An Empirical Investigation on Thematic Accuracy of Landuse/Landcover Classification Using Fused Images

The satellite images at different spectral and spatial resolutions with the aid of image processing techniques can improve the quality of information. Especially image fusion is very helpful to extract the spatial information from two images of different resolution images of same area. An operation of image analysis such as image classification on fused images provides better results in comparison of original data. The comparisons of various fusion techniques have been discussed and their accuracies have been evaluated on their respected classifications. By using the digital image classification techniques such as supervised and unsupervised classification methods, the study reveals that all the fused images have higher information than the original images. In this study to demonstrate the enhancement and accuracy assessment of fused image over the Multispectral images using ERDAS Imagine 9.1 Software.