Digital Image Processing: Principles and Applications

Abstract

Digital image processing is an important part in digital analysis of remote sensing data. It allows one to enhance image features of interest while attenuating irrelevant features of a given application and then extract useful information about the scene from the enhanced image. It comprises the four basic steps, which include image correction/restoration, image enhancement, image transformation, and image classification. Image restoration is basically aimed to compensate the data errors, noise, and geometric distortions introduced during the scanning, recording, and playback operations. Image enhancement helps to alter the visual impact that the image has on the interpreter, that improve the information content and information extraction ability by utilizing the decision-making capability of the computer in order to recognize and classify the pixels on the basis of their digital signatures. The information extracted by comparing two or more images of an area that were acquired at different times. Unsupervised classification distinguish the patterns in the reflectance data and groups them into a pre-defined number of classes without any prior knowledge of the image. Whereas, in supervised classification, the user trains the computer, guiding it what type of spectral characteristics to look for and what type of land cover they represent, and guides the image processing software how to classify certain features. Change-detection analysis provides information about the changes in different seasons or dates. In post-classification analysis, image smoothing and accuracy assessment are important to generate the output from digital image processing.