Finding Letters Via Edge Detection Using an Artificial Neural Network

This is the fifth in a series of reports to document development of a generalized method to create artificial neural networks (ANNs) via a genetic algorithm (GA). This report will be divided into several main sections. The goal of this report is to demonstrate the ability of an ANN to detect edges in images and use those edges to recognize letters. Reports #1-3 showed the development of a genetic algorithm that could evolve an artificial neural network given a set of input images. Report #3 focused on training an ANN to recognize patterns, specifically letters in an image.