[danvk]

I've had really good luck recently running OCR over a corpus of images using gpt-4o. The most important thing I realized was that non-fancy data prep is still important, even with fancy LLMs. Cropping my images to just the text (excluding any borders) and increasing the contrast of the image helped enormously. (I wrote about this in 2015 and this post still holds up well with GPT: https://www.danvk.org/2015/01/07/finding-blocks-of-text-in-a...).

I also found that giving GPT at most a few paragraphs at a time worked better than giving it whole pages. Shorter text = less chance to hallucinate.

[pbhjpbhj]

Have you tried doing a verification pass: so giving gpt-4o the output of the first pass, and the image, and asking if they can correct the text (or if they match, or...)?

Just curious whether repetition increases accuracy or of it hurt increases the opportunities for hallucinations?

[danvk]

I have not, but that's a great idea!