Weed classification using one class support vector machine

Weed classification using one class support vector machine

Weed classification a necessity in identifying species of weeds to control management practice in agricultural systems, which are essential for maintaining crop productivity and quality. Many classification techniques were used to identify weeds based on images, and most of the techniques using a bi...

Full description

Bibliographic Details
Published in:2017 International Conference on Electrical, Electronics and System Engineering, ICEESE 2017
Main Author: Shahbudin S.; Zamri M.; Kassim M.; Abdullah S.A.C.; Suliman S.I.
Format: Conference paper
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2017
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050503666&doi=10.1109%2fICEESE.2017.8298404&partnerID=40&md5=aef6ba7fdb54749c8d0e7b33dea4eda1
id 2-s2.0-85050503666
spelling 2-s2.0-85050503666
Shahbudin S.; Zamri M.; Kassim M.; Abdullah S.A.C.; Suliman S.I.
Weed classification using one class support vector machine
2017
2017 International Conference on Electrical, Electronics and System Engineering, ICEESE 2017
2018-January

10.1109/ICEESE.2017.8298404
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050503666&doi=10.1109%2fICEESE.2017.8298404&partnerID=40&md5=aef6ba7fdb54749c8d0e7b33dea4eda1
Weed classification a necessity in identifying species of weeds to control management practice in agricultural systems, which are essential for maintaining crop productivity and quality. Many classification techniques were used to identify weeds based on images, and most of the techniques using a binary Support Vector Machine (SVM) for measuring the percentage of accuracy. No visualization of decision boundary is illustrated to prove the best performances. To analyzing weed pattern images using One Class Support Vector Machine (SVM), feature vectors of weed images extracted using Gabor Wavelet and Fast Fourier Transform (FFT) were applied. The decision boundaries of the combination extracted feature vectors are visualized and optimal feature vectors are identified. The proposed method also improve the accuracy rate in weed classification task. © 2017 IEEE.
Institute of Electrical and Electronics Engineers Inc.

English
Conference paper
author Shahbudin S.; Zamri M.; Kassim M.; Abdullah S.A.C.; Suliman S.I.
spellingShingle Shahbudin S.; Zamri M.; Kassim M.; Abdullah S.A.C.; Suliman S.I.
Weed classification using one class support vector machine
author_facet Shahbudin S.; Zamri M.; Kassim M.; Abdullah S.A.C.; Suliman S.I.
author_sort Shahbudin S.; Zamri M.; Kassim M.; Abdullah S.A.C.; Suliman S.I.
title Weed classification using one class support vector machine
title_short Weed classification using one class support vector machine
title_full Weed classification using one class support vector machine
title_fullStr Weed classification using one class support vector machine
title_full_unstemmed Weed classification using one class support vector machine
title_sort Weed classification using one class support vector machine
publishDate 2017
container_title 2017 International Conference on Electrical, Electronics and System Engineering, ICEESE 2017
container_volume 2018-January
container_issue
doi_str_mv 10.1109/ICEESE.2017.8298404
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050503666&doi=10.1109%2fICEESE.2017.8298404&partnerID=40&md5=aef6ba7fdb54749c8d0e7b33dea4eda1
description Weed classification a necessity in identifying species of weeds to control management practice in agricultural systems, which are essential for maintaining crop productivity and quality. Many classification techniques were used to identify weeds based on images, and most of the techniques using a binary Support Vector Machine (SVM) for measuring the percentage of accuracy. No visualization of decision boundary is illustrated to prove the best performances. To analyzing weed pattern images using One Class Support Vector Machine (SVM), feature vectors of weed images extracted using Gabor Wavelet and Fast Fourier Transform (FFT) were applied. The decision boundaries of the combination extracted feature vectors are visualized and optimal feature vectors are identified. The proposed method also improve the accuracy rate in weed classification task. © 2017 IEEE.
publisher Institute of Electrical and Electronics Engineers Inc.
issn
language English
format Conference paper
accesstype
record_format scopus
collection Scopus
_version_ 1809677606118752256

Similar Items