Washington: Scientists have developed a face recognition method that works in utter darkness, an advance that may lead to improved surveillance and security technology.
Saquib Sarfraz and Rainer Stiefelhagen from Germany created a system that analyses dozens of infrared images of a person’s face and compares them to dozens of images taken in daylight.
The comparisons are made through a computer programme that works using a so-called deep neural network system designed to imitate the function of a human brain.
The researchers said the deep neural network analysed 4,585 images taken in both infrared and visible light, and was able to establish a match in just 35 milliseconds. “The presented approach improves the state-of-the-art by more than 10 per cent,” Sarfraz and Stiefelhagen told MIT Technology Review.
