The effectiveness of using geometrical features for facial expression recognition

Abstract

Facial expressions play an important role in diverse disciplines ranging from entertainment (video games) to medical applications and affective computing. For tackling the problem of expression recognition, various approaches were proposed over the last two decades. These approaches are primarily divided into two types: geometry and appearance based. In this paper, we address the geometry based approaches to recognize the six basic facial expressions (happiness, surprise, anger, fear, disgust, and sadness). We provide answers to three major questions regarding the geometrical features: 1. What is the minimum number of facial points that could provide a satisfactory recognition rate? 2. How this rate is affected by prior knowledge of person-specific neutral expression? 3. How accurate should a facial point detector be to achieve an acceptable recognition rate? To assess the reliability of our approach, we evaluated it on two public databases. The results show that a good recognition rate could be achieved by using just eight facial points. Moreover, the lack of prior knowledge of person-specific neutral state causes more than 7% drop in the recognition rate. Finally, the recognition rate is adversely affected by the facial point localization error.