Cover Image

Naïve Bayes Classification Of High-Resolution Aerial Imagery

In this study, the performance of Naïve Bayes classification on a high-resolution aerial image captured from a UAV-based remote sensing platform is investigated. K-means clustering of the study area is initially performed to assist in selecting the training pixels for the Naïve Bayes classification....

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmad, Asmala, Sakidin, Hamzah, Abu Sari, Mohd Yazid, Mat Amin, Abd Rahman, Sufahani, Suliadi Firdaus, Rasib, Abd Wahid
Format: Article
Language:English
Published: Science and Information Organization 2021
Online Access:http://eprints.utem.edu.my/id/eprint/25657/2/IJACSA%20NA%C3%8FVE_BAYES.PDF
http://eprints.utem.edu.my/id/eprint/25657/
https://thesai.org/Downloads/Volume12No11/Paper_20-Na%C3%AFve_Bayes_Classification_of_High_Resolution_Aerial_Imagery.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utem.eprints.25657
record_format eprints
spelling my.utem.eprints.256572022-03-14T16:23:24Z http://eprints.utem.edu.my/id/eprint/25657/ Naïve Bayes Classification Of High-Resolution Aerial Imagery Ahmad, Asmala Sakidin, Hamzah Abu Sari, Mohd Yazid Mat Amin, Abd Rahman Sufahani, Suliadi Firdaus Rasib, Abd Wahid In this study, the performance of Naïve Bayes classification on a high-resolution aerial image captured from a UAV-based remote sensing platform is investigated. K-means clustering of the study area is initially performed to assist in selecting the training pixels for the Naïve Bayes classification. The Naïve Bayes classification is performed using linear and quadratic discriminant analyses and by making use of training set sizes that are varied from 10 through 100 pixels. The results show that the 20 training set size gives the highest overall classification accuracy and Kappa coefficient for both discriminant analysis types. The linear discriminant analysis with 94.44% overall classification accuracy and 0.9395 Kappa coefficient is found higher than the quadratic discriminant analysis with 88.89% overall classification accuracy and 0.875 Kappa coefficient. Further investigations carried out on the producer accuracy and area size of individual classes show that the linear discriminant analysis produces a more realistic classification compared to the quadratic discriminant analysis particularly due to limited homogenous training pixels of certain objects. Science and Information Organization 2021 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/25657/2/IJACSA%20NA%C3%8FVE_BAYES.PDF Ahmad, Asmala and Sakidin, Hamzah and Abu Sari, Mohd Yazid and Mat Amin, Abd Rahman and Sufahani, Suliadi Firdaus and Rasib, Abd Wahid (2021) Naïve Bayes Classification Of High-Resolution Aerial Imagery. International Journal of Advanced Computer Science and Applications, 12 (11). pp. 168-177. ISSN 2158-107X https://thesai.org/Downloads/Volume12No11/Paper_20-Na%C3%AFve_Bayes_Classification_of_High_Resolution_Aerial_Imagery.pdf 10.14569/IJACSA.2021.0121120
institution Universiti Teknikal Malaysia Melaka
building UTEM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknikal Malaysia Melaka
content_source UTEM Institutional Repository
url_provider http://eprints.utem.edu.my/
language English
description In this study, the performance of Naïve Bayes classification on a high-resolution aerial image captured from a UAV-based remote sensing platform is investigated. K-means clustering of the study area is initially performed to assist in selecting the training pixels for the Naïve Bayes classification. The Naïve Bayes classification is performed using linear and quadratic discriminant analyses and by making use of training set sizes that are varied from 10 through 100 pixels. The results show that the 20 training set size gives the highest overall classification accuracy and Kappa coefficient for both discriminant analysis types. The linear discriminant analysis with 94.44% overall classification accuracy and 0.9395 Kappa coefficient is found higher than the quadratic discriminant analysis with 88.89% overall classification accuracy and 0.875 Kappa coefficient. Further investigations carried out on the producer accuracy and area size of individual classes show that the linear discriminant analysis produces a more realistic classification compared to the quadratic discriminant analysis particularly due to limited homogenous training pixels of certain objects.
format Article
author Ahmad, Asmala
Sakidin, Hamzah
Abu Sari, Mohd Yazid
Mat Amin, Abd Rahman
Sufahani, Suliadi Firdaus
Rasib, Abd Wahid
spellingShingle Ahmad, Asmala
Sakidin, Hamzah
Abu Sari, Mohd Yazid
Mat Amin, Abd Rahman
Sufahani, Suliadi Firdaus
Rasib, Abd Wahid
Naïve Bayes Classification Of High-Resolution Aerial Imagery
author_facet Ahmad, Asmala
Sakidin, Hamzah
Abu Sari, Mohd Yazid
Mat Amin, Abd Rahman
Sufahani, Suliadi Firdaus
Rasib, Abd Wahid
author_sort Ahmad, Asmala
title Naïve Bayes Classification Of High-Resolution Aerial Imagery
title_short Naïve Bayes Classification Of High-Resolution Aerial Imagery
title_full Naïve Bayes Classification Of High-Resolution Aerial Imagery
title_fullStr Naïve Bayes Classification Of High-Resolution Aerial Imagery
title_full_unstemmed Naïve Bayes Classification Of High-Resolution Aerial Imagery
title_sort naïve bayes classification of high-resolution aerial imagery
publisher Science and Information Organization
publishDate 2021
url http://eprints.utem.edu.my/id/eprint/25657/2/IJACSA%20NA%C3%8FVE_BAYES.PDF
http://eprints.utem.edu.my/id/eprint/25657/
https://thesai.org/Downloads/Volume12No11/Paper_20-Na%C3%AFve_Bayes_Classification_of_High_Resolution_Aerial_Imagery.pdf
_version_ 1728055205625331712
score 13.251813

Similar Items