Hello, This problem occurs when there is very little line spacing or in some cases, font size is too small as footnotes/endnotes in "pleading" documents.
One trick to suggest based on my experience: Just scale your image, isolate the individual blobs put them together and then perform recognition. Ofcourse you should know the layout and/or line information in order to render the correct results in recognized text. Although this works with any OCR engine, but if there are any intrinsic properties in the current version, I am interested to know! Regards, Vicky -- Vicky Budhiraja http://www.sitarasoft.com/ -----Original Message----- From: [email protected] [mailto:[email protected]] On Behalf Of mw18888 Sent: Monday, April 04, 2011 06:09 To: tesseract-ocr Subject: How to improve the Tesseract OCR accuracy when two text lines adjacent to each other >From the testing, I see that the Tesseract OCR can't recognize the characters if two text lines are adjacent (or vertically very closed to each other.) I wonder if I can ( have a way to ) configure the Tesseract to improve the OCR accuracy when two text lines are too closed. Thank you in advance. mw18888 -- 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 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.
