Honors Theses

Date of Award

2016

Document Type

Undergraduate Thesis

Department

English

First Advisor

Gregory Heyworth

Relational Format

Dissertation/Thesis

Abstract

In this research, an attempt to create a neural network classifier for the Latin uncial alphabet found in the Codex A, a late fourth century manuscript held by the Archivo Capitolare in Vercelli, Italy and the oldest of the Latin Gospels, is outlined. Training data collection methods, as well as image processing and artificial data creation methods used for expanding the training set, are discussed, as is their contribution to the success of the neural networks. While successful results are achieved for the testing sets, classification of new image data is largely unsuccessful. Potential improvement and avenues for expanding the research are discussed, as are potential explanations for the results.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.