Thermal imaging camera scans for drunks

September 4, 2012

Thermal imaging technology might one day be to identify drunks before they become a nuisance in bars, airports or other public spaces. Georgia Koukiou and Vassilis Anastassopoulos of the Electronics Laboratory, at University of Patras, Greece, are developing software that can objectively determine whether a person has consumed an excessive amount of alcohol based solely on the relative temperature of different parts of the person's face.

Writing in the International Journal and Digital Forensics, the team explains how such a system sidesteps the subjective judgements one might make based on behaviour and so allow law enforcement and other authorities to have definitive evidence of inebriation.

The team explains how they have devised two algorithms that can determine whether a person has been to excess based on of the person's face. The first approach simply involves measuring pixel values of specific points on the person's face, which are the compared to values in a database of scans of sober and inebriated people. Given that alcohol causes dilation of blood vessels in the surface of the skin hot spots on the face can be seen in the thermal imaging scans, which can be classified as drunk or sober regions. Similar technology has been used at international borders and elsewhere to ascertain whether a person was infected with a virus, such as flu or SARS.

In their second approach, the team assesses the thermal differences between various locations on the face and evaluates their overall values. They found that increased thermal illumination is commonly seen in the nose in an inebriated individual whereas the forehead tends to be cooler. This second system relies on the algorithm "understanding" what different parts of the face are present in the thermal image. The two techniques working in parallel could be used to quickly scan individuals entering public premises or attempting to buy more alcohol, for instance. The team points out, however, that the second technique does not need a thermal image of the sober person to determine whether that individual has been drinking.

Explore further: How thermal-imaging cameras can spot flu fevers

More information: "Drunk person identification using thermal infrared images" in Int. J. Electronic Security and Digital Forensics, 2012, 4, 229-243

Related Stories

How thermal-imaging cameras can spot flu fevers

May 1, 2009

(AP) -- To screen passengers for swine flu and other contagious diseases, some airports use thermal imaging cameras to see whether travelers have fevers, without having to stick thermometers in their mouths. So how do the ...

Everyone looks the same - when you drink

March 19, 2010

(PhysOrg.com) -- People are much better at recognising faces of their own racial group than those of different races, but a new study suggests that drinking alcohol almost eliminates that bias.

Recommended for you

For these 'cyborgs', keys are so yesterday

September 4, 2015

Punching in security codes to deactivate the alarm at his store became a thing of the past for Jowan Oesterlund when he implanted a chip into his hand about 18 months ago.

How to curb emissions? Put a price on carbon

September 3, 2015

Literally putting a price on carbon pollution and other greenhouse gasses is the best approach for nurturing the rapid growth of renewable energy and reducing emissions.

Magnetic fields provide a new way to communicate wirelessly

September 1, 2015

Electrical engineers at the University of California, San Diego demonstrated a new wireless communication technique that works by sending magnetic signals through the human body. The new technology could offer a lower power ...

1 comment

Adjust slider to filter visible comments by rank

Display comments: newest first

NOM
3 / 5 (2) Sep 04, 2012
So they want to exclude people by the colour (in infrared) of their face.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.