A comparative analysis of deep learning algorithms in eye gaze estimation

Abstract

Eye tracking is the procedure of keeping track of one’s point of gaze. Researchers have proposed a range of algorithms and methods to automatically track the gaze direction and position, which can be beneficial in a number of applications. Eye tracking is growing in popularity due to its ability to make a range of activities simpler, especially for the elderly or people with special needs. This research intends to investigate and review eye tracking methodologies by focusing on modern approaches such as machine learning and deep learning for gaze detection. This paper provides a quick overview of gaze tracking based upon appearance of eye images and model based approaches. Different mapping functions are mostly used for calculating gaze points. The findings of this study indicates that when compared with machine learning algorithms for estimating gaze points, deep learning techniques produce more accurate results in gaze detection from images captured using camera. Finally, some potential applications of gaze tracking are discussed.