Abstract-This paper presents the fuzzy video based emotion recognition system VISBER, that allows to analyze facial expressions in video sequences. In order to process images in real-time a tracking mechanism is used for face localization. The fuzzy classification itself analyzes the deformation of a face separately in each image. In contrast to most existing approaches, also blended emotions with varying intensities as proposed by psychologists can be handled. For this purpose we propose a fuzzy emotion model which is generally applicable for also for other emotion recognition solutions. Furthermore, VISBER supports the automatic adaptation to the characteristics of individual human faces by a short training phase that can be done before the emotion recognition starts.

This paper presents a fuzzy emotion model and its use by a fuzzy emotion recognition system that allows to analyze facial expressions in video sequences. In order to process images in real-time a tracking mechanism is used for face localization. The fuzzy classification itself works on single images. It analyzes the deformation of a face using a size-invariant, feature based representation by a set of typical angles. Automatic adaptation to the characteristics of individual human faces is achieved by a short training phase that can be done before the emotion recognition starts. In contrast to most existing approaches, also blended emotions with varying intensities as proposed by many psychologists can be recognized and represented by the fuzzy emotion model. This model is generally applicable also for other emotion recognition solutions.