Cyclops is a facial recognition tool we have built that caters to people with motor neuron disease who cannot move any part of their body, and enables them to browse through webpages. Cyclops is a google chrome extension which uses a webcam to record the user. Then extension then uses a https request to send the webcam data across to a server which interacts with Python. Here Python uses Open CV and DeLib to use facial recognition to identify the eye and the pupil/or closed eye. This movements of the eye are tracked and used as a tracker to enable the user to browse through the web without having to use a mouse. The challenges we ran into were firstly it was difficult to get Python to isolate the eye. We used a combination of threshold intensity and Bayesian Statistics to solve this problem. Accomplishments we are proud of are that majority of the team are first time newcomers and we have accomplished a tough challenge. We have picked up new skills such as using Open CV, JavaScript and HTML in a short period of time.
We would like to develop Cyclops further to polish up the technology so it caters for a wider variety of eye colours and to a higher precision eventually finding multiple uses for the software throughout the health industry.
Log in or sign up for Devpost to join the conversation.