College for Professional Studies
MS Software Engineering
Thesis - Open Access
Number of Pages
Optical character recognition (OCR) software currently being used at radiation portal monitor (RPM) sites to read cargo container identification numbers is expected to produce 90% accuracy when the containers meet ISO Standard 6346: 1995, Freight containers – Coding, identification, and marking. One of the RPM seaport sites was reporting low OCR accuracy results, prompting a request to fix the problem. A data analysis conducted at the site determined overall accuracy was only at 68% (69% for nighttime and 62% for daytime) with poor image quality in both day and night conditions being the primary factor in low OCR accuracy. Nighttime image quality was primarily impacted by inadequate lighting. After conducting several tests to find the appropriate lighting, a new lighting configuration was implemented at the site that included using higher wattage light fixtures and placing the light fixtures closer to the target. This improved overall nighttime OCR accuracy from 69% to 87%. Daytime image quality was primarily impacted by the sun. Placing the cameras at different angles and adding cameras to obtain more images of the containers have the potential for improving daytime OCR accuracy. No changes were made at the site to improve daytime OCR.
Date of Award
© Mark Bayless
All content in this Collection is owned by and subject to the exclusive control of Regis University and the authors of the materials. It is available only for research purposes and may not be used in violation of copyright laws or for unlawful purposes. The materials may not be downloaded in whole or in part without permission of the copyright holder or as otherwise authorized in the “fair use” standards of the U.S. copyright laws and regulations.
Bayless, Mark, "Improving Optical Character Recognition Accuracy for Cargo Container Identification Numbers" (2010). All Regis University Theses. 895.