An unsupevised package for multi-spectral image processing for remote data

• Main Authors: Zaid, Muhsin A., Zeki, Akram M.
• Format: Article
• Language: English
• Published: Design for Scientific Renaissance 2015
• Subjects: T Technology (General)
• Online Access: http://irep.iium.edu.my/49596/1/1249-2938-1-PB.pdf; http://irep.iium.edu.my/49596/; http://www.sign-ific-ance.co.uk/index.php/JACSTR/article/view/1249

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.