Title
An approach for hyperspectral image classification by optimizing SVM using self organizing map.
Abstract
•This paper gives an efficient technique for the classification of Hyper-Spectral images, based on the concept of optimizing Support Vector Machine(SVM) using Self Organizing Maps(SOM).•Objective of this research is to improve the recognition of pixels with a degree of uncertainty and improve the classification results.•We also calculate the posterior probability of each pixel and compare with the threshold value.
Year
DOI
Venue
2018
10.1016/j.jocs.2017.07.016
Journal of Computational Science
Keywords
Field
DocType
Self organizing Map(SOM),Support vector Machine(SVM),Classification,Hyper-spectral image
Hyperspectral image classification,Data mining,Confusion matrix,Computer science,Support vector machine,Self-organizing map,Posterior probability,Pixel
Journal
Volume
ISSN
Citations 
25
1877-7503
1
PageRank 
References 
Authors
0.36
5
7