Innate and Artificial entity Recognition on Satellite Images by Level Set Evolution and Knn Classification

Enhancing Entity Recognition in Satellite Images using Level Set Evolution and KNN Classification

Abstract

Extraction of entities from image is one of the desired and important steps in image processing. Entity extraction from image is playing a vital role in many areas. To work with satellite images for cropping some useful entity body is very much desired motive in mapping and surveying area. Many improvements have been done in this area and some are in progress. The past work has been done for section same kind of items and some demonstrations have been done for enhancing its productivity, effectiveness and its efficiency. Here we classify both kinds of entities i.e, natural or artificial entities from the images got from satellite. Level set evolution (LSE) is being used for clipping out artificial entities from remote sensing images. Level set evolution (LSE) offers effective outcomes for clipping physiographical changes. We have used some geometrical features and texture features for feature extraction and K-nearest neighbor classification for classification of artificial and natural entities which gave us better output performance and we have calculated precision, recall, accuracy and finalized our paper with some important conclusions and appropriate results.