Human Emotion Recognition and Gaze Detection

日期 : Jun 2018 - Jun 2019

<p>Facial expression analysis has been attracting considerable attention in the advancement of human machine interface since it provides a natural and efficient way to communicate between humans. Some application areas related to face and its expressions include personal identification and access control, video phone and tele-conferencing, forensic applications, human-computer interaction, automated surveillance, cosmetology, and so on. But the performance of the face detection certainly affects the performance of all the applications. Many methods have been proposed to detect human face in images, they can be classified into four categories: knowledge-based methods, feature-based methods, template based methods and appearance-based methods. When used separately, these methods cannot solve all the problems of face detection like pose, expression, orientation, occlusion. Hence it is better to operate with several successive or parallel methods. Most of the facial expression recognition methods reported to date are focused on recognition of six primary expression categories such as: happiness, sadness, fear, anger, disgust and grief. For a description of detailed facial expressions, the Facial Action Coding System (FACS) was designed by Ekman and Friensen in the mid 70s. In FACS, motions of the muscles of the face are divided into 44 action units and any facial expression are described by their combinations.</p>