A PCA based human facial expression classification algorithm

• Main Authors: Chih Wei, Yang, 楊志偉
• Other Authors: Chung J.Kuo
• Format: Others
• Language: en_US
• Published: 2003
• Online Access: http://ndltd.ncl.edu.tw/handle/08804169117786621310

碩士 === 國立中正大學 === 電機工程研究所 === 91 === In this research, we try to develop an analytical framework for classifying human basic emotions, which are happiness, sadness, anger, surprise, disgust, and contempt, according to the definition by psychologist Ekman. Under the condition that the coordinates of several feature points was previously obtained by some pre-processing techniques. We try to find out what are the major components of each facial expression, what are the patterns that distinguish them from one another. We applied widely used pattern recognition technique-principle component analysis (PCA) to characterize the feature point displacements of each basic human facial expression for each individual in the existing database. For faces not existent in the database, so called “novel face” in our experiment, we will first find the face in the database that has most likely neutral face to this individual, and base on an assumption that are widely accepted in cognitive science, we will classify this novel face to the category where the most similar one belongs, and classifying his/her facial expression using the so called “expression model” of the most similar individual. This kind of approach has never be exploited before, we will examine its robustness in our experiment, and suggest methods that may potentially make it even more robust.