期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：8
页码：15679
DOI：10.15680/IJIRSET.2016.0508184
出版社：S&S Publications
摘要：Automatic human emotion recognition is an important and emerging aspect of human facial expressionrecognition for human-machine interface. Facial expressions are mostly the reflections of one’s emotional state. So toknow the true emotional state of a person, accurate evaluation of his/her facial expressions is must. In recent times,major advances were made in understanding and analyzing facial expressions by applications of image processing andmachine learning methods. In this paper we have proposed a novel approach which uses neural network to classify andrecognize facial expressions. The system is able to recognize six basic emotions. The proposed system works in threesteps. First, the face is detected from image, and then features are extracted from it using Zernike moments. In the laststep the neural network is trained to classify the emotions. The system so designed was implemented on Cohn-Kanadedatabase and accuracy of around 74 % was achieved.
关键词：Face detection; feature extraction; Zernike moments; and neural network.
