Hi,
I am working on a image processing assignment and I would like to use Tesseract for recognising the letters/numbers on the plate after it has been located. I want to use Tesseract as OCR is hard and this library claims that it can handle skewed and curved lines. I seems to work reasonably well but I think I need to tweak the settings. So far I have told it to only look for A-Z and 0-9. It seems to try to break the number plate up into words, when it should be a single 'word'. It also tries to stick words into all numbers or all letters rather than letting it mix. e.g. 4536B becomes 45368. So how do I get it to disable the word breaking, and disable the dictionary/number classifier part. Is it possible to tell it some sort of pattern to match? All the number plates I need to recognise follow these patterns: S[C or D][A to Z]xxxx[A to Z] S[C or D][A to Z]xxx[A to Z] S[C or D][A to Z]xx[A to Z] EA to Z]xxxx[A to Z] Some of the S... number plates are split into two lines: S[C or D][A to Z] xxxx[A to Z] S[C or D][A to Z] xxx[A to Z] x = [0 to 9] Thanks, Leith -- 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.
