Javascript must be enabled for the correct page display

Matching of images by maximization of mutual information

Schraal, W.H. (1998) Matching of images by maximization of mutual information. Master's Thesis / Essay, Computing Science.

Infor_Ma_1998_WHSchraal.CV.pdf - Published Version

Download (1MB) | Preview


Medical images play an important role in hospitals. The information in the images helps to make a diagnose of the illness of a patient. Different types of images provide the medical staff with different information. Combining the information gives a more complete picture of the situation a patient is in. It would be nice to merge all information into one image. Before merging can be done, the information that different images have about a certain feature has to be spatially aligned. The process of aligning the information in two images is what we call matching. Mutual information, which is known from information theory, is used to measure how well two images match. The mutual information is maximal when the images match best. A property of the mutual information is that it is intensity independent, which is important because a certain feature will have different pixel values in images originating from different sources. Two optimization algorithms have been used to find the maximum of the mutual information. To speed up the matching process, random downsampling of the images is used.

Item Type: Thesis (Master's Thesis / Essay)
Degree programme: Computing Science
Thesis type: Master's Thesis / Essay
Language: English
Date Deposited: 15 Feb 2018 07:29
Last Modified: 15 Feb 2018 07:29

Actions (login required)

View Item View Item