Document Type


Date of Award


Degree Name

Master of Science in Computer and Information Science - (M.S.)


Computer and Information Science

First Advisor

Frank Y. Shih


Neural network can be applied on the image enhancement after adding another two layers into the Adaptive Resonance Theory architectures (ART 1). The analysis for selecting a nice training pattern set associate the appropriate vigilance values is the main concerns in this thesis. For a single training pattern ,the network can act as a mathematical morphology operators such as erosion , dilation, opening and closing. With more than one training patterns in the network, 16 experiments are tested and are compared to each other in order to find the best selection for doing the image enhancement work. With both the training pattern set and vigilance values fixed, the first iteration always show the best performance than the other iterations. The comparison between 16 experiments explores the criteria for selecting the better training pattern set. Increasing the local features in the network training and a little bit "flexibility" of the vigilance parameter can increase the performance of the image enhancement. With the vigilance changed in different iterations also can be the good way to choose the training pattern set.



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.