Abstract: Image Segmentation is one of the emerging trends in the field of image processing. It has found applications in the field of satellite imagery, medical applications etc. Image segmentation helps in the segment the images into sub-regions which are of our interest which can be analyzed individually. Mechanically detecting buildings from satellite images has a lot of potential applications, from monitoring movements of populations in remote areas to evaluating the available surface to implant solar panels on roofs. Image segmentation is the basic step to analyze images and extract data from them. Along with the various image processing techniques in the image, segmentation is edge detection, Thresholding, region growing, and clustering is used to segment the images. The image Segmentation algorithms are based on two properties similarity and discontinuity. These papers focuses on the various methods that are K-means Clustering, Back Propagation Algorithm of ANN, U-net algorithm, Thresholding technique and active Contours for satellite image segmentation and evaluate the best method in satellite image segmentation using various performance parameters like Correlation Ratio and segmentation accuracy widely used to segment the image.

Keywords: Segmentation, Edge detection, Thresholding, Back Propagation, Clustering, Region Growing

| DOI: 10.17148/IARJSET.2018.5115