A novel approach to quantitative evaluation of hyperspectral image fusion techniques

Authors:
Ketan Kotwal;Subhasis Chaudhuri
Affiliations:
Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India;Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India
Venue:
Information Fusion
Year:
2013

Citing 8
Cited 2

Multisensor image fusion using the wavelet transform

Graphical Models and Image Processing
Remote Sensing, Third Edition: Models and Methods for Image Processing

Remote Sensing, Third Edition: Models and Methods for Image Processing
Guest editorial: Image fusion: Advances in the state of the art

Information Fusion
Pixel- and region-based image fusion with complex wavelets

Information Fusion
Theoretical analysis of an information-based quality measure for image fusion

Information Fusion
A fast approach for fusion of hyperspectral images through redundancy elimination

Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
Divergence measures based on the Shannon entropy

IEEE Transactions on Information Theory
Multispectral image visualization through first-order fusion

IEEE Transactions on Image Processing

Objective evaluation of noisy multimodal medical image fusion using Daubechies complex wavelet transform

Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing
A Bayesian approach to visualization-oriented hyperspectral image fusion

Information Fusion

Quantified Score

Hi-index	0.00

Visualization

Abstract

In recent years, several image fusion techniques have been proposed to cater to various objectives. An appropriate visualization of the data is one of the key objectives of image fusion, particularly in case of hyperspectral images where the number of bands are far more than those can be displayed on standard tristimulus display. While a few techniques that address the issue of visualization of hyperspectral data can be seen in the literature, the evaluation of performances of these different techniques is still an open problem. In this paper, we first introduce a notion called fusion consistency and we suggest that the fusion techniques should satisfy the consistency criterion under appropriate measures that evaluate the fusion performance. We also propose several modifications for a number of existing measures that can quantify the progression of fusion operation efficiently for the fusion of a large number of image bands. We use these observations to validate suitability of any given technique for fusion of hyperspectral images.