[tesseract-ocr] Any way to prevent contextual digits-letters flipping ?

Hi everyone, tesseract seems to sometime use the closest characters to guess what will be the next one. Let me explain that with an exemple: I want to parse a picture that contains the following sequence of characters SE3P-104168 but most of the time the output will be SESP-104168 I believe

Re: [tesseract-ocr] Any way to prevent contextual digits-letters flipping ?

Hi, I haven't tried it, but quickly grepping around the source code suggests setting the config variable crunch_include_numerals to true might do the job. Please let us know if that works. Nick On Wed, Jul 09, 2014 at 11:15:10PM -0700, Damien D wrote: Hi everyone, tesseract seems to