A STUDY OF IRIS RECOGNITION SYSTEM IN THE CONTEXT OF ALCOHOL CONSUMPTION

Abstract

Iris recognition is one of the important methods used to recognize cooperative subjects in controlled environments. With the advent in the technology & low cost iris scanners, this biometric method is being used in varied application areas and also poses new challenges. This paper investigates one of such challenges, namely matching iris images captured before and after alcohol consumption. Due to alcohol consumption, the pupil dilates/constricts which causes deformation in iris pattern, possibly affecting iris recognition performance. The experiments performed on some standard databases show that in matching pre and post alcohol consumption images, the overlap between genuine and impostor match score distributions increases by approximately 20%. This suggests that about one in five subjects under alcohol influence may be able to evade identification by iris recognition.