News for hackers. Stuff that matters.
Re:Extracting Chinese Hard Subs from a Video, Part 1 by Seanny123 on Tuesday May 30, 2017 @12:41AM (#14443038)
I totally thought the state-of-the-art for OCR would be ConvNets, but apparently it isn't? Or are there just not any easily available/usable libraries that do OCR with Convents? Or is the benefit of ConvNets marginal enough to not be useful?
Re:Extracting Chinese Hard Subs from a Video, Part 1 by Seanny123 on Tuesday May 30, 2017 @12:48AM (#14443055)
Found a paper! Yes, it is better. Maybe not for this specific application and given there's no pre-trained network available, I can totally understand the choice made. https://www.semanticscholar.org/paper/The-recognition-of-Chi...
Re:Extracting Chinese Hard Subs from a Video, Part 1 by anewhnaccount2 on Tuesday May 30, 2017 @03:49AM (#14443573)
Here's a free complete OCR solution using LSTM https://github.com/tmbdev/ocropy