Review of Feature Extraction on Video-Oculography (VOG) and Electro-Oculography (EOG) Signals

Eye tracking is used to observe where users are looking, how long they are looking, and what order they are looking. Eye tracking has been widely used in various fields such as helping people with disabilities by using Electro-Oculography (EOG) and analyzing eye movements signal in vestibular patients by using Video-Oculography (VOG). The human eye has a cornea and retina that are located between the front and back of the human eye. Eye movement signal analysis is a necessary step prior to eye movement classification. Selecting a model and tuning the feature extraction algorithm on eye movements are tasks that researchers continue to optimize. However, there are very few studies investigating various feature extraction methods in VOG and EOG signals. To solve this research gap, this paper systematically describes feature extraction that is suitable for use in VOG and EOG signal analysis. Three main factors are important to be considered when choosing a feature extraction method: (1) classification, (2) filters and amplifiers, and (3) dataset characteristics. The results of this literature review can be used as a reference for developing feature extraction algorithms for EOG and VOG applications.