In this paper, a temporal-reinforced approach to enhancing emotion recognition from facial images is presented. Shape and texture models of facial images are computed by using active appearance model (AAM), from which facial feature points and geometrical feature values are extracted. The extracted features are used by relevance vector machine (RVM) to recognize emotional states. We propose a temporal analysis approach to recognizing likelihood of emotional categories, such that more subtle emotion, such as degree and ratio of basic emotional states can be obtained. Furthermore, a method is developed to map the recognition result to the arousal-valence plane (A-V Plane). Experimental results verify that the performance of emotion recognition is enhanced by the proposed method.