Tailoring Model-based Techniques to Facial Expression Interpretation by Matthias

Computers have been widely deployed to our daily lives, but human-computer interaction still lacks intuition. Re-searchers intend to resolve these shortcomings by aug-menting traditional systems with human-like interaction capabilities. Knowledge about human emotion, behavior, and intention is necessary to construct convenient interac-tion mechanisms. Today, dedicated hardware often infers the emotional state from human body measures. Similar to humans interpreting facial expressions, our approach acquires video information using standard hard-ware that does not interfere with people to accomplish this task. It exploits model-based techniques that accurately localize facial features, seamlessly track them through image sequences, and finally interpret the visible infor-mation. We make use of state-of-the-art techniques and specifically adapt most of the components involved to this scenario, which provides high accuracy and real-time ca-pability. We base our experimental evaluation on pub-licly available databases and compare its results to related approaches. Our proof-of-concept demonstrates the feasi-bility of our approach and shows promising for integration into various applications. ∗This research is partly funded by a JSPS Postdoctoral Fellowship for North American and European Researchers (FY2007).