An Improved Integrated Intensity-Hue-Saturation with Stationary Wavelet Transform Multi-sensor Image Fusion Approach

Abstract

Image fusion aims to retrieve information data from a set of multiple images into a composite output image. Pan-sharpen is the method of combining a high spatial resolution panchromatic (PAN) image and a high spectral resolution multispectral (MS) data of the same scene. It is not only beneficial for enhancing the spatial contents but also to preserve its spectral quality to be more useful for interpretation. Intensity-Hue-Saturation (IHS) transform is a commonly performed method for image fusion, but it causes some spectral distortion. A proposed hybrid approach applies IHS fusion with a Stationary Wavelet Transform (SWT) because the recent usually preserves the color information via multilevel decomposition. By using different fusion rules, for combining the corresponding approximation and details coefficients obtained from wavelet decompositions, a coefficient combining, and activity level measurement based fusion rules are executed. The main characteristic of the composite platform is utilizing the features of the combined algorithms with different fusion rules into a single image. The fusion results are evaluated and compared with results by conventional fusion techniques. Choosing the optimum fusion rules counts on the imageries set and depending upon the application. Visual inspection and quantitative analysis demonstrate that successful results among the different fusion methods.