Sorry, Deepti, I misunderstood your problem. Anyway, I'm using 3.02.02 which might be slightly newer. You probably need to solve your problem with image pre-processing rather than Tesseract OCR itself. I'm not aware of any option to disable partial matches. It just does the best it can, so if you want to put a mask around the edges of your image you might eliminate the problem. How many images are you processing? Perhaps you could also use regular expressions (or some other pattern matching) for post-processing to throw out bad data. --Sven
On Tue, Nov 26, 2013 at 3:36 PM, dkas <[email protected]> wrote: > After looking thru your output, I see that you are getting "4.4.3" (not > 143, as in my case) and then 114. > So, we need some way for Tesseract ot be told that if it is 'cut' /not > full digits' ignore them. > > > On Tuesday, November 26, 2013 11:36:16 AM UTC-8, sventech wrote: > >> I'm using the latest release and I get the attached output (114 not 143). >> What version are you using? >> >> >> On Tue, Nov 26, 2013 at 2:04 PM, Deepti Sogani <[email protected]> wrote: >> >>> Hi, >>> I have an image where I have either 2 digit and 3 digit numbers >>> separated by space. >>> I want tesseract to only recognize full digits and not 'cut' digits as >>> in the attached image. >>> In the attached image, the first fully visible digit is "114" but >>> tesseract reports 143. >>> >>> >>> tessaract imageBeforeFirst.png imageBefore_outputFirst digits >>> >>> I have tried adding space to tessdata/configs/digits but that did not >>> help. Can someone please suggest how do I train Tesseract to fix the two >>> issues that I am facing ? >>> >>> Thanks. >>> >>> -- >>> -- >>> 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. >>> >> >> >> >> -- >> ``All that is gold does not glitter, >> not all those who wander are lost; >> the old that is strong does not wither, >> deep roots are not reached by the frost. >> From the ashes a fire shall be woken, >> a light from the shadows shall spring; >> renewed shall be blade that was broken, >> the crownless again shall be king.” >> > -- > -- > 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. > -- ``All that is gold does not glitter, not all those who wander are lost; the old that is strong does not wither, deep roots are not reached by the frost. >From the ashes a fire shall be woken, a light from the shadows shall spring; renewed shall be blade that was broken, the crownless again shall be king.” -- -- 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.
