Tesseract's textline finder relies a bit too heavily on there being several lines in a text block. The existing line finder is too unstable to make it work well both ways.There are plans to fix this in 3.00, and there will also be a new API to control the layout analysis mode to force it to believe that all the text in the image is a single line, single word, or even single character. Ray.
On Sun, Nov 9, 2008 at 11:12 PM, Tien Dung <[EMAIL PROTECTED]> wrote: > Hi Ray, > > One of the text line recognition scripts in OCRopus said that: > http://ocropus.googlecode.com/svn/trunk/ocroscript/scripts/rec-ltess.lua > > -- Example of using the Tesseract line recognizer together with > -- OCRopus layout analysis. > -- Note: *this does not work very well right now because Tesseract* > -- *has problems with recognizing text in individual lines*. > > Is it true that Tesseract has problems with recognizing text in individual > lines? > > If yes, how can we fix it? > > Best regards, > > -- > Tien Dung > http://codemonkeycode.blogspot.com/ > > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
