International Journal of Advanced Research in Computer and Communication Engineering

A monthly peer-reviewed online and print journal

ISSN Online 2278-1021
ISSN Print 2319-5940

Abstract: Drunk person identification is carried out using thermal infrared images. Two different methods for  identifying drunk person face. The features used in first method are simply the pixel values of specific points on the face. It is proved that  cluster of a specific person moves in the feature space as the person consumes alcohol. The Fisher linear discriminate approach is used for space dimensionality reduction. In feature, space is found to be of very low dimensionality. The majority of the clusters moves towards the same direction, which can be easily  separated into the ‘sober’ and ‘drunk’ regions. The ‘drunk’ feature space is introduced. The second method is thermal differences between various locations on the face are evaluated. It identify that specific areas in the face of a drunk person present an increased thermal evaluation. These best approach for identifying a drunk person. The concept behind this second proposed method relies on a physiology-based face identification procedure.

Keyword: Biometrics, Thermal Infrared Signatures, Drunk Person Verification.


PDF | DOI: 10.17148/IJARCCE.2018.7535