How many photos of you are on your phone right now? Proportionally, majority of them, right? And most of them must be self-portraits aka “selfies”. If you are a selfie lover, well here is something exciting just for you.
Let’s take a look at how many pictures we human beings take each day – almost 1 trillion photographs a year! That means we take more photos taken within every few minutes than taken in the ENTIRE 19th century – crazy stats! Considering the generic ration, majority of them are selfies, and I am not just saying it; because there are nearly 300 million images on just Instagram which are tagged as #selfie – not even counting any other tag, tag-less selfies and social media.
Considering the increasing number of selfie maniacs, and even more, the level of risks they take to get that perfect selfie, researchers at University of Waterloo have developed a scientifically engineered mobile application to master the art of taking perfect selfies, each time. The application is integrated with an algorithm which directs the user where to position the camera, allowing them to take the best shot possible.
But the development of algorithm was no piece of cake – Vogel and Qifan Li of Waterloo Uni bought 3D digital scans of “average” looking people. They took hundreds of “virtual selfies” by writing code to control a virtual smartphone camera and computer-generated lighting which allowed them to explore different composition principles, including lighting direction, face position and face size. Using an online crowd-sourcing service, the researchers had thousands of people vote on which of the virtual selfie photos they felt were best, and then mathematically modelled the patterns of votes to develop an algorithm that can guide people to take the best selfie.
When tested practically, the application gave 26% better results and the developers say that this can be expanded with other variable aspects like hairstyles, smile, makeup and even outfits! But we will just have to wait for “Guided Selfies” to launch on the app stores for installation.