Show HN: AI OCR API that handles complex IDs, like Brazil's many card types

[draculazmm]

Hi everyone,

For the past few months, I've been working on this project: an OCR API for ID cards. I think it's finally at a point where I'd love to get some feedback from the HN community.

My main focus has been on reliability, especially for "edge-case" documents that often break other systems. I spent a lot of time specifically on Brazilian IDs to prove the model could handle high variance.

This is still very much a work in progress, and I know there's a lot to improve. Your feedback would be invaluable in helping me figure out what to build next.

You can try it out here (I've set up a free tier with plenty of calls): https://www.100ocrapi.com/

What's the one feature you feel is missing? And what other countries or document types should I prioritize adding support for next?

[yoeven]

Hey! Awesome product, not sure which model you use under the hood but you should check out https://jigsawstack.com/docs/api-reference/ai/vocr. Great for ID extraction which also includes bounding boxes and other attributes you'd need

[draculazmm]

Hey, thanks so much for the kind words and the great suggestion! I really appreciate you taking the time to check it out.

Jigsawstack looks really interesting! I'll definitely check out their approach, especially for the bounding boxes and attributes, as that's something I'm actively looking to refine.

Thanks again for the feedback and for sharing the link!