Abstract
There are two approaches to automating the task of facial expression recognition, the first concentrating on what meaning is conveyed by facial expression and the second on categorising deformation and motion into visual classes. The latter approach has the advantage that the interpretation of facial expression is decoupled from individual actions as in FACS (Facial Action Coding System). In this chapter, upper face action units (aus) are classified using an ensemble of MLP base classifiers with feature ranking based on PCA components. When posed as a multi-class problem using Error-Correcting-Output-Coding (ECOC), experimental results on Cohn-Kanade database demonstrate that error rates comparable to two-class problems (one-versus-rest) may be obtained. The ECOC coding and decoding strategies are discussed in detail, and a novel weighted decoding approach is shown to outperform conventional ECOC decoding. Furthermore, base classifiers are tuned using the ensemble Out-of-Bootstrap estimate, for which purpose, ECOC decoding is modified. The error rates obtained for six upper face aus around the eyes are believed to be among the best for this database.