Date of Award
1985
Publication Type
Doctoral Thesis
Degree Name
Ph.D.
Department
Electrical and Computer Engineering
Keywords
Engineering, Electronics and Electrical.
Rights
info:eu-repo/semantics/openAccess
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Abstract
This thesis discusses the development of algorithms for the recognition of handwritten numeral strings in their various forms viz. isolated, broken and connected. For isolated numerals, the use of a new class of Fourier shape descriptors derived from the contours of the numeral together with a new class of topological features is shown to yield high recognition accuracy ((TURNEQ) 98%). For isolated and possibly broken numerals, a syntactic recognition algorithm that utilizes features derived from the left and right profiles of the numerals is shown to yield fast and accurate recognition. Finally, an algorithm for segmenting connected handwritten numeral strings has been developed and is shown to yield accurate segmentation. The segmented numerals are then identified by the syntactic recognition system.Dept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis1985 .B337. Source: Dissertation Abstracts International, Volume: 46-08, Section: B, page: 2751. Thesis (Ph.D.)--University of Windsor (Canada), 1985.
Recommended Citation
BADRELDIN, AMIRA M. K., "STRUCTURAL RECOGNITION OF HANDWRITTEN NUMERAL STRINGS." (1985). Electronic Theses and Dissertations. 3618.
https://scholar.uwindsor.ca/etd/3618