<%@ 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-351

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

Guo-Huei Chen and Roland Wilson, Image Segmentation Based on the Multiresolution Fourier Transform and Markov Random Fields (October 15, 1998).

Abstract

In this work, the Multiresolution Fourier Transform (MFT) and Markov Random Fields (MRFs) are combined to produce as a tool for image segmentation. Firstly, a Laplacian Pyramid is used as a high-pass filter. Then, the MFT is applied in order to segment images based on the analysis of local properties in the spatial frequency domain. A methodology for edge detection in image segmentation in the Bayesian framework using Markov random field models is then developed. Stochastic Relaxation is also adopted to maximise the likelihood and find the globally minimum energy states using simulated annealing.

Download

cs-rr-351.ps.gz

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