Facial expression modeling using component AAM models — Gaming applications

Abstract

In this paper we provide preliminary results on a new modeling approach for improved determination of facial expressions from a low-resolution video stream. An initial proof-of-concept using an extension of an Active Appearance Model (AAM) to measure facial parameters and a set of classifiers to determine facial states are described. We also discuss the potential for applying this technique to determine the emotional state of the players of a computer game and suggest how this information can be integrated into the workflow of a game. In addition we describe a number of use cases where the game environment can be adapted based on feedback from the players.