摘要：The aim of this study was to automatically identify the iris and pupil of the eye in the video stream and to parameterize the identified structures in order to make assumptions if the subjected is stressed or not. During tests subjects were given a number of issues which they had to respond by selecting only one correct answer. Visual material was gathered using a helmet-fitted stationary near-infrared camera that recorded iris and pupil of the eye reactions to stimuli. Subsequently it was made an automatic iris and pupil recognition and approximation by curves in the gathered sequence of images. Each change in the pupil size is described by different time series length. Thus, it is impossible to compare the obtained data using the Euclidean distance measures. For this reason, the metrics based on periodograms was used to compare the data series. The differences calculated between the eye pupil reaction to stimuli and question show-up time was introduced in multidimensional scaling algorithms for dimension reduction. It was noticed that the stimulus to the false answers tend to cluster.
关键词：real-time iris and pupil parameterization;time series analysis;reaction to stimuli;stress detection
