Real-time Facial Expression Recognition in Image Sequences Using an AdaBoost-based Multi-classifier

In this paper, a highly automatic facial expression recognition system without choosing characteristic blocks in advance is presented. The system is able to detect and locate human faces in image sequences acquired in real environments. To achieve efficient facial expression recognition, we evaluate the performance of three different classifiers using multi-layer perceptrons (MLPs), support vector machines (SVMs), and Adaboost algorithms (ABAs). From the experimental outcomes, we can observe that the average recognition rates obtained from both ABAs and MLPs are better than that from SVMs, but the training of MLPs takes quite a long time. Comparatively, ABAs have an advantage of facilitating the speed of convergence, which are chosen as the core technique to implement our strong facial expression classifier. Through conducting many experiments, the statistics of performance reveals that the accuracy rate of our facial expression recognition system reaches more than 90% for a single kind or multiple kinds of expressions appearing in an image sequence.APSIPA ASC 2009: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference. 4-7 October 2009. Sapporo, Japan. Oral session: 3D Synthesis and Expression (5 October 2009)