I don't think it is significantly different to just regular OCR. Look at Tensorflow if you are interested in the comparision/classifying game.
On Thursday, August 3, 2017 at 9:57:00 PM UTC+3, ak...@cronj.com wrote: > > I need to verify if a vehicle at a gate is the one I'm expecting it to be > i.e. the for the vehicle image I intend to run OCR on, I already know the > licence plate number which I'm expecting, just need to verify that it's the > same, > > Ideally this task should ideally be way simpler/efficient for any OCR to > do than actually try to recognize texts from scratch. > > My question is there a way I can tell Tesseract OCR the expected text and > it just gives me the match score and based on which my application can take > the decision? > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/c9f409d2-f402-49fa-bc85-b9aa840a77f2%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.