Investigations on satellite images For classification using intelligent Soft computing techniques

Abstract

Satellite Image segmentation and classification is common but still very challenging problem in the area of satellite image processing but it has its application in many industries and medical field. For example target tracking, object recognition and medical image processing. The task of image segmentation is to divide image into number of meaningful pieces on the basis of features of image such as color and texture. Satellite Image classification is the way of adjusting at least two pictures of a similar scene taken at various times from multiple perspectives by different sensors. It is broadly utilized as a part of PC vision applications. Several image processing approaches have been designed to enhance the illustration of remote sensing images and to remove the required data from the remote images. A wide range of superpixel segmentation calculations have been proposed to address the issues of different applications. The attractive properties of superpixel segmentation has the characteristic of image boundary extraction using superpixel enhancement. Then the minimum error is produced by the preprocessing strategy using various types of filters and enhancement of low randomness pixels. This research work proposes a satellite image classification strategy by assessing two different vulnerabilities. The framework state incorporates position and introduction of all perspectives to enhance the worldwide consistency. The area and presentation of point have been evaluated with superpixel segmentation algorithm and hyper graph structure strategies used to process the global transformation in the comparing image. This procedure demonstrates a programming, accomplishing better accuracy and dynamically reconfigurable image registration in diminished complexity newline