An associate memory model of facial expressions and its application in facial expression recognition of patients on bed

In this paper, we proposed a new method of monitoring patients on bed by utilizing the facial expression analyses and recognition. In this proposed method, the optical flows of the corresponding image sequence, which appeard the facial actions, were computed. Based on the optical flow projection histogram on and coordinate axes in the mouth region and the eye region, the facial action features were extracted. By utilizing the facial action feature rate of occurrence on the happiness, easiness, uneasiness, disgust, suffering and surprise, the associate memory model of facial expressions is composed to recognize the facial expressions. The classification performance of our associate memory model is demonstrated by using a training set and a testing set from the facial expression database made for our research project.