Date of Award

2001

Publication Type

Master Thesis

Degree Name

M.A.Sc.

Department

Electrical and Computer Engineering

Keywords

Engineering, Electronics and Electrical.

Supervisor

Sid-Ahmed, M. A.,

Rights

info:eu-repo/semantics/openAccess

Abstract

Various Neural network models are investigated for Optical Character Recognition application and a Multi-layer Feed forward neural network is trained using a Fast training algorithm. Then the fast training algorithm is compared with the delta rule training algorithm. The various neural network models studied in this thesis are Hopfield, Hamming, Carpenter/Grssberg, Kohonen, Single layer and Multi-layer neural networks. These models are trained using Arabic numbers and investigated for training speed of the network, number of patterns that can be trained, size of the network, speed of the trained network for test data and noise sensitivity. The Multi-layer feed forward neural network is trained using the Fast training algorithm and delta rule training algorithm. Then both algorithms are compared for speed and generalization capability of Optical Character Recognition application. The trained and tested data are the 26 English capital letters, Times New Roman font and a font size of 16. All of the programs are implemented in visual C++ environment. The results are recorded and analyzed in this thesis. It was found that the Multi layer feed forward neural network is the best of all the other neural networks in the numeric recognition but it has a weakness of slow training process. Training speed of the Fast Training Algorithm is faster than the standard Delta Rule Algorithm and the generalization capability is also better compared to the Delta Rule AlgorithmDept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2001 .S26. Source: Masters Abstracts International, Volume: 40-03, page: 0759. Adviser: M. A. Sid-Ahmed. Thesis (M.A.Sc.)--University of Windsor (Canada), 2001.

Download

Share

COinS