A Comparative Analysis of SVM, K-NN and Decision Trees for High Resolution Satellite Image Scene Classification

摘要

In this paper, we evaluate and compare the performance of three machine learning classifiers: Support VectorMachines (SVM), Decision Trees (DT) and K-Nearest Neighbor (K-NN) for high resolution satellite image sceneclassification.This study aims at providing insights into the selection of the appropriate classifier and highlighting theimportance of the appropriate setting of the classifier parameters. We illustrate these issues through applying sceneclassification to UC-Merced high resolution satellite image dataset. Image features are obtained through the SURFdescriptor and BOVW model.