Description

Extraction of map objects such roads, rivers and buildings from high resolution satellite imagery is an important task in many civilian and military applications. Here we classify 7 No. of classes from satellite images by using fuzzy logic based classification. In this, before classification we segment the satellite images into seven classes by using SOM segmentation. With the segmented result of satellite image, we extract textural features of segmented image by using GLCM feature extractor. With this feature values we classify the 7 classes in the given image and finally we represent the 7 different classes in 7 different colors.