Computer scientists have developed a smartphone app that teaches people the art of taking the perfect selfie. Within the app is an algorithm that guides the user where to hold the camera to take the best shot possible. “Selfies are increasingly becoming a normal way for people to express themselves and their experiences, but not all selfies are created equal,” said the computer science professor. “Unlike other apps that improve a photo after you take it, this system gives direction, meaning the user actually learns why their photo will be better.”
When developing the algorithm, 3D digital scans of “average” people were purchased. They took hundreds of "virtual selfies" by writing codes to control a virtual smartphone camera and computer-generated lighting, allowing them to explore different composition principles, including light direction, face position and face size.
Using an online crowdsourcing service, thousands of people voted on which of the virtual selfie photos they felt best and then the voting patterns were mathematically modeled to develop an algorithm that can guide people to take the best selfie. Later on, real people took selfies with a standard camera app and an app with the algorithm. Based on more online ratings, they found a 26 percent improvement in selfies taken with this (University of Waterloo's) app.
Watch a video here how this app works
