One day soon, your mobile game may be able to register your joy, anger and frustration thanks to a creepily accurate webcam algorithm.
Developed by Vietnamese computer scientists Nhan Thi Cao and An Hoa Ton-That of Vietnam National University in Ho Chi Minh City and Korean computer scientist Hyung-Il Choi of Seoul's School of Media at Soongsil University, the algorithm allows video games to read their players' emotions, reports TechRadar.
By using mathematical processing, the trio's invention analyzes everything from a person's mouth shape and eyebrow position to the openness of a player's eyes to determine which emotion a game elicits. Even with low-resolution images, the algorithm can distinguish between anger, joy, disgust, fear, sadness, surprise and a neutral facial expression.
According to the creators themselves, when tested on two sets of facial images, achieved an accuracy of 96.3% and 99.85%. In future, the invention could be used to help video games adapt to their players.
[Photo via What - When - How]
