Multispectral image fusion for improved RGB representation based on perceptual attributes
- 10 August 2005
- journal article
- research article
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 26 (15) , 3241-3254
Abstract
A pixel‐level fusion technique for RGB representation of multispectral images is proposed. The technique results in highly correlated RGB components, a fact which occurs in natural colour images and is strictly related to the colour perception attributes of the human eye. Accordingly, specific properties for the covariance matrix of the final RGB image are demanded. Mutual information is employed as an objective criterion for quality refinement. The method provides dimensionality reduction, while the resulting RGB colour image is perceptually of high quality. Comparisons with existing techniques are carried out using both subjective and objective measures.Keywords
This publication has 15 references indexed in Scilit:
- Principal-components-based display strategy for spectral imageryIEEE Transactions on Geoscience and Remote Sensing, 2003
- Perceptual evaluation of different image fusion schemesDisplays, 2003
- Fusion of 2D grayscale images using multiscale morphologyPattern Recognition, 2001
- Real‐time multi‐spectral image fusionConcurrency and Computation: Practice and Experience, 2001
- Pattern-selective color image fusionPattern Recognition, 2001
- Image fusion by using steerable pyramidPattern Recognition Letters, 2001
- Objective image fusion performance measureElectronics Letters, 2000
- Review article Multisensor image fusion in remote sensing: Concepts, methods and applicationsInternational Journal of Remote Sensing, 1998
- Application of Morphological Pyramids: Fusion of MR and CT PhantomsJournal of Visual Communication and Image Representation, 1995
- Comparative digital analysis of Seasat-SAR and Landsat-TM data for IcelandInternational Journal of Remote Sensing, 1991