<%@ 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-226

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

Tao-I Hsu, A.D. Calway and R.G. Wilson, Analysis of Structured Texture Using the Multiresolution Fourier Transform (June 1, 1992).

Abstract

A multiresolution approach to the analysis of structural texture is presented. The multiresolution Fourier transform (MFT) is utilized as a framework to derive a robust algorithm which estimates textural features over a range of spatial scales based on local frequency domain properties. A pair of centroids of local spectra are extracted to represent the dominant frequencies of underlying spatial regions which are equivariant to rotation and scaling. Based on these centroids, the relationship between two different local spectra is characterized by an affine transformation. Assessment of the estimated affine transform is made by normalized correlation, which also provides local phase shift information. Analysis and synthesis of both artificial and natural images demonstrate the capability of the algorithm.

Download

The report may be downloaded in five parts: cs-rr-226.1.ps.gz, cs-rr-226.2.ps.gz, cs-rr-226.3.ps.gz, cs-rr-226.4.ps.gz, cs-rr-226.5.ps.gz

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