Human Sense
Team IMAGE
The « Human Sense » demonstrator presents a use of deep learning in computer vision.
From a video stream, pre-trained neural networks automatically estimate several biometric informations for the people present.
This include :
- -The face, its key points and its emotion
- -The age and the gender
- -The skeleton of the body and of the hands
This demonstrator uses the TensorFlowJS technology.
Contributor
Olivier Lézoray