Recognition of Emotions Induced by Music Videos Using DT-CWPT

Viewers are attracted and attached to multimedia content due to their emotional experience associated with it. In this paper, we present an emotion recognition method of EEG signals elicited while watching music videos. The emotional features are extracted from EEG signals using dual-tree complex wavelet packet transform (DT-CWPT). The most discriminating emotional features are selected by Singular value decomposition (SVD), QR factorization with column pivoting (QRcp) and F-ratio based method. The selected features are used to train support vector machine (SVM) to classify emotion for each video using leave-one-out cross-validation strategy.