A classification package for remote sensing data /
"A picture is worth one thousand words". This Chinese proverb dates back to 2500 years ago gives us a quick glance of the importance of images and information that might be contained in it. With the advent of photography equipment and techniques combination to revolution of computer and di...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Information and Communication Technology, International Islamic University Malaysia,
2013
|
| Subjects: | |
| Online Access: | Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | "A picture is worth one thousand words". This Chinese proverb dates back to 2500 years ago gives us a quick glance of the importance of images and information that might be contained in it. With the advent of photography equipment and techniques combination to revolution of computer and digitalization in both hardware and software this importance takes another dimensions.This research is a trying to shade a light on the Multi-Spectral Image Classification and the importance of this field in Image processing. Two classification approaches were included, Supervised and Unsupervised Classification. Three types of supervised classification were explained, Minimum Distance (MD), Maximum Likelihood (ML), and Probabilistic Neural Network (PNN). Also two types of unsupervised classification were contained, K-Means (KM) and Kohonen Neural Network (KNN). The research involves design a package for Multi-Spectral Images classification. This includes reading 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 research used two types of classification methods one is a supervised method, which is Minimum Distance (MD) approach, and the second one is unsupervised method that is K-Means approach (KM). |
|---|---|
| Physical Description: | xii, 91 leaves : ill. ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 79-85). |