See the documentation at http://tesseract-ocr.googlecode.com/svn-history/r725/trunk/doc/tesseract.1.html . You'll want to do just like it does in the example - suppress the default dictionary and supply your own. Check the tesseract FAQ for how to increase the confidence in the dictionary also. If this doesn't work, you could also consider post-ocr approaches like edit distance between OCR output and your desired words, or even something so crude as an image search for a picture of the word you want. Hopefully it won't come to that, though.
On Wednesday, December 12, 2012 8:48:57 AM UTC-5, Timo Tischler wrote: > > Hi I want to use tesseract-ocr to recognize nutrition-facts from food. > > tesseract doesn't recognize the data I want very well. So I have the > question whether there is a possibility to force tesseract to pick a word > from a (custom) dictionary. > I want tesseract to only recognize a custom set of words. > > And another Question: > How can I optimize the pictures i have taken, so tesseract can recognize > the words more easy > > Thanks in advantage for help and please ignore my bad english > > > > -- -- 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.
