Document Type

Honors Thesis


It is not uncommon to see vehicles speeding in residential neighborhoods, particularly near high traffic areas such as highways or city centers. This issue is typically either dealt with by stationing police officers along streets, or by ignoring the issue completely. By capturing images of license plates and processing them to extract the plate numbers, offenders can easily and inexpensively be monitored and reported. One method of processing these images is to run them through a convolutional neural network. These networks excel at detecting objects within images. By creating a convolutional neural network, and training it based on sample data, it was demonstrated to always recognize license plates in scenes it had seen before, but it struggled to recognize plates in a new environment.

Publication Date






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.