期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：2
页码：2074-2076
出版社：TechScience Publications
摘要：This paper includes a prospective approach of developing an efficient algorithm for classification of remotely sensed images. Image classification is the first and foremost step in remote sensing applications. Classification using SVM is a efficient technique which when optimized with the particle swarm intelligence will yield better classification accuracy. The main focus will be on the boundary pixels that are misclassified by standard SVM and other conventional methods.
