Multi-Class Image Classification Using Machine Learning

Senior Capstone Experience by Robert Clark ’20

Submitted to the Department of Mathematics & Computer Science

Advised by Dr. Kyle Wilson

Short Description: Dr. Wilson and I created an image classifier to classify images of traffic signs, with a final validation accuracy of 94.1%. The purpose of this paper is to demonstrate the utility of image classifiers, help readers understand how they are created, and demonstrate how they work. This paper defines essential terms for understanding machine learning algorithms, discusses the process towards making our image classifier, shows examples of the input images used, and examines how neural networks are being used unethically today.

Contributor Bio: Robert Clark ‘20 is a Computer Science and Mathematics graduate from Annapolis, Maryland. He received a two-year degree in Computer Science from Anne Arundel Community College and then transferred to Washington College in 2018. Robert likes to study French in his free time and hopes to work in a field where he can use his skills with machine learning.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s