Nonfrontal Expression Recognition in the Wild Based on PRNet Frontalization and Muscle Feature Strengthening

Abstract

Nonfrontal facial expression recognition in the wild is the key for artificial intelligence and human-computer interaction. However, it is easy to be disturbed when changing head pose. Therefore, this paper presents a face rebuilding method to solve this problem based on PRNet, which can build 3D frontal face for 2D head photo with any pose. However, expression is still difficult to be recognized, because facial features weakened after frontalization, which had been widely reported by previous studies. It can be proved that all muscle parameters in frontalization face are more weakened than those of real face, except muscle moving direction on each small area. Thus, this paper also designed muscle movement rebuilding and intensifying method, and through 3D face contours and Fréchet distance, muscular moving directions on each muscle area are extracted and muscle movement is strengthened following these moving directions to intensify the whole face expression. Through this way, nonfrontal facial expression can be recognized effectively.