<%@ page language="java" contentType="text/html" %> <%-- Include common initialisation code --%> <%@ include file="/arch/common.jsp" %> <%-- The current tab --%> <% String currentTab = "Research"; %> <%-- Content of navigation pane --%> <%@ include file="nav.jsp" %> <% showCurrentLink=true; %> <%-- Current navigation location --%> <% String currentNav = "Reports and Theses"; %> <%-- Include the code for the document header --%> <%@ include file="/arch/header.jsp" %>

Research Report CS-RR-398

<%-- Include the code for the lines and navigation --%> <%@ include file="/arch/middle.jsp" %>

Constantino Carlos Reyes-Aldasoro, A Guide to Co-occurrence Matrix Analysis, (February 19, 2004).

Abstract

This report considers the analysis of the co-occurrence matrix that has been widely used in many texture analysis problems. The co-occurrence matrix was first presented by Haralick and since then, many researches have used it in a variety of applications. Though simple in concept and powerful, it has a great computational burden, first for the size of the matrix depends on the number of grey levels of the original image, second because of the number of features that can be extracted from the matrix. Many of these features would not be useful at a discrimination process. The report focuses in the analysis of the matrices and features for several binary and natural textures. Finally a human knee MRI is segmented with a set of features that is selected with the use of the Bhattacharyya distance as a measure of discrimination.

Download

cs-rr-398.pdf

<%-- Include the code for the document footer --%> <%@ include file="/arch/footer.jsp" %>