Emotion Detection Using Facial Image Based on Geometric Attributes

Building a system for Human-Computer Interaction (HCI) that can interpret emotions in a similar manner for natural interaction between humans became an interesting and essential challenge. Auto emotion detection systems are demanded in various fields such as medicine, education, driver safety, games, etc. Despite the importance of this issue it still remains an unsolved problem. There are different ways to distinguish person emotions such as facial image, voice, shape of body and others. Mehrabian explained that person impression can be expressed through words (verbal part) by 7%, and 38% through tone of voice (vocal part) while the facial image can give the largest rate which reaches to 55%. Also, he indicates that one of the most important ways to display emotions is through facial expressions; where facial image contains much information (such as, person's identification and also about mood and state of mind which can be used to distinguish human inspiration). In this book, two systems have been proposed to recognize facial emotion for two different environments, where the ethnicity, skin color, head hair color and lightning condition are different.