Self-organizing adaptation for facial emotion mapping

Abstract

This paper presents an emotion mapping system that attempts to emulate human brain reference model. The system first locates the human face in an image, and then identifies the localized face emotion. The understanding of cognitive system is presented in the paper. It highlights how individual module is mapped to the proposed system. Then, single- and multi-layer self-organizing emotion maps are described. The system is evaluated through various test sets. The experimental results show encouraging hit rates for identifying emotions of unknown subjects.