News for hackers. Stuff that matters.

A comment on Replace OCR with Vision Language Models. Parent comment

Re:Replace OCR with Vision Language Models by tensor on Thursday February 27, 2025 @12:26PM (#43196432)
100% this, combining traditional OCR with VLMs that can work with bounding boxes so that you can correlate the two is the way to go.
[ Parent | on HN ]

There are no comments on this comment yet.