Sponsor
Portland State University. Department of Electrical Engineering
Advisor
George G. Lendaris
Date of Award
1989
Document Type
Thesis
Degree Name
Master of Science (M.S.) in Electrical and Computer Engineering
Department
Electrical and Computer Engineering
Physical Description
1 online resource (113 p.)
Subjects
Pattern recognition systems, Neural computers
DOI
10.15760/etd.5807
Abstract
This thesis describes an approach for accomplishing a pattern recognition task using conceptual graph theory and neural networks (NNs). The set of patterns to be recognized are the capital letters of six different fonts of the English alphabet, plus two shifted and six rotated versions of each. The letters are represented to the neural network on a 16x16 input grid (256 "sensor lines"). A standard classification encoding for such patterns is to use a 26-bit vector (26 lines at the NN's output), one bit corresponding to each letter. Experiments with such an encoding yielded results with poor generalization capability. A new encoding scheme was developed, based on the conceptual graph formalism. This entailed designing a set of concepts and a set of associated relations appropriate to the upper case letters of the English alphabet. From these, the following were developed: a conceptual graph representation for each letter, a connection matrix for each, and finally, a C-vector and an R-vector representation for each. The latter were used as the output encoding (21 bits) of the NN pattern recognizer. A feed-forward neural network with 256 inputs, 21 outputs, and 2 hidden layers was trained using the back-propagation- of-error algorithm. Results were significantly better than with the more standard. encoding. Generalization on fonts improved from 74% to 96%, generalization on rotations improved from 83% to 94%, and finally, generalization on shifts improved from 2% to 93%.
Persistent Identifier
http://archives.pdx.edu/ds/psu/22006
Recommended Citation
Harb, Ihab A., "An approach to pattern recognition of multifont printed alphabet using conceptual graph theory and neural networks" (1989). Dissertations and Theses. Paper 3923.
https://pdxscholar.library.pdx.edu/open_access_etds/3923
10.15760/etd.5807
Description
If you are the rightful copyright holder of this dissertation or thesis and wish to have it removed from the Open Access Collection, please submit a request to pdxscholar@pdx.edu and include clear identification of the work, preferably with URL