Comparative Analysis of Image Fusion Techniques

Abstract

The relevance of multispectral image fusion problem during search and rescue operations is shown. Well-known algorithms for multispectral image fusion are considered and implemented. The comparison involved algorithms based on averaging, maximum method, analysis of low and high frequency components, assessment of information content, addition of differences, extraction of local contrasts, Laplace pyramid, wavelet transform, principal component analysis, 3D low pass filter, power transformation, tv channel priority, Pytyev morphology, diffuse morphology and local weighting summation. Based on publicly available multispectral image datasets, a combined database to compare the algorithms considered including 496 pairs of images has been compiled. The results of image fusion using the considered algorithms are obtained. The aim of the work is to compare well-known image fusion algorithms in terms of objective quality metric. The comparison of fusion results was carried out according to combined quality metric. Based on comparison results, the authors concluded that the best values of combined quality metric for multispectral image fusion are provided by the algorithms based on local weight summation, principal component analysis and Laplace pyramid.