12. Future perspectives: fusion approaches

The material presented in this chapter appears in the literature for first time worldwide. It is actually the first approach worldwide to address drunkenness by means of thermal infrared images of the face of the inspected person. This material was based on a PhD thesis carried out in the Physics Department University of Patras, Greece [39]. The whole material incorporates seven different approaches for feature extraction used for identifying drunk persons. All methods have been presented in scientific journals. The scientific work was based on a wellorganized experimental procedure based on which thermal images of 41 persons were recorded when they were sober and when they were drunk. A well-organized database and the basic routines are available to access the thousands of images recorded (http://www. physics.upatras.gr/sober/).

References

229-243

Lisbon, Portugal; 4–5 April 2013

DOI: 10.1080/00450618.2015.1060522

mal-camera/

(IST 2016); Chania, Crete; 4–6 October 2016

[12] IEEE Spectrum October 2012, Intoxicam. p. 12

Concentration Limits; Washington; 2014

[1] Κoukiou G, Anastassopoulos V. Facial blood vessels activity in drunk persons using thermal infrared. In: Proceedings of the 4th International Conference on Imaging for

Intoxication Identification Using Thermal Imaging http://dx.doi.org/10.5772/intechopen.72128 171

[2] Koukiou G, Anastassopoulos V. Mint: Drunk person identification using thermal infrared images. International Journal of Electronic Security and Digital Forensics (IJESDF). 2012;4:

[3] Κoukiou G, Anastassopoulos V. Face locations suitable drunk persons identification. In: Proceedings of the IEEE International Workshop on Biometrics and Forensics (IWBF 2013);

[4] Κoukiou G, Anastassopoulos V. Eye temperature distribution in drunk persons using thermal imagery. In: Proceedings of the IEEE International Conference of the Biometrics

[5] Koukiou G, Anastassopoulos V. Mint: Neural networks for identifying intoxicated persons. Forensic Science International. 2015;252:69-76. DOI: 10.1016/j.forsciint.2015.04.022

[6] Koukiou G, Anastassopoulos V. Mint: Drunk person screening using eye thermal signatures. Journal of Forensic Sciences. 2016;61:259-264. DOI: 10.1111/1556-4029.12989

[7] Koukiou G, Anastassopoulos V. Mint: Intoxicated person discrimination using infrared signature of facial blood vessels. Australian Journal of Forensic Sciences. 2016;48:326-338.

[8] Κoukiou G, Anastassopoulos V. Drunk person identification using local difference patterns. In: Proceedings of the IEEE International Conference on Imaging Systems & Technology

[9] Koukiou G, Anastassopoulos V. Local difference patterns for drunk person identification. Multimedia Tools and Applications. 2017. pp. 1-13 (in press). DOI: 10.1007/s11042-017-4892-6

[10] Available from: http://phys.org/news/2012-09-thermal-imaging-camera-scans-drunks.html [11] Available from: http://www.cbsnews.om/8301-205\_162-57505875/drunks-detected-by-ther

[13] Wu YC, Xia YQ, Xie P, Ji XW. The design of an automotive anti-drunk driving system to guarantee the uniqueness of driver. In: Proceedings of the International Conference on Information Engineering and Computer Science (ICIECS 2009); December 2009. pp. 1-4

[14] International Center of Alcohol Policies. ICAP Blue Book, Module 16: Blood Alcohol

[15] Jones AW. The Relationship between Blood Alcohol Concentration (BAC) and Breath Alcohol Concentration (BrAC): A Review of the Evidence. London: Department of Forensic

Special Interest Group (BIOSIG 2013); Darmstadt, Germany; 4–6 September 2013

Crime Detection and Prevention (ICDP-11); Kingston, GB; 3–4 November 2011

All seven methods analyzed present high drunk identification success which is over 80%. It is expected that combining all this information into a unified identification procedure, the success rate will approach 100%. This requires sophisticated information fusion techniques which will employ combination of different kind of information. Work is currently carried out on this interesting topic. An important aspect toward completing this task is to elaborate on the correlation properties of the different features information extracted from the seven methods. In practice, an electronic system incorporating a thermal infrared camera can embody one of the proposed methods and point out to the police to whom an extended inspection for alcohol consumption is due.

The presented methodologies have found great recognition and publicity from the scientific community and the media [10–13].

The main advantages of these methods are as follow:

