Fuzzy-GIST for emotion recognition in natural scene images

Emotion modeling evoked by natural scenes is challenging issue. In this paper, we propose a novel scheme for analyzing the emotion reflected by a natural scene, considering the human emotional status. Based on the concept of original GIST, we developed the fuzzy-GIST to build the emotional feature space. According to the relationship between emotional factors and the characters of image, L*C*H* color and orientation information are chosen to study the relationship between human's low level emotions and image characteristics. And it is realized that we need to analyze the visual features at semantic level, so we incorporate the fuzzy concept to extract features with semantic meanings. Moreover, we treat emotional electroencephalography (EEG) using the fuzzy logic based on possibility theory rather than widely used conventional probability theory to generate the semantic feature of the human emotions. Fuzzy-GIST consists of both semantic visual information and linguistic EEG feature, it is used to represent emotional gist of a natural scene in a semantic level. The emotion evoked by an image is predicted from fuzzy-GIST by using a support vector machine, and the mean opinion score (MOS) is used for performance evaluation for the proposed scheme. The experiments results show that positive and negative emotions can be recognized with high accuracy for a given dataset.