期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2012
卷号：3
期号：2
页码：443-446
语种：English
出版社：Ayushmaan Technologies
摘要：Automatic facial expression recognition is the kernel part of emotional information processing. The regions of interest for extracting the features from the facial images include eyes, eyes with eyebrows, mouth. In this paper there are two main parts locating the points in the face region to form graph based features and training the neural network to recognize the emotions from the corresponding feature vector. For the first phase, sixteen points are manually located to create graph with edges connecting such points. Subsequently, the Euclidean distances from those edges are calculated and defined as features for training in the next phase. The next phase is using Feed forward networks (FFN), a kind of artificial neural network (ANN), with back propagation algorithm to recognize the emotions like excitement, happy, shocked, confusion, and disgust.
