The recognition of basic facial expressions by neural network

Abstract

An attempt is being made to develop a mind-implemented robot that can carry out intellectual conversation with humans. As the first step for this study, a method for the robot to perceive human emotion is investigated. Specifically, a method of human emotion recognition from facial expressions by a neural network is shown. The authors categorized facial expressions into six groups (surprise, fear, disgust, anger, happiness, and sadness) and obtained 70 CCD (charge coupled device) camera-acquired data of facial feature-points from three components of the face (eyebrows, eyes, and mouth). Then the facial expression information is generated and input into the input units of the neural network; network learning and recognition are done by a backpropagation algorithm.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>