Every millennial has probably taken at least one selfie in their life, and sometimes the best way to get good selfies is to know which angle makes you look best. That’s why computer scientists from the University of Waterloo have created a smartphone app that helps people learn how to take awesome selfies. The app contains an algorithm that directs the user where they should position the camera so that they will be able to take the best shot possible.
Source: YouTube, Daniel Vogel
According to Dan Vogel, a professor of computer science at Waterloo, “Selfie’s have increasingly become a normal way for people to express themselves and their experiences, only not all selfies are created equal. Unlike other apps that enhance a photo after you take it, this system gives direction, meaning the user is actually learning why their photo will be better.”
Vogel and Qifan Li, a former Master’s student at Waterloo, bought 3D digital scans of “average” looking people when they were developing the algorithm. They took hundreds of “virtual selfies” by writing code to control a virtual smartphone camera and computer-generated lighting. This allowed them to explore different composition principles which include lighting direction, face position and face size.
By using an online crowdsourcing service, the researchers asked help from thousands of people to vote on which of the virtual selfie photos they felt were best, and then mathematically modelled the patterns of votes to create an algorithm that can guide people to take the best selfie.
Later, they then had real people take selfies with a standard camera app, and an app that is powered by the algorithm. They found a 26% improvement in selfies taken with Waterloo’s app based on more online ratings.
“This is just the beginning of what is possible,” Vogel said. “We can expand the variables to include variables aspects such as hairstyle, types of smile or even the outfit you wear.