Hacker News new | past | comments | ask | show | jobs | submit login
Ask HN: What’s a good solution for messy handwriting recognition for mobile app?
6 points by faizshah on Nov 26, 2021 | hide | past | favorite | 3 comments
Looking for an API, pretrained model or some guidance on how to implement handwriting recognition of post it notes, handwritten paper notes etc. for a mobile app.



The canonical example of image recognition for AI is recognizing handwritten digits from the NIST dataset; you'll find it in most computer vision tutorials.

If you want to learn about rolling your own: https://towardsdatascience.com/classifying-mnist-digits-usin...

https://machinelearningmastery.com/handwritten-digit-recogni...

https://scikit-learn.org/stable/auto_examples/classification...

The only issue is that you'll have to find training data for letters. I'd be surprised if that didn't exist.

Also, Google has an API for recognizing handwriting: https://cloud.google.com/vision/docs/handwriting

I haven't used it, so I can't vouch for it one way or another. But that'd be a pretty easy way to go!


I’m looking for something specific to messy handwriting, the kind you find in notebooks and on post it notes.


I found an interesting solution from caltech: https://github.com/caltechlibrary/handprint

Also it seems the keyword to find models and apis for this is “handwritten text recognition.”




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: