Analysis of positive and negative emotions in natural scene using brain activity and GIST

This paper proposes a novel emotion understanding system based on brain activity and ''GIST'' to categorize emotions reflected by natural scenes. According to the intensified relationship of human emotion and the brain activity, functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) are used to analyze and classify emotional states stimulated by a natural scene. The ''GIST'' is used to extract the visual low-level features, which are used as input signals to a classifier for obtaining the high-level emotional gist of a natural scene. Mean opinion scores are used for teaching signals of the classifier. Considering the way a human brain is responding to the same visual stimuli, a machine will be able to extract the emotional features of natural scenes using the ''GIST'' and the EEG signals, judge the emotions reflected by the nature scenes and achieve interaction with a human in terms of emotional sharing through the EEG signals. The experimental results demonstrate that positive and negative emotions can be distinguished.