A Candy Dispenser using Android Things + TensorFlow Lite + Mobilenet
The Android Things A.I Candy Dispenser it's a demonstration of how to create a “smart” candy machine. The device have a game that ask the user for a specific thing like a Bird, Dog ou Cat and the user should show a photo of that thing in the predefined time to win candies.
This project uses a button to interact with the user, obtains images via a camera peripheral and a modified electric candy dispenser being controlled by a GPIO with a transistor.
When the user start the game, the device takes pictures in sequence and processes each one using Tensorflow and MobileNet neural network, which classifies each image. This info is used by the device to see if it matches what it requested. When we have a match, the motor of the candy machine is activated to give the user the prize.
All users interface is presented in a Serial i2C 20x4 Display.
To run the app
module on an Android Things board:
app
module