Live data from Hacker News

Replace OCR with Vision Language Models

github.com

1–10 of 130 posts

Re: Replace OCR with Vision Language Models

#4
I think OCR tools are good at what they say on the box, recognizing characters on a piece of paper etc. If I understand this right, the advantage of using a vision language model is the added logic that you can say things like: "Clearly this is a string, but does it look like a timestamp or something else?"

Re: Replace OCR with Vision Language Models

#5
I've been experimenting with vlm-run (plus custom form definitions), and it works surprisingly well with Gemini 2.0 Flash. Costs, as I understand, are also quite low for Gemini. You'll have best results with simple to medium-complexity forms, roughly the same ones you could ask a human to process with less than 10 minutes of training.

If you need something like this, it's definitely good enough that you should consider kicking the tires.

Re: Replace OCR with Vision Language Models

#8
post #5

I've been experimenting with vlm-run (plus custom form definitions), and it works surprisingly well with Gemini 2.0 Flash. Costs, as I understand, are also quite low for Gemini. You'll have best results with simple to medium-complexity forms, roughly the same ones you could ask a human to process with less than 10 minutes of training. If you need something like this, it's definitely good enough that you should consid…

Very cool! If you have more examples / schemas you'd be interested in sharing, feel free to add to the `contrib` section.

Re: Replace OCR with Vision Language Models

#9
post #2

I wonder what the speed of this approach vs traditional ocr techniques. Also, curious if this could be used for text detection (find a bounding box containing text within an image).

Was just coming here to say this, there does not yet exist a multimodal vision LLM approach that is capable of identifying bounding boxes of where the text occurs. I suppose you could manually cut the image up and send each part separately to the LLM but that feels like an kludge and it's still in-exact.
Post reply on HN