Camera overlay with rectangle detection (potential job too)

Solar2D General Questions/Discussion
#1

Hi all,

I’m sure many of you have seen “scanner” apps where you can point your camera at a sheet of paper and it will detect rectangles (and hopefully the sheet of paper), thereby when you take a picture it can crop the image and remove any unwanted background areas around the paper.

Now I’m looking into how I might be able to achieve this with Corona.

Does anyone have a clue where I should begin?

From Googling around a bit It seems a few years ago there was a blog post that described functionality for live on-screen camera overlays (the original url was https://coronalabs.com/blog/2013/12/19/holiday-surpril-time-effects/ ) but that’s long since vanished it would seem.

Since I can’t seem to find much in the forums or Google, and there doesn’t appear to be any documentation for any camera overlays, and certainly nothing like rectangle detection, I’m rather stuck.

So, has anyone done anything similar, or even something like face recognition? That way I’m sure I could adapt for rectangles. Or if there’s someone that thinks they could put something together, please hit me up. I’d be happy to discuss this as a paid job.

Many thanks,

#2

To give you an example of what I’m looking to achieve, something like this ideally:

https://itunes.apple.com/us/app/docscan-free/id1037744487?mt=8

#3

We made a Google Vision plugin which might be able to do help with this:

https://marketplace.coronalabs.com/corona-plugins/google-vision

It picks up various objects that it finds within an image, and the coordinates etc of where the object lies within the image. So I think it would probably be able to do a large part of the work that you are after.

We’re in the process of migrating our website so the docs link doesn’t lead anywhere at the moment, but I’ll PM you a copy of them.  

#4

Thanks Alan,

Looking forwards to reading through them.

Paul

#5

To give you an example of what I’m looking to achieve, something like this ideally:

https://itunes.apple.com/us/app/docscan-free/id1037744487?mt=8

#6

We made a Google Vision plugin which might be able to do help with this:

https://marketplace.coronalabs.com/corona-plugins/google-vision

It picks up various objects that it finds within an image, and the coordinates etc of where the object lies within the image. So I think it would probably be able to do a large part of the work that you are after.

We’re in the process of migrating our website so the docs link doesn’t lead anywhere at the moment, but I’ll PM you a copy of them.  

#7

Thanks Alan,

Looking forwards to reading through them.

Paul