As anyone who has used the interwebs knows, one of the appeals of the Internet is anonymity. But one researcher is trying to ruin it for everyone (well, maybe just criminals) by actually fusing a person’s real biometrics with his or her 3D avatar.
Sound far-fetched? Well, it kinda is. But it’s a project that came about because of a rise in virtual crime—and an increased likelihood that it will be investigated. In fact, Japanese police have arrested virtual muggers, and the FBI has investigated Second Life casinos’ dealings.
Computer scientist Roman Yampolskiy is leading the charge against virtual crimes. Already, multinational defense firm Raytheon has a patent pending on fusing a person's real biometrics with their 3D avatar. That would let you know for sure who you are speaking to online.
Yampolskiy and co. at the Cyber-Security Lab at the University of Louisville are taking the idea even further: They’re developing the field of artificial biometrics, known as "artimetrics." Much like human biometrics, artimetrics could be referenced to “authenticate and identify non-biological agents such as avatars, physical robots or even chatbots.”
When virtual worlds run on peer-to-peer networks, Yampolskiy explains, there’s no central authority to enable police to investigate virtual crime. That’s where artimetrics come in, New Scientist explains:
Yampolskiy and colleagues have developed facial recognition techniques specifically tailored to avatars, since current algorithms only work on humans. "Not all avatars are human looking, and even with those that are humanoid there is a huge diversity of colour," Yampolskiy says, so his software uses those colors to improve avatar recognition.
The team also investigated matching a human face to an avatar generated from that face; previous studies show that avatars often resemble their owners. Combining their color-based technique with existing facial recognition software produced the best results, suggesting it might be possible to track someone between the physical and virtual worlds.
Next up, Yampolskiy wants to create recognition algorithms for robots as well. Since autonomous robots might one day become ubiquitous, he says, they’ll eventually require identification of their own, distinct from humans.