Dealing with Feature Uncertainty in Facial Expression Recognition Using Possibilistic Fuzzy Rule Evaluation

[journal]

Full reference

M. Wallace, S. Ioannou, A. Raouzaiou, K. Karpouzis, S. Kollias, Dealing with Feature Uncertainty in Facial Expression Recognition Using Possibilistic Fuzzy Rule Evaluation, International Journal of Intelligent Systems Technologies and Applications, Volume 1, Number 3-4 / 2006

Abstract

Since facial expressions are a key modality in human communication, the automated analysis of facial images for the estimation of the displayed expression is central in the design of intuitive and human friendly human-computer interaction systems. In existing approaches, over-formalised description of knowledge concerning the human face and human expressions, as well as failures of the image and video processing components, often lead to misclassification. In this paper, we propose the utilisation of extended fuzzy rules for the more flexible description of knowledge, and the consideration of uncertainty and lack of confidence in the process of feature extraction from image and video. The two are combined using a flexible possibilistic rule evaluation structure, leading to more robust overall operation. The proposed approach has been implemented as an extension to an existing expression analysis system and conclusions from comparative study have been drawn.

Download

Click here to access the paper.

3 known citations

1. I. Maglogiannis, D. Vouyioukas and C. Aggelopoulos, Face detection and recognition of natural human emotion using Markov random fields,. Personal and Ubiquitous Computing, vol 13(1) , pp. 95-101, 2009
2. D. Tzovaras, Multimodal User Interfaces: From Signals to Interaction, Signals and Communication Technology Series, Springer, 2008
3. G. Caridakis, Emotion Analysis in Natural Human Computer Interaction, PhD Thesis, National Technical University of Athens, School of Electrical and Computer Engineering, 2009