Automatic detection of gaze direction for NLP applications

Abstract

This paper proposes a solution for detecting the Eye Accessing Cue (EAC) model used in Neuro-Linguistic Programming based on the position of the eye center inside the bounding box of the eye. The eye points are determined using an iris center detection method based on the curvature of the isophote and a facial points detection method based on graph models. The distribution of luminance is analyzed inside the bounding box and added as an extra feature to increase the detection rate. This paper also introduces a new database with manual markings used for testing the EAC detection as generated by various classifiers.