compare results using > baseAPIs, but it is slow, and when graph is printed on ICs, it is not > working. > > How can I use tesseract fot correlation pattern recognization? Have > any one done it? thanks. > > pic 1: > http://groups.google.com/group/tesseract-ocr/web/2.jpg > pic 2: > http://groups.google.com/group/tesseract-ocr/web/3.jpg > pic 3: > http://groups.google.com/group/tesseract-ocr/web/6.jpg > > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
