August 2018

MetaGo

MetaGo was a MetaSwitch Networks "Vacathon" (3-day-long hackathon) project with the aim of automating canteen transactions.

First, it identified people by comparing them against a database of company directory pictures. Then, it captured the barcodes of the items they took and charged them the approptiate amount.

The backend used the Django framework with WhiteNoise for serving static files and gunicorn as a WSGI. The code was deployed on Heroku with an AWS server hosting the PostgreSQL database. The libraries we utilised were;

• quaggaJS,
• tracking.js,
• openfoodfacts-python,
• and face_recognition.

The hackthon was concluded by our team of 5 preparing a Pitch Deck and presenting our product to the judges. We won the hackathon.

The project has been described in further detail in my Final Placement Report. The codebase for the project can be seen on GitHub.