Hi Efi, On Mon, Nov 25, 2013 at 07:05:46AM -0800, Efi Jorn wrote: > I need to perform OCR on tables that contain a product's name in the left > column and the quantity of this product that was ordered in the right column. > > Will Tesseract's accuracy will be greater if I have all possible product names > in the freq-dawg file and then train Tesseract?
Yes, it should help to improve things. Note that you don't have to completely re-train Tesseract to do this, you can just use 'combine-tessdata -u' to take apart the appropriate training file, use dawg2wordlist to extract the original freq-dawg wordlist, add your words, then use wordlist2dawg and combine-tessdata to create a new training file with the extra product names. Nick -- -- 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.
