A region of interest (often abbreviated ROI), is a selected subset of samples within a dataset identified for a particular purpose. The concept of an ROI is commonly used in many application areas. For example, in medical imaging, the boundaries of a tumor may be defined on an image or in a volume, for the purpose of measuring its size. The endocardial border may be defined on an image, perhaps during different phases of the cardiac cycle, for example end-systole and end-diastole, for the purpose of assessing cardiac function. In geographical information systems (GIS), an ROI can be taken literally as a polygonal selection from a 2D map. Previous works for ROI detection in remote sensing images are inaccurate and prohibitively computationally complex. Hence we propose region-of-interest extraction method based on frequency domain analysis and salient region detection (FDA-SRD) method for ROI extraction. For this, the images are converted from RGB to HIS as preprocessing. The saliency driven image resulting scale space in general preserves or even enhances semantically important structures such as edges, lines, or flow-like structures in the foreground, and inhibits and smoothest clutter in the background. The image is reconstructed using fusion based on the original image, the image at the final scale at which the diffusion process converges, and the image at a midscale. Our algorithm emphasizes the foreground features, which are important for image classification. The background image regions, whether considered as contexts of the foreground or noise to the foreground, can be globally handled by fusing information from different scales.