Facial emotion feature extraction based eigenface for three-dimensional video

Abstract EN

Recent psychological research has shown that facial expressions are the most expressive way in which humans display emotion.

Facial expressions are widely used in the behavioral interpretation of emotions, cognitive science, and social interactions.

Therefore, automated and real-time facial expression recognition would be useful in many applications, such as human-computer interfaces, virtual reality, video-conferencing, and customer satisfaction studies.

This paper presents a proposed technique for facial expression extraction, which is based on the appearance features technique - principle component analysis, which depending on extract features (largest eigenvalues and eigenvectors).

Experimental results show the quick technique for feature extraction of three-dimensional video frames, which takes 5.1 s in the process of feature extraction.