Abstract

We present a Gaussian Mixture Model (GMM) fitting method for estimating the unknown neutral face shape for frontal facial ex-pression recognition using geometrical features. Subtracting the es-timated neutral face, which is related to the identity-specific compo-nent of the shape leaves us with the component related to the varia-tions resulting from facial expressions. Experimental results on the Extended Cohn-Kanade (CK+) database show that subtracting the estimated neutral face shape gives better emotion recognition rates as compared to classifying the geometrical facial features directly, when the person-specific neutral face shape is not available. We also experimentally evaluate two different geometric facial feature extraction methods for emotion recognition. The average emotion recognition rates achieved with the proposed neutral shape estima-tion method and coordinate based features is 88%, which is higher than the baseline results presented in the literature, although we do not use the person-specific neutral shapes (94 % if we use), and any appearance based features. Index Terms — neutral face estimation, gaussian mixture mod-els, facial expression recognition 1.