A novel method for pupil diameter measurement based on fuzzy techniques

This paper proposes a fuzzy-based algorithm for measurement of the pupil diameter (PD) from the pupil video. The proposed algorithm consists of four stages: data acquisition, preprocessing, edge detection, and calculation of PD. In this algorithm the effective procedure for edge detection is presented based on the hybrid combination of interval type-2 fuzzy logic system (IT2FS) and genetic algorithm (GA) wherein GA is used for parameters optimization of IT2FS membership function, to adjust the amplitude of the upper bound of the IT2FS so as to improve the behavior of the IT2FS in edge detector. In order to evaluate the performance of the proposed algorithm, a pupil videos dataset is constructed. The proposed algorithm is tested on this dataset. The experimental results show that the IT2FS has great potential for edge detection and the proposed algorithm for the PD measurement is promising.