Date of Award


Publication Type

Doctoral Thesis

Degree Name



Electrical and Computer Engineering

First Advisor

Ahmadi, M.


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.


A comparative evaluation of the effectiveness of moment invariants as shape sensitive features for pattern recognition applications is presented. Zernike, pseudo Zernike, Hu, Bamieh, and regular moment invariants were compared for their performance in a shape recognition study using two data sets: handwritten numerals and aircraft pictures. Zernike moment invariants and pseudo Zernike moment invariants have been derived in a new form for the n-th order. Using a new normalization scheme, it is shown that Zernike moment invariants as derived in this dissertation yielded a better performance. New algorithms have also been developed for the optimum thresholding and contour extraction of images.Dept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis1990 .B453. Source: Dissertation Abstracts International, Volume: 52-11, Section: B, page: 5986. Co-Supervisors: M. Ahmadi; M. Shridhar. Thesis (Ph.D.)--University of Windsor (Canada), 1990.