Hacker News Reader

Comment by resonious | Hacker News Reader

Agree on reading. The one tool I feel I want is a good OCR + dictionary setup, as a quick escape hatch for physical books.

I actually cobbled together something like that using Google's OCR API for Android. Works well for me but might be too janky for release. Maybe I should release it as a good tool for upper intermediates.

View on HN

If you haven't checked it out my other app Nihongo has a good OCR + dictionary setup. You can see a demo here: https://www.youtube.com/watch?v=ffRxPyc9K8A

iOS-only though.

Ahh yes that's basically perfect! Let me know when there's an Android version ;)

Haha yes! I would LOVE to make the app for Android someday. But as a solo dev, it’s just too much to take on on my own. If Nihongo ever blows up and I make enough to hire someone to help me out, an Android app is top of my list.

Web apps work everywhere, fwiw

If I’m paying for an app; and it’s not native, it usually annoys the hell out of me; I’ll gravitate towards a native option every time.

Oh wow, first time I see an OCR that can deal with 行書体. How extensive is your dataset for 行書 and do you also have 草書 or 隷書?

Under the hood, it's actually using Google's Cloud OCR API. Not sure how well it handles 草書 or 隷書, but it does a pretty remarkable job with 行書. Also does surprisingly well with super pixelated text. I can look up words in 16-bit games trying to squeeze kanji into 16x16 sprites or something, and it holds up incredibly well.

You can also swap out the OCR API it uses. Right now I support Google and ocr.space.

Reply on news.ycombinator.com