Hello everyone, I am trying to make something that will help my brother. Long story short, he has a lazy eye. He can correct it when he realizes the eyes deviates, but obviously he cannot think about it every second of the day.
What I want to do is put two small cameras in a pair of glasses, so they can detect when one eye deviates from the other. I would like the trigger of detection something like a small red light turn on (that he can see, of course) when there is deviation.

I imagine this will is a fairly simply project, with the only real obstacle being the programming. It will essentially need to...
1) Identify the pupil in each eye. Deal with issues like glare, different lighting conditions, shadows, blinking, crying at sad movies, etc.
2) Determine where each of those pupils is 'aimed'
3) Determine if the axis of one pupil is skewed from the other axis of the cameras

I need to know the hardware necessary (Type of chip for the programming, type of cameras, battery, etc.),
The software to program the recognition of eye deviation (and how to program it onto a chip),
And how to connect all of these components.

Clearly, I don’t know much about electronics, but I will be researching all of this so I am not just blindly following instructions. I just need help with the basic information to point me in the right direction.

Please feel free to send me an email at Lucassteele101@hotmail.com
Thank you all in advance!

 

The hardware may not be too difficult (although far from easy) but I'm sure the software (the real obstacle as you call it) is as far away from simple as you can get?

 

I've done object tracking on three platforms, it's a mighty job for an individual,
and a small computer, and fitting it into something that portable, but good luck.

I have considered following the pupil with the front facing camera of an iPhone.
I currently have a game in the App Store that uses the rear facing camera to track
a laser pointer on the wall to control the game.

 

I've dealt with similar left/right muscular control problems when I was a bodybuilding trainer.

You shouldn't need an external feedback device as the eye itself is a feedback device.

Try a black eyepatch (Pirate style) and rotate it from left eye to right eye every hour during the day. That will bring about a neuromuscular reprogramming where the brain will start to equally favour each eye, instead of the habitual eye.

 

Paul and art: I have clearly overstated the simplicity. Considering that the chip will need to handle the jobs of:1) Identify the pupil in each eye. Deal with issues like glare, different lighting conditions, shadows, blinking, crying at sad movies, etc.
2) Determine where each of those pupils is 'aimed'
3) Determine if the axis of one pupil is skewed from the other axis of the cameras
It is a daunting task at best. But I still believe it is possible, especially considering the embedded microcontrollers out on the market today.
RB: Although in theory you are right, my brothers condition is very different. It's not a matter of strength between the eye muscles, but the two eyes working together. He has alternating exotropia which means either of the eyes could be deviating.
Also, I doubt anyone is willing to wear an eye patch in public.
Thanks for the replies everyone!

 

There are problems when the lighting changes or the camera focuses
(in the case of auto focus camera, you have to turn it off).
When the focus changes, the colours you're looking for also change.

 

Sunglasses stacked with LCD switched blackout lenses. There are LCD lens for Welding, that might work?

Alternate turning each lens completely dark about every 3 to 5 seconds for about 1.5 seconds.

Any dissimilarity of focal points should resolve.

 

a wonderful idea. i would use two miniature cameras and a small FPGA but it will take some hard work to make it ready. i would suggest to talk to universities and ask them to promote the idea to students as a capstone project. it is something that would not only demonstrate the skill but also open many doors and - make something that is actually helpful

 

I imagine this will is a fairly simply project...

This is doable but far from simple. Image pattern recognition is not a simple task that can be accomplished on your everyday run-of-the-mill microcontroller.