Computational Models of Face Perception
Faces are one of the most important means of communication for humans. For example, a short glance at a person’s face provides information about his or her identity and emotional state. What are the computations the brain uses to acquire this information so accurately and seemingly effortlessly? This article summarizes current research on computational modeling, a technique used to answer this question. Specifically, my research tests the hypothesis that this algorithm is tasked with solving the inverse problem of production. For example, to recognize identity, our brain needs to identify shape and shading features that are invariant to facial expression, pose, and illumination. Similarly, to recognize emotion, the brain needs to identify shape and shading features that are invariant to identity, pose, and illumination. If one defines the physics equations that render an image under different identities, expressions, poses, and illuminations, then gaining invariance to these factors can be readily resolved by computing the inverse of this rendering function. I describe our current understanding of the algorithms used by our brains to resolve this inverse problem. I also discuss how these results are driving research in computer vision to design computer systems that are as accurate, robust, and efficient as humans.