single-jc.php

JACIII Vol.1 No.1 pp. 45-61
doi: 10.20965/jaciii.1997.p0045
(1997)

Paper:

Fuzzy Modeling based Approach to Facial Expressions Understanding

Anca Ralescu* and Riad Hartani**

*ECE&CS Department, University of Cincinnati, Cincinnati, Ohio 45221, USA

**Nortel-Entreprise Networks, Ottawa, Canada

Received:
March 30, 1997
Accepted:
May 20, 1997
Published:
October 20, 1997
Keywords:
Facial expressions, Facial information processing, Fuzzy modeling, Hybrid reasoning, Human perception modelling
Abstract
We consider two problems related to the understanding of facial expressions: (I) modeling the perception of human facial expressions from information extracted from face photographs and (II) reasoning about the transition between facial expressions as modeled in (I). For (I) we develop a hierarchical fuzzy modeling method. The results obtained are satisfactory when compared with those of other approaches: for the six basic facial expressions (happiness, surprise, sadness, anger, disgust and fear), we achieve a recognition ratio of 85 %. More importantly, in addition to the usual advantages of fuzzy rules such as easy interpretation and adaptability in a changing environment, our approach can be applied without additional training to (i) the identification of mixed facial expressions - the recognition ratio of the two strongest facial expressions in the same face being about 75%, and (ii) the recognition in noisy environment (that is, our approach can successfully deal with lack of data). For (II) we propose a model for transition between facial expressions based on a hybrid reasoning scheme combining generalized modus tollens and fuzzy backward reasoning. Appropriate examples are used to illustrate our approach and we conclude with a discussion about future issues, and possible applications to an intelligent humancomputer interface using the transition model.
Cite this article as:
A. Ralescu and R. Hartani, “Fuzzy Modeling based Approach to Facial Expressions Understanding,” J. Adv. Comput. Intell. Intell. Inform., Vol.1 No.1, pp. 45-61, 1997.
Data files:

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Oct. 01, 2024