Re: [tesseract-ocr] Any suggestions on pre-processing to improve accuracy?

Thanks, this is really useful. (and shame on me for not RTFM'ing a bit more first) That document mentions to make sure the orientation/skew is straight, but does not give any hints on how to actually do this in an automated fashion. Any tips? On Friday, June 20, 2014 12:08:50 PM UTC-7, Ni

Re: [tesseract-ocr] Any suggestions on pre-processing to improve accuracy?

Hi Traun, > Any tips on doing pre-processing on the images to improve the > recognition? The place to start would be here: https://code.google.com/p/tesseract-ocr/wiki/ImproveQuality Nick -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To

[tesseract-ocr] Any suggestions on pre-processing to improve accuracy?

I'm wondering how I can get better results with Tesseract. Here are a few images I've been testing with + results: *Image *: *Actual O

Re: [tesseract-ocr] Re: Pharmaceutics OCR recognition project

Yep, that was the solution. Now it works fine even with bigger dictionaries. Thank you guys. Elena 2014-06-19 18:25 GMT+02:00 Nick White : > On Wed, Jun 18, 2014 at 07:30:03AM -0700, Paul wrote: > > That upper bound actually might be the root of your problem. If you've > already > > compiled T