List of all system fonts Tesseract OCR Text2Image
I am using tesseract OCR on Windows 10, I was able so far to create .box and .tif files for one font at a time, but when I try to make fontslist as described on the github website, it doesn't work, giving me a warning
WARNING: Could not find font to render image title with <
and it gives an error for every font like:
Aldhabi font failed with 62 images = 21.60%
also gives '%' (U + 25) not covered in font , but I dont know what that means anyway, the command I use is: text2image --text = training_text.txt --outputbase = eng.fontlist. txt --fonts_dir = C: \ Windows \ Fonts --find_fonts --min_coverage = 1.0 --render_per_font = false --fontconfig_tmpdir = C: \ Tesseract \ Tesseract-OCR
Any idea how to resolve this error?
Thank you in advance
source to share
No one has answered this question yet
Check out similar questions: