Human Emotion Recognition and Classification from Digital Colour Images Using Fuzzy and PCA Approach

Abstract

Abstract. In this paper, we proposed a new model for recognizing various emotions of humans with different age groups and gender. Fuzzy is used for extracting more accurate region of interest, i.e., face. The dimensionality of face image is reduced by the Principal Component Analysis (PCA) [12] and finally emotion is recognized and classified using Euclidean Distance. Database is prepared and some performance metrics like recognition-rate v/s Eigen-range has been calculated. The proposed method was also tested on FACES Collection database [13]. The experiment results demonstrate that the emotion recognition system has been successful with average recognition rate of 96.66% (with both experiment databases) when approximately or more than 60% eigenfaces used. It is also shown that database can be easily expanded to classify faces and non faces images.