Research On The Fusion Of Infrared And Visible Images Based On The NSCT Transform

This paper combined with the application need of image fusion studied deeply about the the infrared image and visible image fusion algorithm by NSCT. infrared and visible image fusion algorithm based on a combination of NSCT transform and wavelet transform is proposed.And the further details of the transformation theory of NSCT is introduced.This paper studies NSCT transform based image fusion algorithm .For NSCT transform can extract a good approximation of the advantages of image edge contour information, At high and low frequency coefficients of the edge-based fusion rule and the variance based on the improved integration of regional rules is studied.By analyzing the experimental results , This article on how to maximize the retention following the results of spectral information fusion, at the same time the amount of information fusion and clarity is the next step is to improve the content of the study.Transformation for a single image fusion based on NSCT not a good image of the spectral information extraction,HIS transform can efficiently separate the visible light spectrum information. NSCT transform and proposed based on HIS transform infrared and visible image fusion algorithm. A large number of experiments show that, the fusion algorithm, on the one hand improve the integration of the results of spectral information content. at the same time more clear fused image, However, the integration of the results of this algorithm and clarity of information has not been significantly improved.For NSCT is not a very good performance characteristics of the image of local changes and wavelet transform is not a good expression for image edge information, wavelet-based image fusion algorithm by NSCT is proposed in this paper. Combination of the two transform their purpose is to take advantage of , Meanwhile, the fusion rule also proposes a new method of regional variance. Large number of experimental data show that using the fusion rule, fused to better target information and spectral information retained, show that the algorithm has the strong advantage .