In tesseract, you are able to pull out, in HTML, the conversion areas so you can see what is being selected for analysis. Try putting the something other than 0/D in the edge boxes. I had an issue in the past with the thickness of the curved edges.
On Thursday, 27 February 2014 02:35:48 UTC-5, temp name wrote: > > Hello, > > I have an image which contains only table. When I used tesseract for OCR > it doesn't recognize text from first and last column. > I have attached the image which I have used. > > After lot of trial, when I modified the image manually and added some text > over the table before feeding image to the tesseract. > I got correct results. I am not able to understand the logic here. why > tesseract don't recognize first image but it recognized second image. > I suspect it is because of table border analysis or page border analysis > in preprocessing phase of tesseract. if this is the case, then tesseract > should have a parameter which can force tesseract to ignore page border > analysis. I need some help urgently. Any idea? > > P.s.I have attached the two images. > -- -- 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.
