<%@ 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-170

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

A.R. Davies and R.G. Wilson, Linear Feature Extraction using the Multiresolution Fourier Transform (November 1, 1990).

Abstract

A hierarchical space-time image representation - the Multiresolution Fourier Transform (MFT) - is discussed, and its properties are used in order to define a spectrum based model for the class of simple linear features, such as straight lines and edges. The model is used to derive a method of identifying these features and estimating their parameters, ie position and orientation. Results are presented for this process using a test image. The effect of white noise is considered, and a correlation measure is defined to show the effect of the noise upon the model. A method of further improving the results for a noisy image, by smoothing with oriented ellipses is also considered.

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