Generation of personalized video summaries by detecting viewer's emotion using electroencephalography

摘要

Video summaries produced by low level features are unaware of the viewer's requirements and result in a semantic gap. Video content evokes certain emotions in a viewer, which can be measured and act as a strong source of information to generate summaries meeting viewer's expectation. In this paper, we propose a personalized video summarization framework that classifies viewer's emotion based on electroen-cephalography (EEG) signals, while watching a video to extract keyframes. Features are extracted from recorded EEG signals in time, frequency and wavelet domain to classify viewer's emotions. Those frames are selected as keyframes from the video, where different emotions of viewer are evoked. Experiments are performed on 50 viewers and 50 video sequences to validate the effectiveness and efficiency of the proposed framework. It is evident from the results that the proposed method generates summaries with high precision, recall, F-measure, accuracy, and low error, hence reducing the semantic gap. (C) 2019 Elsevier Inc. All rights reserved.