Video Based Eye Blink Analysis For Psychological State Determination

The status of mental health and mood of human beings are well comprehensible by careful observation of movements of different body parts. Eye being the most prominent body part, analysis of different eye parameters such as blink, gaze, opening and closing rate provides important clues on mood status as well as mental health conditions. The present work can be viewed from a statistical and machine learning perspective that utilizes eye blink information to study the mental health status of a person. By using appropriate image processing techniques eye blinks of different subjects were collected through an experimental setup. The setup contained a recording environment where each participant was required to watch two videos of opposite emotions, i.e., joy and sad during different time settings. From the recorded videos of each participant, eye blinks were extracted and investigated. On analyzing the blink rates thoroughly, using statistical and machine learning means we observed; 1) an increase in number of eye blinks when the mood of a participant swings from sad to joy and 2) a significantly smaller number of blinks in depressed participants than the normal participants while in sad mood.