Want to take the perfect selfie? Now, thanks to computer scientists from the University of Waterloo, there is an app to do just that.
The app instructs the user, using an algorithm, where to position the smartphone camera for the best possible selfie results.
"Selfie's have increasingly become a normal way for people to express themselves and their experiences, only not all selfies are created equal," said Dan Vogel, a professor of computer science at Waterloo. "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."
To develop the algorithm, the researchers obtained 3D digital scans of “average” looking people and took hundreds of “virtual selfies.” Factors, such as face position, face size and lighting direction were controlled by code.
The researchers shared the “virtual selfie” results using an online crowdsourcing service where thousands of people were asked to vote on what selfies were best. Taking those results and mathematically modelling the pattern of votes, the researchers were able to develop the algorithm.
Later, researchers asked real participants to take selfies using both the Waterloo app and a standard camera app. After another online vote, researchers found a 26 percent improvement in selfies photographed with the app powered by the algorithm.
This is just the beginning of what is possible," said Vogel. "We can expand the variables to include variables aspects such as hairstyle, types of smile or even the outfit you wear.
"When it comes to teaching people to take better selfies, the sky's the limit."
The computer scientists recently presented the app at the 2017 ACM Conference on Designing Interactive Systems held in Edinburgh, Scotland.