Hacker News new | past | comments | ask | show | jobs | submit login

It would be great if OCR got to the point where you could just point the phone camera at a sign and have it output 1:1 what is in front of you with translated text, like a magic little window frame. Shit still struggles with parsing PDFs though so I'm not holding out too much hope, though.



The Google Translate app does exactly that in its camera mode, and has been doing so for at least 3 years.


Have you seen https://www.youtube.com/watch?v=06olHmcJjS0&feature=emb_titl... ? That was 2015 and it's improved a bit since.

I've used it in a number of countries with great success, especially reading menus.

(Disclaimer: Googler, but unrelated to those teams)


Google translate kinda does this already, with a mixed success




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

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

Search: