Neural network-based fuzzy observer with application to facial analysis

Abstract

Human facial wrinkles can be effectively utilized for facial analysis. It is not an easy task, however, to extract features of wrinkledness directly from a camera image of a human face. For one thing, it is difficult to construct appropriate mathematical models for wrinkle features. In this work, a fuzzy observer is proposed as a means of providing linguistic descriptions about the image of a human face with wrinkles. In the proposed observer, some well-defined classical image features and numerical information are transformed into fuzzy numbers. A feedforward multilayered artificial neural network (ANN) is employed for parameter adjustment of the fuzzy observer based on the available crisp-input fuzzy-output sample sets. An experiment is performed to demonstrate that the facial wrinkles can be indirectly estimated by the proposed fuzzy observer. (C) 2000 Elsevier Science B.V. All rights reserved.