An improved neural-network-based face detection and facial expression classification system

Automatic facial expression recognition is one of the most difficult and important problems in the scientific areas of cybernetics, pattern recognition and computer vision and their technological applications. New, friendlier human-computer interaction modes and multimedia interactive services require processing of images obtained with the use of multiple cameras to detect the presence and location of computer users´ faces and determine their affective state. In order to be fully automated, the system proposed in this paper, consists of two modules: firstly, we use a face detection algorithm to determine whether or not there are any faces in the image and, if so, return the location and extent of each face, and secondly, we use a facial expression classification module to determine the facial expression of a person