Graphic STI
logo EPFL
text EPFL
english only
Biomedical Imaging Group
Algorithms
BIG > Algorithms > Steerable Wavelet Transform
CONTENTS

Home page

News & Events

People

Research

Publications

Tutorials & Reviews

Demos

Download Algorithms

Teaching

Steerable Wavelet Transform

Outline

References

Software

Related Works

Download

SteerableWavelets.zip

Plugin for ImageJ

[Beta Version, January 2014]

Steerable Wavelet Transform Toolbox

A complete parametric framework and set of JAVA tools for computing steerable wavelet frames in 2-D

Written by Virginie Uhlmann at the Biomedical Image Group (BIG), EPFL, Switzerland

Outline

The Steerable Wavelet Transform Toolbox is a JAVA library that implements a variety of 2D Steerable Wavelet Transforms as proposed in this reference paper. It contains a 2D implementation of the Riesz transform as well as a generic isotropic wavelet transform for both the pyramid and redundant decomposition schemes. Most of the commonly used isotropic profiles are available for the latter generic transform, namely Simoncelli, Meyer, Papadakis and Shannon decompositions. While shaping matrices describing standard cases of the Steerable Wavelet Transform such as the monogenic, gradient and Hessian signals are already implemented, any other matrix can be conveniently specified by the user. In addition to that, the Steerable Wavelet Transform Toolbox contains several standalone ImageJ plugins. It is hence possible to directly perform any isotropic wavelet transform or the Riesz transform on an input image via dedicated GUIs. Finally, a collection of plugins feature examples of use of the Steerable Wavelet Transform, such as monogenic signal analysis, symmetry centers detection and reconstruction from edges in wavelet domain.

As we aim at maintaining an application-oriented approach in our research, we commit ourselves to develop working versions of the algorithms we propose as plugins for ImageJ, a free, open-source software widely used by the biology community. This motivates the present JAVA toolbox, which is based on Zs. Püspöki's Matlab implementation of the same framework.

This work is supported by the European Research Council under Grant ERC-2010-AdG 267439-FUN-SP.

References

Technical Explanations

We point the reader to M. Unser and N. Chenouard's paper on which the implementation was based for theoretical details. The developer of the present Toolbox will be happy to answer via e-mail any question regarding the JAVA implementation.

Software

ImageJ prerequirement

The Steerable Wavelet Toolbox contains JAVA tools for computing steerable wavelet frames, as well as several dedicated plugins for ImageJ, a general purpose image-processing and image-analysis package. ImageJ has a public domain licence; it runs on several plateforms: Unix, Linux, Windows, Mac OS 9 and Mac OS X. It doesn't take more than a couple of minutes to install.

Download and install

The Steerable Wavelets Toolbox for ImageJ is currently under development, and latest versions might be unstable. For this reason, the download link on the left is not active yet. All the sources are however always available upon request. Users or developers willing to obtain the code in its current state are welcome to send an e-mail to the developer. The Steerable Wavelets Toolbox also requires some external libraries that will be provided along with the sources.

Conditions of use

You'll be free to use this software for research purposes, but you must not transmit and distribute it without our consent. In addition, you undertake to include a citation to the associated papers whenever you present or publish results that are based on it. EPFL makes no warranties of any kind on this software and shall in no event be liable for damages of any kind in connection with the use and exploitation of this technology.

Related Works

© 2014 EPFL • webmaster.big@epfl.ch • 30.01.2014