RETRACTED ARTICLE: Real-time facial expression recognition for affect identification using multi-dimensional SVM

Abstract

Automated detection of different affect states for human beings using facial expressions has attracted an increasing level of research attention for high accuracy. In general, existing facial expressions databases have been used in automated affect state detection to achieve better efficiency. However, minimal real-time experiments data has been used for detecting affect state. To efficiently automate the affect recognition process, in this work, we proposed a new classifier framework and acquired experimentally real-time dataset for training and testing phase. The participants’ face images are captured and processed on the Region of Interest (ROI) to determine the feature points, and hence feature vectors are obtained. The facial feature vectors are given as an input to the proposed multiclass classifier, Multi-dimensional Support Vector Machine (MDSVM), which efficiently identifies and classifies the different affect state. The MDSVM is designed multi-dimensional, based on the two-dimensional valence-arousal emotional model. Thus, two SVMs are used, one in level-1, which classifies the input dataset into two classes based on valence, similarly the second SVM in level-2 classifies the input dataset into two categories based on arousal. The efficiency is improved by using the 8-cross-validation method. Thus, the methodology proposed in this work combines the advantage of reliable dataset acquired experimentally, significant 12 feature vectors obtained from facial expressions, prominently active multidimensional SVM, and 8-cross validation method. Experimental results illustrate the efficacy of the proposed system for accurately classifying the affect state into four categories, Relax, Sad, Angry, and Happy. The average accuracy obtained is 94.25% without k-fold cross-validation and 95.88% with 8-fold cross-validation.