[tesseract-ocr] Re: Tesseract couldn't load any languages!

I downloaded a new language from https://github.com/arturaugusto/display_ocr/tree/master/letsgodigital (7-segment numbers) i put the file in my tessdata directory: C:\Program Files (x86)\Tesseract-OCR\tessdata when I run tesseract I get the error: An error occured: { [Error: Command failed: C

Re: [tesseract-ocr] Problem reading text in two columns

Sorry, I forgot to specify that. Tesseract 3.04.01 I'm using the data from tesseract-ocr-eng On Sunday, May 6, 2018 at 11:16:39 PM UTC-5, shree wrote: > > Which version of tesseract are you using? > > Which traineddata (from which repo) > > Try with --psm 6 if using tesseract 4 beta. It will re

Re: [tesseract-ocr] Pytesseract used with captcha images unable to recognize characters with lines on top

Try to get rid of all the noise/lines, you can use denoise before binarization or component analysis. Then remove the white border so all the fragments have the same size. Try to do this with gimp and see if it helps before coding it. Then try psm=8 it means "single word" (this should fix the pr