Local versus global segmentation for facial expression recognition

We examined the open issue of whether FACS action units (AUs) can be recognized more accurately by classifying local regions around the eyes, brows, and mouth compared to analyzing the face as a whole. Our empirical results showed that, contrary to our intuition, local expression analysis showed no consistent improvement in recognition accuracy. Moreover, global analysis outperformed local analysis on certain AUs of the eye and brow regions. We attributed this unexpected result partly to high correlations between different AUs in the Cohn-Kanade expression database. This underlines the importance of establishing a large, publicly available AU database with singly-occurring AUs to facilitate future research