Recognition of facial expressions based on the Hopfield memory model
Ying Dai, Yoshitaka Shibata, Yuya Nakano, Koji Hashimoto · 2003
In this paper, a new method for recognizing facial expressions by utilizing the Hopfield model is presented. In this method, the Hopfield memory model with recall capability is constructed. When a facial image is given to the Hopfield memory as an input, all units which are at a stable state yield associate recall patterns. Based on the composed Hopfield memory model, the relation between the reliability of the recalls and the number of faces which are memorized in the Hopfield memory is analyzed. Based on the performance of the Hopfield memory model, the scheme for facial expression recognition combined with pattern matching is presented. The experimental results are shown and analyzed.