Facial feature extraction is an important step in automated visual interpretation and human face recognition. Among the facial features, the eyes play the most important part in the recognition process. This paper describes algorithms for facial feature extraction such as iris center and radius, eye corner and contour. The eye windows (rough eye regions) are assumed to be known. The proposed technique work fast, stably and exactly. Applied to the test sequences of eyes, the facial features are estimated with subjectively high accuracy.