Robust Facial Expression Recognition via Principal Component Analysis and AdaBoost Algorithm  
Author Cheng Fan


Co-Author(s) Eric T.T. Wong


Abstract Facial expression is a key component in evaluating a person’s feelings, intentions and characteristics. Facial expression is an important part of human-computer interaction and has the potential to play an equal important role in real life applications. This paper is aimed to propose a robust approach for facial expression recognition through Principal Component Analysis (PCA) and AbaBoost algorithm. With the help of PCA one can extract the important feature pixels in a facial expression figure for the feature classifier to recognize the facial expression concerned. We propose to combine the AbaBoost algorithm with a special machine learning algorithm to reduce the error rate in feature classification. The proposed approach was applied to images of facial expressions posed by a Japanese female model in The Japanese Female Facial Expression (JAFEE) database. The classifying precision 92.45% has demonstrated the feasibility of our proposal method.


Keywords Facial expression recognition, AdaBoost, principal component analysis
    Article #:  24255
Proceedings ISSAT International Conference on Reliability and Quality in Design 2018
August 2-4, 2018 - Toronto, Ontario, Canada