Please use this identifier to cite or link to this item:
|Performance evolution of improvement in change detection techniques based on edge enhanced images
|DIP;Edge Detection;Change Detection;PSNR;ECED
|Digital Image Processing is the branch of Digital Signal Processing in which, various Image Processing algorithms are applied on digital images. Digital Image Processing allows the use of much more complex algorithms and hence, can offer both sophisticated performance at simple tasks and the implementation of methods which would be impossible by analog means. Satellite images are the images of the whole or part of the earth taken using artificial satellites. Satellite images can either be visible light images, water vapour images or infrared images. Image Change Detection is a very important parameter in Digital Image Processing. Image Change Detection is the process of finding pixels of two images of same area taken at different times, which corresponds to real changes. Without Image Change Detection algorithms, it is very difficult to detect the changes in the earth’s geographical areas and also in the other applications like missing part of the organ in medical imaging. Another important parameter in Digital Image Processing is Edge Detection. Edges extracts features like corners, line etc. from an image. Edges are generally defined as the lines present in the picture. Various steps to identify edge in an image are smoothing, enhancement, detection, localization. Sobel operator, Prewitt operator, Compass Edge detection, Zero Crossing and Unsharp are some techniques to detect the edges. Its applications include automated driving and many machine vision systems etc. In this research work, first of all satellite images are enhanced using Edge Detection algorithms and after that Image Change Detection algorithms are applied on enhanced images to detect the better change. The best result is obtained by applying Unsharp edge enhancement operator on satellite images and then calculating the difference between those enhanced satellite images using Image Mean Ratio change detection algorithm and achieved an improvement of 4.356 dB.
|Appears in Collections:
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.