Search

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. (c) 2011 Elsevier B.V. All rights reserved.

In this paper we propose a new approach for visualization-oriented fusion of hyperspectral image bands. The proposed technique has been devised to generate the fused image with a certain set of desired properties for a better visualization. The fusion technique should provide a resultant image with a high local contrast without driving individual pixels into over- or under-saturation. We focus on these desired properties of the resultant image, and formulate a multi-objective cost function for the same. We have shown how we can incorporate the constraint of spatial smoothness of the weight vectors, as opposed to the smoothness of the fused image. The solution of this optimization problem has been provided using the Euler-Lagrange technique. By using an appropriate auxiliary variable, we show how the constrained optimization problem can be converted into a computationally efficient unconstrained one. The effectiveness of the proposed technique is substantiated from the visual and quantitative results provided.