Orientation Selectivity for Representing Dynamic Diversity of Facial Expressions

Abstract

This paper presents a representation method of facial expression changes using Adaptive Resonance Theory (ART) networks. Our method extracts orientation selectivity of Gabor wavelets on ART networks, which are unsupervised and self-organizing neural networks that contain a stability-plasticity tradeoff. The classification ability of ART is controlled by a parameter called the attentional vigilance parameter. However, the networks often produce redundant categories. The proposed method produces suitable vigilance parameters according to classification granularity using orientation selectivity. Moreover, the method can represent the appearance and disappearance of facial expression changes to detect dynamic, local, and topological feature changes from obtained whole facial images.