Drunk person identification using local difference patterns
Γεωργία Κούκιου, V. Anastassopoulos · 2016
In this work, facial thermal infrared images are employed for intoxicated person discrimination. Specifically, the region of the forehead of the face of the sober and the intoxicated person are used to test if the employed local difference patterns can result into discriminative features. For an intoxicated person, vessels on the forehead become more active so that the intensity of the pixels in this region is modified accordingly. The behavior of the local difference patterns for a drunk person is different than that of a sober one and accordingly drunkenness can be ascertained by only using the thermal infrared image of the intoxicated person. The proposed method can be incorporated into a non-invasive inspection system used by the police as a first step for intoxicated person detection. The identification success of the used simple local difference pattern is over 85 per cent while other simple difference patterns are currently tested in order to improve the performance of the approach. The 40 participants in the experiment have contributed to the creation of the unique sober-drunk database which is available on the web and contains over 4.000 images.