The problem of optical pattern recognition is a broad one. It ranges from identifying shapes in aerial photographs to recognizing letters in hand or machine printed words. This thesis examines many of the issues relating to pattern recognition and, specifically, those pertaining to the optical recognition of characters. It discusses several approaches to various parts of the problem as an illustration of the variety of methods of attack. Some of the particular strengths and weaknesses of those approaches are discussed as well. Finally, a new method of approaching OCR is introduced, developed, and studied. At the conclusion, the study is summarized, the results are examined, and suggestions are made for continued research. / Department of Computer Science
| Identifer | oai:union.ndltd.org:BSU/oai:cardinalscholar.bsu.edu:handle/185835 |
| Date | January 1997 |
| Creators | Kirkpatrick, Michael Gorden |
| Contributors | Ball State University. Dept. of Computer Science., Fuelling, Clinton P. |
| Source Sets | Ball State University |
| Detected Language | English |
| Format | vi, 127 leaves : ill. ; 28 cm. |
| Source | Virtual Press |
Page generated in 0.0029 seconds