Facial recognition using visible light is one thing, doing it the dark using infrared images is something else entirely. Facial recognition technology has progressed immensely in the last few years, with everything from apps to smartphones now packing some impressive tech, but recognizing people’s faces in the dark has always been very difficult. However, thank to a group of German researchers, this may no longer be an issue.
Matching an infrared image of a face to its visible light counterpart is a difficult task, but one that deep neural networks are now coming to grips with. One problem with infrared surveillance videos or infrared CCTV images is that it is hard to recognize the people in them. Faces look different in the infrared and matching these images to their normal appearance is a significant unsolved challenge. The problem is that the link between the way people look in infrared and visible light is highly nonlinear. This is particularly tricky for footage taken in the mid- and far-infrared, which tends to use passive sensors that detect emitted light rather than the reflected variety. Today, Saquib Sarfraz and Rainer Stiefelhagen at the Karlsruhe Institute of Technology in Germany say they’ve worked out how to connect a mid- or far-infrared image of a face with its visible light counterpart for the first time. The trick they’ve perfected is to teach a neural network to do all the work.