Coming from similar regions as Košice, we figured there are many remote villages with a long ride from bigger grocery and medicine suppliers. Often people living in such areas turn out to be the elderly, who might not be able to drive themselves to the shops everyday. Hence, their children have to go and take them around which might not always be possible, due to work, family etc. On the first thought, an online shopping could be a solution but a lot of people are still not comfortable using it, and more importantly, large vendors like Amazon usually don't even deliver in such areas - at least not for a reasonable price.
What it does
Therefore, we designed a system which allows the elderly (and others) to scan their handwritten shopping lists and automatically issues a delivery order at their preferred supplier. We figured that many people are still not comfortable using smart phones and many don't even own them. That's why we split the app into two components.
One is a small device, powered by the Dragonboard 410c, which can be installed at a local block of flats or some other facility that is very handy for the locals. This device uses facial recognition to identify the user and then allows scanning of the handwritten list and digitalises . It then displays a list and asks for a confirmation.
The second part is a web application that is meant to be used by the vendors. They can manage their orders there, update prices and send SMS receipts to the users to inform them about the price they'll need to pay. The system also maps an efficient root for the vendor to deliver everything.
This way we could help local vendors to participate in a smaller delivery system without having to implement their own APIs which is very costly. By simply creating an account with our web application, they can already start participating.
How we built it
We used Dragonboard 410c and a webcam for the face and list scanning and processing. The web application is build with NodeJs, MongooseDB, and Socket.io.
Challenges we ran into
This was our first ever attempt at creating something with a Dragonboard and it took us some time to get the hang of it. Regardless, we managed to figure it out and we started liking it quite a bit. :D
Accomplishments that we're proud of
We are firstly very proud of making use of the dragonboard and also for having all core components (image scanning, handwriting recognition, face recognition, main server with a webApp) also linked together.