Spanish researchers sniff out an emerging biometric modality
Researchers at the Universidad Politécnica de Madrid, along with the Ilía Sistemas company, are currently developing a new biometric modality that’s existed in the animal kingdom long before now: body odor.
The research of the Group of Biometrics, Biosignals and Security (GB2S) of the Universidad Politécnica de Madrid (UPM) in collaboration with Ilía Sistemas SL has found that there are recognizable patterns of each person’s body odor that remain steady, which allows for identification with 85% accuracy.
The researchers are also quick to point out that there is no criminal stigma attached to body odor identification, as there is to fingerprints and the nature of this kind of sensing could be quite uninvasive. “Identification could be at the same time when crossing the system stall,” the researchers say of a potential B.O. –sensing system installed somewhere like a train station or airport.
Body odor can vary considerably, but the research carried out by the group of the GB2S of the UPM showed that during the analysis of 13 people in 28 sessions, recognizable patterns in BO make identification possible with an rate error of 15%.
Sensors designed to smell people are increasingly sophisticated, but still can’t hold up to the accuracy of a dog. That being said, a system developed by the Ilí Sistemas SL company used in the trials, “has a high sensitivity to detect volatile elements present in body odor.”
Developers are increasingly looking to other quantifiable measures for biometric identification, and body odor isn’t the only modality in development that’s outside the traditional tool chest of the biometrics community.
Almost along the same lines as BO recognition, Swiss researchers have discovered a way to identify humans by the composition of their breath.
Rawlson King, contributing editor at BiometricUpdate.com, recently wrote “Make Way For Knobbly Kneed ID… Or Who’s This Ear?“, an article about other unlikely measures of identity such as knees and ears, and how they could soon rival fingerprints as personal identification