We wanted to work with computer vision and we got inspired by CapitalOne's mission of humanising finance.
What it does
It allows for a frictionless and more secure payment experience on e-commerce websites
How we built it
In order to demonstrate our solution we needed to have our API working on a sample. Therefore we worked on the API an a mock website (Based on a superhero theme!!!). In order to achieve this, we split up into two groups. One was in charge of developing the backend part and the other one the frontend. To start, we sourced some code from the web to use it as a foundation for our API.
Challenges we ran into
The most difficult part was to have the website to POST captured picture to our backend for usage in our main function
Accomplishments that we're proud of
We have been able to implement a button that requests user to capture a selfie from his webcam. The picture is then properly decoded and returned as an argument for our image-comparison function which in the end routes you to the "Transaction Declined" or "Transaction Approved" webpages.
What we learned
What's next for FlashPay
Better integration with websites, development of a scalable solution for big databases, improvement of our face-recognition function through computer vision libraries, better storage of users' accounts and images