Date of Award


Publication Type

Master Thesis

Degree Name



Electrical and Computer Engineering

First Advisor

Chen, X.


Engineering, Electronics and Electrical.



Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.


In order to minimize the cost for any improvement or changes in manufacturing products, a flexible manufacturing system is necessary. To do so, robots should be empowered with equipment like vision sensors, which can work as human eyes for robots. A tracking vision sensor consists of a CCD camera, data acquisition, preprocessing, recognition and tracking modules. In this thesis, a design methodology for invariant recognition-based object tracking is proposed, which can potentially be used for implementation of either vision sensors or tracking vision sensors. The performance of Invariant Recognition-based object tracking to a large extent depends on the object recognition process rather than object sensing and tracking. For that reason, in this thesis the major focus is mostly on the recognition procedure. Fuzzy Associative Database (FAD) and Adaptive Fuzzy Associative Database (AFAR) are introduced as supervised networks to overcome the weaknesses of some computational intelligence approaches like fuzzy inference and neural networks for object recognition purposes. FAD consists of a Fuzzy Database (FD) and a Fuzzy Search Engine (FSE). (Abstract shortened by UMI.)Dept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2003 .S52. Source: Masters Abstracts International, Volume: 42-03, page: 1020. Adviser: Xiang Chen. Thesis (M.A.Sc.)--University of Windsor (Canada), 2003.