Y
Hacker News
new
|
ask
|
show
|
jobs
by
bhanhfo
2372 days ago
Tesseract is optimized for images with white backgrounds. ID cards or movie screenshots do not work well.
1 comments
Certified
2372 days ago
I have used tesseract ocr combined with imagemagick and ffmpeg to great success for video text extraction.
link
beagle3
2371 days ago
Can you list your script/pipeline? I haven't had much success (though, I only ran ffmpeg's internal tesseract OCR[0], no imagemagick processing or any other processing in between)
[0]
https://ffmpeg.org/ffmpeg-all.html#ocr
link