Hi Richard, I know it was a while ago but did you ever find a solution to this problem?
I'm attempting something similar where I wish only to recognize digits and discard any text matches. The method presented in the FAQ isn't exactly what I need as it seems to only limit the returned results to digits, yet still matches all letters in the image. Thanks, Jalal. On Friday, March 4, 2011 12:36:56 AM UTC+11, Richard wrote: > > Yes, that is possible and I am scanning now to do that > > .... but its not possible to always the know the format of the plate > and just changing random chars may/does give strange results. > > On Mar 3, 1:13 pm, patrickq <[email protected]> wrote: > > The answer lies within your own question! Since you expect only > > digits, simply accept these letters as the equivalent digit by > > replacing them. > > > > Patrick > > > > On Mar 3, 5:09 am, Richard <[email protected]> wrote: > > > > > Hi, > > > > > I am really new to Tesseract OCR 3.0 as a static DLL within a windows > > > envionment and have the majority of what I want working but... > > > > > Is there a way to increase the sensitivity of the OCR engine? > > > > > For instance, I am passing JPG images that purely have images of > > > registration plates (ANPR essentially) but the OCR engine reads > > > > > 1 as I > > > 0 as U > > > 8 as S > > > > > I have tried altering params on the TessBaseAPI::INit but this simply > > > crashes it set to nything other than OME_DEFAULT > > > > > I have also set up a char whilelist to limit to certain chars/digits > > > > > Any help would be appreciated. -- 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
