On 7 July 2010 10:34, Halindel <[email protected]> wrote: > hi, > > Thanks for you answer, I try to poste a message yesterday about my > problem. I solve only a small piece, my image seems to be too small so > I use this commande : > convert -sample 200%x200% -monochrome -depth 8 test.png test.tif > > But It did not translate all and I have a lots of error, I need to use > 2 or 3 size to have the complete information, but the information are > one each new file so I need to make an other script to select the best > choice.
Well, the characters in the image you linked to were a bit thin, which is usually a problem with OCR. If you have a lot of these images to process, it might be worth manually correcting a few and using a statistical post-editor. There's one linked to from the wiki - I can't get to it at the moment, but it should be easy to find. -- <Leftmost> jimregan, that's because deep inside you, you are evil. <Leftmost> Also not-so-deep inside you. -- 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.
