Attached a picture of the technical guy on a seat at the theater. As you can see, the seat are quite low, there is a small space in front of the spectator, the light are low.
** Proof of concept **
The scope of this pre-project is to make a "proof of concept" in order to:
- validate the idea (expression recognition capabilities in low light)
- understand the technical requirements for deployment : the needed tablet specifications (camera's quality/resolution, process speed, memory cache, Android version)
- understand technical difficulties (customer and tablet camera's distance, view tilt angle). A solution to this point could be to use an external camera and connect it to the tablet via USB.
The external camera could be more flexible to install.
An example of implementation:
[url removed, login to view]
** Specification **
- An Android application
- We install it and click on the app Icon
- 2 options
1) use of the front camera
2) use of an external camera connected by USB
- It launch the selected camera
- the user position his face (optional?)
- then the app detect the mouth region
That's it !
We try it in the theater in order to see where/how we can best fix the tablet for best use
Once this is validated we go forward to step n°2 : the complete app with backend for which we will create a new project with mockups ecc...