Recognizing emotions by analyzing facial expressions

Recognizing expressions is a key part of human social interaction, and processing of facial expression information is largely automatic. However, it is a non-trivial task for a computational system. Our purpose of this work is to develop Computational models capable of differentiating between ranges of human Facial expressions. The Gabor feature is effective for facial image representation. The Gabor feature dimensionality is so high that a dimensionality reduction technique such as PCA must be applied. Classification of various classes of expressions can be achieved by training and then testing with a Support Vector Machine (SVM).