Unsupervised Pixel Classification in Satellite Imagery Using Artificial Neural Network

Abstract

The resolution of remote sensing images increases every day, raising the level of detail and the heterogeneity of the scenes. Most of the existing geographical information systems classification tools have used the same methods for years. With these new high-resolution images, basic classification methods do not provide satisfactory results. In this paper, we have implemented two different algorithms namely K-means Algorithm and Back Propagation Algorithm for Segmentation and Classification of Satellite images. Wide database of images has been used to test both the algorithms. The paper also shows the comparison of the results obtained by implementing both algorithms. The comparison of results shows good accuracy in both the methods.