Near-optimal facial emotion classification using a WiSARD-based weightless system.

Abstract

The recognition of facial expressions through the use of a WiSARD-based n-tuple classifier is explored in this talk. The competitiveness of this weightless neural network is tested in the specific challenge of identifying emotions from photos of faces, limited to the six basic emotions described in the seminal work of Ekman and Friesen (1977) on identification of facial expressions. Current state-of-the-art for this problem uses a convolutional neural network (CNN), with accuracy of 100% and 99.6% in the Cohn-Kanade and MMI datasets, respectively, with the proposed WiSARD-based architecture reaching accuracy of 100% and 99.4% in the same datasets.

Short Bio

Felipe M.G. França is Full Professor of Computer Science and Engineering at the Systems Engineering and Computer Science Program, COPPE, Universidade Federal do Rio de Janeiro (UFRJ). He received his B.E.E. (Electronics Engineering, 1981) and his M.Sc. (Computer Science, 1987) from UFRJ, and his Ph.D. (Neural Systems Engineering, 1994) from the Imperial College London. His research and teaching interests include artificial neural networks, complex systems, computer architecture, cryptographic circuits, distributed algorithms, computational intelligence, collective robotics, complex systems, intelligent transportation systems and parallel computing.