Scribd
Upload
27 views2 pages

ReadMe PDF

This document describes a toolbox for fusing multi-exposure and multi-focus images in the gradient domain. The toolbox can fuse both grayscale and color images with an arbitrary number of input images. It implements an algorithm that computes the gradients of the input images, generates a fused gradient, and then reconstructs the fused image from the gradient domain using a wavelet-based technique. The document provides references to papers describing the algorithm and reconstruction method.

Uploaded by

avi0341
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
27 views2 pages

ReadMe PDF

This document describes a toolbox for fusing multi-exposure and multi-focus images in the gradient domain. The toolbox can fuse both grayscale and color images with an arbitrary number of input images. It implements an algorithm that computes the gradients of the input images, generates a fused gradient, and then reconstructs the fused image from the gradient domain using a wavelet-based technique. The document provides references to papers describing the algorithm and reconstruction method.

Uploaded by

avi0341
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Multi-exposure and Multi-focus Image Fusion in Gradient Domain

Version 1.0
Sujoy Paul1, I.S. Sevcenco2, P. Agathoklis2
1

Department of Electronics and Telecommunication Engineering, Jadavpur University, Kolkata, India

Department of Electrical and Computer Engineering, University of Victoria, Victoria, B.C., Canada

Introduction
In this toolbox, an algorithm for the fusion of multi-exposure and multi-focus images has been
implemented.This toolbox may be used for the fusion of both single channel (gray scale) images,
as well as multi-channel (RGB) images, and can handle the fusion of an arbitrary number of
images (at least two).
The fusion of the images is done in the gradient domain, and then the reconstruction of the fused
image from the gradient domain is done using a wavelet based method proposed in [2].
The details regarding the algorithm are detailed in [1]. This file will be completed with the full
reference and a link to the paper as soon as it gets accepted for publication.

List of functions and files


Demo.m

This file is a short demo meant to familiarize the user with the setup
required in order to use the toolbox and its functionsto fusea set of
images. Executing this code illustrates the fusion of a setof multiexposure imagesincluded in Matlabnamed office.

GradientFusion.m

This is the main function file usedfor the fusion of the images. This
function takes as input a stack of images and outputs the fused image.

getGradientH.m

This function is to compute the gradient of the input images.

getFusedGradients.m

This function is used to generate the one channel (luminance


channel) fusion of the gradients of the input images

ReconstructGradient.m This function reconstructs the image from the gradient domain, using
a wavelet based technique coupled with Poisson solver at each
resolution to remove artifacts. Detailed code with description of this
reconstruction method is available at [3]
ChannelNorm.m

This function uses a non-linear transformation to normalizing a


single channel image from its input range to a required range.

References
[1] S. Paul, I.S. Sevcenco, P. Agathoklis, "Multi-exposure and Multi-focus image fusion in
gradient domain", submitted for publication
[2] I.S. Sevcenco, P.J. Hampton, P. Agathoklis, "A wavelet based method for image
reconstruction from gradient data with applications", Multidimensional Systems and Signal
Processing, November 2013
[3] Matlab File Exchange, Link: http://www.mathworks.com/matlabcentral/fileexchange/48066wavelet-based-image-reconstruction-from-gradient-data

You might also like