Greek researchers have developed software to analyze images from thermal imaging cameras to objectively determine whether a person has consumed an excessive amount of alcohol.
Georgia Koukiou and Vassilis Anastassopoulos of the Electronics Laboratory at the University of Patras (Rio,Greece) have devised two algorithms that can determine whether a person has been drinking alcohol to excess by analyzing infrared thermal images of the person's face.
The first algorithm measures pixel values of specific points on the person's face, which are 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 used to classify whether an individual is drunk or sober.
The second algorithm assesses the thermal differences between various locations on the face. Using the approach, the researchers found that increased thermal illumination is common in the noses of inebriated people whereas their foreheads tend to be cooler. The advantage of the second technique is that no thermal image of the sober person is needed to determine whether the individual has been drinking.
Working together, the researchers say that the two techniques could be used to quickly scan individuals entering public premises or attempting to buy alcohol while inebriated.
The researchers presented the results of their work in the International Journal of Electronic Security and Digital Forensics in a paper entitled "Drunk person identification using thermal infrared images."
Recent articles from Vision Systems Design on thermal imaging that you might also be interested in.
A Swedish company has developed a system for automatically monitoring the health of dairy cows using thermal imaging cameras from FLIR (Portland, OR, USA).
Scientists from Loma Linda and Asuza Pacific Universities have employed thermal imaging to help in quantifying muscle soreness.
Scientists at Nottingham University (Nottingham, UK) are using thermal imaging to determine the amount of brown adipose tissue in the human body.
-- Dave Wilson, Senior Editor, Vision Systems Design