An Unsupevised Package for Multi-Spectral Image Processing for Remote Data

Abstract

 The ability to match digital images and technique combination in the computer world had revolutionalised the trend. This paper researched on the unsupervised classification of the Multi-Spectral Image. All the two classes under the unsupervised classification were presented and explained. That is the K-Means (KM) and Kohonen Neural Network (KNN). A package for Multi-Spectral Images is designed with the ability to read data, apply Principal Component Analysis (PCA) as a feature extraction, then apply False Colour Composite (FCC) as one of the classification techniques in multi-spectral images. The unsupervised classification method is considered throughout in this research.

An Unsupevised Package for Multi-Spectral Image Processing for Remote Data