Automatic eye detection using intensity filtering and K-means clustering

This paper proposes a novel eye detection method, which can locate the accurate positions of the eyes from frontal face images. The proposed method is robust to pose changes, different facial expressions and illumination variations. Initially, it utilizes image enhancement, Gabor transformation and cluster analysis to extract eye windows. It then localizes the pupil centers by applying two neighborhood operators within the eye windows. Experiments with the color FERET and the LFW (Labeled Face in the Wild) datasets (including a total of 3587 images) are used to evaluate this method. The experimental results demonstrate the consistent robustness and efficiency of the proposed method.