I'm really impressed, I didn't expect to have 100% recognition without training tesseract, I take my hat off to you, sir Did you manually clean image in GIMP/Photoshtop or you used some image processing library to get such clean result?
On Mon, Nov 4, 2013 at 8:34 AM, zdenko podobny <[email protected]> wrote: > Tesseract is "noise sensitive" - you need to pre-process image before OCR. > See FAQ[1] > > [1] > https://code.google.com/p/tesseract-ocr/wiki/FAQ#Output_without_result_or_bad_output > > > Zdenko > > > On Mon, Nov 4, 2013 at 1:24 AM, Valent <[email protected]> wrote: >> >> Hi, >> got back to doing this project, plan is to ocr my gas and power meters so >> I can get some insight how much of each we use them over time. >> I got past first block, and instead or "Empty page" error I get some OCR >> results, finally! >> >> After reading blog posts and forum posts about how tesseract works still >> can't fully figure it out, so your help is much appreciated. >> >> I have this image to work with: http://imgur.com/CiruqHF >> >> Tesseract gets this as result "3 2 9 3 3... 3 -" which is far from >> perfect because meter reads "32830,8" >> >> From what I have read so far I guess that my next step to get better >> results is to take 10-20 pictures and train tesseract, right? >> >> WIki on training tesseract is not clear for newbie like me. Now I got >> Qt-Box-Editor installed on my Linux Mint laptop and got first box text file >> done: >> https://www.dropbox.com/s/8hjgh21wu41d2l9/struja.box >> >> I have followed these instructions: >> https://github.com/this-is-ari/python-tesseract-3.02-training >> >> But how do I now train for more samples? >> >> What do I do after I take more pictures from my power meter and gas meter? >> Should I train tesseract for each meter separately or together? >> >> >> -- >> -- >> 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. > > > -- > -- > 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. -- follow me - www.twitter.com/valentt & http://kernelreloaded.blog385.com linux, anime, spirituality, wireless, scuba, linuxmce smart home, zwave ICQ: 2125241, Skype: valent.turkovic, MSN: [email protected] -- -- 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.
