An accurate Eye Gaze detection Method Employing Ant Colony Optimizer

This paper addresses the eye gaze estimation problem in low-resolution images, using the low-cost camera in order to eliminate problems caused by using infrared high-resolution imaging such as needing an expensive camera, complex setup, special light sources, and being limited in lab research environments. In the proposed method, the human face is detected with Ant Colony Optimization (ACO) algorithm, then the Kirsch compass mask is utilized to detect the human eye. For iris detection, a novel strategy based on ACO algorithm, which has not been used before, is applied. The pupil is recognized by morphological processing. Finally, the extracted features, obtained from the radius and position of the irises and pupils, are given to the Support Vector Machine classifier to estimate the gaze pointing. Extensive experiments are performed on our created dataset with 90.71% accuracy. The suggested method outperformed the state of the art gaze estimation methods in terms of the robustness and accuracy.

An accurate Eye Gaze detection Method Employing Ant Colony Optimizer Keywords:

Gaze Estimation , Ant Colony Algorithm , Low-Resolution Image , Kirsch Filter , 2D image