Off-campus South Dakota State University users: To download campus access theses, please use the following link to log into our proxy server with your South Dakota State University ID and password.

Non-South Dakota State University users: Please talk to your librarian about requesting this thesis through interlibrary loan.


Qiong Chen

Document Type

Thesis - University Access Only

Award Date


Degree Name

Master of Science (MS)

Department / School

Electrical Engineering

First Advisor

Dennis Helder


Computational techniques involving additive filtering and smoothing are developed in this paper. noise A new local mean and variance algorithm is used for additive noise filtering on two dimensional arrays. This new algorithm is implemented by computing a local median and median variance (LMMV) using 3x3, 5x5, 7x7, 9x9, and 11x11 windows. Performance of this algorithm is evaluated using both a simulated test image and a real world image. The algorithm's performance is quantitatively measured on all test images by calculating a mean square error. Results of the performance are compared with other additive noise filtering algorithms, such as local variance and median variance. Results, substantiated by analysis of variance, indicate that this new algorithm significantly reduces the additive noise and produces results as good as or better than other methods while preserving sharp edges in the image and also working better in the smooth areas.

Library of Congress Subject Headings

Image processing -- Digital techniques
Analysis of variance
Digital filters (Mathematics)




South Dakota State University