Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Opctical Character Recognition (OCR) / Seven Segment Display reading through Camera #339

Open
DeastinY opened this issue Mar 22, 2019 · 3 comments

Comments

@DeastinY
Copy link

Has this been discussed somewhere?
This would allow to add many roasters in a non-invasive manner that were not originally designed to work with artisan.

@tanius
Copy link

tanius commented Apr 9, 2019

That's a really interesting idea! Such a feature exists in the Android app Roasted and Logged. Sadly, that one has not been updated since 2014, but could still be great as a source of inspirations for this feature.

For Artisan, the cameras probably would be webcams, connected with a USB cable. That allows to attach multiple such "sensors" and to fix them in the right positions. Ideally, the seven-segment displays would stay visible to the roaster operator.

Finally, in principle reading analog dial thermometers is also possible this way.

@DeastinY
Copy link
Author

DeastinY commented Apr 9, 2019

Thanks for picking it up! Roasted and Logged sadly seems not to be Open Source :o
I've looked into seven segment reading algorithms and roughly plotted out a way to do it, but it involves quite a bit of homework. Probably nothing I could do as a sidegig. But if anyone was up for it, I'd gladly drop some insights.
In regards to cameras - one could go the way of http://roastlogger.co.uk and decouple the camera input from the program. Roastlogger reads a part of the screen and does OCR on there, so it could be any webcam stream, a recorded video or USB - leaving ultimate freedom to the user

@Koumi460
Copy link

Just randomly came across this thread years later... I'm the developer of Roasted and Logged app. I would have no problem making it open source, but the reason why I have not updated it since 2014 was because I was unhappy with the OCR. It was very primitive and most of the time it didn't work reliably. I tried some other approaches, but never got it to a state where I would be happy with how it works. So I'm afraid my code would be not much help...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

4 participants