Investigating the impact of drug induced pupil dilation on automated iris recognition

Recent research has demonstrated the negative impact of pupil dilation on iris recognition performance. Apart from light intensity changes, several factors such as alcohol, drugs, age, disease and psychology, are known to affect the size of the pupil. This work (1) analyzes the impact of drugs on pupil dilation, (2) proposes the use of a biomechanical nonlinear iris normalization scheme along with key point-based feature matching for mitigating the impact of drug-induced pupil dilation on iris recognition, and (3) investigates differences between drug-induced and light-induced pupil dilation on iris recognition performance. Experimental results indicate performance improvement when nonlinear normalization is used along with key point-based feature encoding for matching iris images with large differences in pupil size.