•1 min read•from Machine Learning
[D] Large scale OCR [D]
I need to OCR 50 million pages of legal documents. I'm only interested in the text, layout is not very important.
What is the most cost effective way on how I could tackle this while it not taking longer than 1 week?
[link] [comments]
Want to read more?
Check out the full article on the original site
Tagged with
#rows.com
#large dataset processing
#OCR
#optical character recognition
#legal documents
#50 million pages
#text extraction
#large scale
#cost effective
#automation
#text
#document processing
#machine learning
#text-only
#tackle
#efficiency
#data processing
#information retrieval
#layout
#scalability