Real Time Detection of Eye Corners and Iris Center from Images Acquired by Usual Camera

A precise iris center and eye corners detection algorithm for gaze tracking is proposed. The work is based on the common Web camera under the natural light condition instead of the infrared illumination. The algorithm includes two parts. Firstly, the face region is detected by Adaboost method, Active Appearance Models is used to locate the rough area of the eyes. Secondly, an improved local integral algorithm based on Ahlberg´s method is proposed to locate the iris center and eye corners in the eye region. The features in a blink image are estimated by comparing with the consecutive images. This method provides a potential application in the gaze based aids tools for disabled people like the cerebral palsy.