Understanding Cognitive and Affective States Using Eyelid Movements

Biometrics related to the eye region are of particular interest in a range of applications -from identification to adaptive interfaces. This paper describes a technique for monitoring dynamic eye region biometrics (i.e., blinking) as unique indicators of cognitive and affective states in subjects involved in HCI scenarios. We integrate a novel collection of robust, minimally-intrusive computer vision techniques for effective interpretation of eye blink behaviors using color video, including k-means clustering for learning, histograms and normal flow fields for steady-state and transitional tracking, and a deterministic finite state machine for state analysis. Sample results that illustrate the application of our approach are presented.