Researchers say your body odor should be your new ID

Friday, February 14, 2014 by: J. D. Heyes
Tags: body odor, personal ID, biometrics

(NaturalNews) Ever share a cab, an elevator or some other small space with someone who has an odor? Well, in the near future, our body odor will not need to be quite that pungent in order for us to be identified through technology. Just a hint of a smell will do.

At least, that is what researchers at Universidad Politecnica de Madrid, along with the Ilia Sistemas company, are hoping. They are making progress on the development of a brand-new biometric technology that would allow some sort of device to identify us based on our personal odor.

Less accurate, for now

According to the research website Phys.org:

The research of the Group of Biometrics, Biosignals and Security (GB2S) of the Universidad Politecnica de Madrid (UPM) in collaboration with Ilia Sistemas SL unveils that there are recognizable patterns of each person's body odor that remain steady. Therefore, every person has his/hers [sic] own odor and this would allow his/her identification within a group of people at an accurate rate higher than 85%. This result leads the way to improve personal identification that is less aggressive than other biometric techniques being used today.

Less aggressive, sure, but less accurate as well.

Nevertheless, the researchers note that, most often today, our identities are verified at most border checkpoints or airports based on physical resemblance to our government-issued ID card or passport photo. Even though new electronic passports are pretty tough to copy or forge, the use of biometric techniques based on someone's physical features would nonetheless bolster security and effectiveness of control checkpoints.

Other more commonly used biometrics like eye and fingerprint scans have low rates of error. But these techniques are often tied to criminal records, and because of that, when a person is required to identify himself, he or she may not always want to cooperate.

"On the other hand," says Phys.org, "other recognized biometric techniques like the face recognition have a high error rate. Therefore, the development of new sensors that allow the capture of body odor can provide a less aggressive solution because the identification could be at the same time when crossing the system stall."

Not as good as a bloodhound - yet

Using body odor to help identify people is not a new concept. Police departments, for example, have keyed in on scent to locate missing persons or escapees, using specially trained dogs like bloodhounds. These dogs are marvels; they are able to follow the trail of a person after whiffing a sample of something that contains body odor, like a piece of clothing, and can then track that person for dozens of miles, often through onerous weather conditions.

And while sensors developed thus far do not have the ability to sense smell, researchers at Ilia Sistemas have developed a system which has a greater capability to detect volatile elements that are present in body odor:

Body odor can vary considerably by actions such as diseases, diet changes or even the mood swings. However, the research carried out by the group of the GB2S of the UPM showed that, the analysis of a group of 13 people during 28 sessions have proven that recognizable patterns on each person body odor have an identification at rate error of 15%. This successful experiment and result confirms that odor biometric system as a novel technique with an enormous potential.

Though current research was conducted within the framework of the Emocion Proyect, which is focused on citizen safety, body odor analysis can nonetheless be utilized in a number of other fields, Phys.org said. GB2S is collaborating with the Hospital Infanta Sofia, Ilia Sistemas and SEADM SL (European Society of Differential Mobility Analysis) on research involving projects that are capable of using blood and breath characteristics to detect diseases, like early signs of colon cancer and leukemia.

Sources:

http://www.theverge.com

http://phys.org

http://www.zdnet.com