Micro Expression Classification Accuracy Assessment

The ability to identify and draw appropriate implications from non-verbal cues is a challenging task in facial expression recognition and has been investigated by various disciplines particularly social science, medical science, psychology and technological sciences beyond three decades. Non-verbal cues often last a few seconds and are obvious (macro) whereas others are very short and difficult to interpret (micro). This research is based on the area of micro expression recognition with the main focus laid on understanding and exploring the combined effect of various existing feature extraction techniques and one of the most renowned machine learning algorithms identified as Support Vector Machine (SVM). Experiments are conducted on spatiotemporal descriptors extracted from the CASME-II dataset using LBP-TOP, LBP-SIP, LPQ-TOP, HOG-TOP, HIGO-TOP and STLBP-IP. We have considered two different cases for the CASME-II dataset where the first case measures performance for five class i.e. happiness, disgust, surprise, repression and others and the second case considers three classes namely positive, negative and surprise. LPQ-TOP with SVM produced highest accuracy against rest of the approaches in this work.