Reliable high speed iris detection for video based eye tracking systems

Automatic tracking of eyes is a challenging task, with numerous applications in biometrics, security, intelligent human-computer interfaces, and driver's drowsiness detection systems. Eye localization and extraction is, therefore, the first step in approaching such problems. In this paper, a novel approach for high speed iris detection is introduced. The paper proposes to detect iris based on arc separation and circle detection. The new algorithm is more accurate and flexible in addition to its high speed. The key feature of this approach is a new circle detection algorithm. The circle detection is done by something similar to curve fitting or solving an over determined system.