Facial Expression Recognition System Using Local Texture Features of Contourlet Transformation
Australian Journal of Basic and Applied Sciences, 10(2), January 2016
4 Pages Posted: 10 Jul 2017
Date Written: January 8, 2016
Facial expression is important in interpersonal relations also significant among communication in both human and machine iteration. Thus the importance of facial expression recognition is becoming active research area in last three decades. In this study, a robust and automated facial expression recognition system is proposed using facial images. It is implemented based on Contourlet transform, Discriminative Robust Local Binary Pattern (DRLTP) and K-Nearest Neighbour (KNN) classifier. To extract facial features, the given facial image is decomposed using Contourlet Transform. Then, DRLTP features are computed from each decomposed contourlet coefficients. Finally, KNN classifier is used for the classification of facial expressions. Experiments are carried out using benchmark Japanese Female Facial Expression (JAFFE) database. The proposed system achieves satisfactory classification accuracy over 75%.
Keywords: Facial Expression Recognition, Contourlet Transform, K-Nearest Neighbor Classifier, Discriminative Robust Local Binary Pattern.
Suggested Citation: Suggested Citation