← Back to context

Comment by kbumsik

3 months ago

> My impression is that OCR is basically solved at this point.

Not really in practice to me. Especially they still struggle with Table format detection.

11 comments

kbumsik

Reply
coulix  3 months ago

This.

Any complex parent table span cell relationship still has low accuracy.

Try the reverse, take a complex picture table and ask Chatgpt5, claude Opus 3.1, Gemini Pro 2.5 to produce a HTML table.

They will fail.

  • pietz  3 months ago

    Maybe my imagination is limited or our documents aren't complex enough, but are we talking about realistic written documents? I'm sure you can take a screenshot of a very complex spreadsheet and it fails, but in that case you already have the data in structured form anyway, no?

    • daemonologist  3 months ago

      Now if someone mails or faxes you that spreadsheet? You're screwed.

      Spreadsheets are not the biggest problem though, as they have a reliable 2-dimensional grid - at worst some cells will be combined. The form layouts and n-dimensional table structures you can find on medical and insurance documents are truly unhinged. I've seen documents that I struggled to interpret.

      1 reply →

richardlblair  3 months ago

I had mentioned this when the new QWEN model dropped - I have a stack of construction invoices that fail through both OCR and OpenAI.

It's a hard (and very interesting) problem space.