Weed detection system using support vector machine

Asnor Juraiza Ishak, Mohd. Marzuki Mustafa, Noritawati Md Tahir, Aini Hussain

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

In the oil palm plantation in Malaysia, typically blanket spraying is applied to a whole field without regard to the species and location of the weeds in the field. This practice is uneconomical since some areas where no or few weeds exist will receive just as much herbicides as those areas with high densities of weed infestation. Many of these chemical are soil-applied herbicides which easily absorb to ground water and surface water supplies. To control the weed grow and to solve the problems, automatic weed detection system need to be employed. This paper presents the results of automatic classification of broad and narrow weed using feature vector extracted using a combination of Gabor filter and FFT, and classifier using the support vector machine (SVM) Results obtained revealed that the proposed technique results in higher classification accuracy compared to other techniques.

Original languageEnglish
Title of host publication2008 International Symposium on Information Theory and its Applications, ISITA2008
DOIs
Publication statusPublished - 2008
Event2008 International Symposium on Information Theory and its Applications, ISITA2008 - Auckland
Duration: 7 Dec 200810 Dec 2008

Other

Other2008 International Symposium on Information Theory and its Applications, ISITA2008
CityAuckland
Period7/12/0810/12/08

Fingerprint

Herbicides
Support vector machines
Gabor filters
Palm oil
Spraying
Surface waters
Water supply
Fast Fourier transforms
Groundwater
Classifiers
Soils

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Ishak, A. J., Mustafa, M. M., Tahir, N. M., & Hussain, A. (2008). Weed detection system using support vector machine. In 2008 International Symposium on Information Theory and its Applications, ISITA2008 [4895454] https://doi.org/10.1109/ISITA.2008.4895454

Weed detection system using support vector machine. / Ishak, Asnor Juraiza; Mustafa, Mohd. Marzuki; Tahir, Noritawati Md; Hussain, Aini.

2008 International Symposium on Information Theory and its Applications, ISITA2008. 2008. 4895454.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ishak, AJ, Mustafa, MM, Tahir, NM & Hussain, A 2008, Weed detection system using support vector machine. in 2008 International Symposium on Information Theory and its Applications, ISITA2008., 4895454, 2008 International Symposium on Information Theory and its Applications, ISITA2008, Auckland, 7/12/08. https://doi.org/10.1109/ISITA.2008.4895454
Ishak AJ, Mustafa MM, Tahir NM, Hussain A. Weed detection system using support vector machine. In 2008 International Symposium on Information Theory and its Applications, ISITA2008. 2008. 4895454 https://doi.org/10.1109/ISITA.2008.4895454
Ishak, Asnor Juraiza ; Mustafa, Mohd. Marzuki ; Tahir, Noritawati Md ; Hussain, Aini. / Weed detection system using support vector machine. 2008 International Symposium on Information Theory and its Applications, ISITA2008. 2008.
@inproceedings{2e15320b00984b379a9c605e534fffae,
title = "Weed detection system using support vector machine",
abstract = "In the oil palm plantation in Malaysia, typically blanket spraying is applied to a whole field without regard to the species and location of the weeds in the field. This practice is uneconomical since some areas where no or few weeds exist will receive just as much herbicides as those areas with high densities of weed infestation. Many of these chemical are soil-applied herbicides which easily absorb to ground water and surface water supplies. To control the weed grow and to solve the problems, automatic weed detection system need to be employed. This paper presents the results of automatic classification of broad and narrow weed using feature vector extracted using a combination of Gabor filter and FFT, and classifier using the support vector machine (SVM) Results obtained revealed that the proposed technique results in higher classification accuracy compared to other techniques.",
author = "Ishak, {Asnor Juraiza} and Mustafa, {Mohd. Marzuki} and Tahir, {Noritawati Md} and Aini Hussain",
year = "2008",
doi = "10.1109/ISITA.2008.4895454",
language = "English",
isbn = "9781424420698",
booktitle = "2008 International Symposium on Information Theory and its Applications, ISITA2008",

}

TY - GEN

T1 - Weed detection system using support vector machine

AU - Ishak, Asnor Juraiza

AU - Mustafa, Mohd. Marzuki

AU - Tahir, Noritawati Md

AU - Hussain, Aini

PY - 2008

Y1 - 2008

N2 - In the oil palm plantation in Malaysia, typically blanket spraying is applied to a whole field without regard to the species and location of the weeds in the field. This practice is uneconomical since some areas where no or few weeds exist will receive just as much herbicides as those areas with high densities of weed infestation. Many of these chemical are soil-applied herbicides which easily absorb to ground water and surface water supplies. To control the weed grow and to solve the problems, automatic weed detection system need to be employed. This paper presents the results of automatic classification of broad and narrow weed using feature vector extracted using a combination of Gabor filter and FFT, and classifier using the support vector machine (SVM) Results obtained revealed that the proposed technique results in higher classification accuracy compared to other techniques.

AB - In the oil palm plantation in Malaysia, typically blanket spraying is applied to a whole field without regard to the species and location of the weeds in the field. This practice is uneconomical since some areas where no or few weeds exist will receive just as much herbicides as those areas with high densities of weed infestation. Many of these chemical are soil-applied herbicides which easily absorb to ground water and surface water supplies. To control the weed grow and to solve the problems, automatic weed detection system need to be employed. This paper presents the results of automatic classification of broad and narrow weed using feature vector extracted using a combination of Gabor filter and FFT, and classifier using the support vector machine (SVM) Results obtained revealed that the proposed technique results in higher classification accuracy compared to other techniques.

UR - http://www.scopus.com/inward/record.url?scp=77951122143&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951122143&partnerID=8YFLogxK

U2 - 10.1109/ISITA.2008.4895454

DO - 10.1109/ISITA.2008.4895454

M3 - Conference contribution

SN - 9781424420698

BT - 2008 International Symposium on Information Theory and its Applications, ISITA2008

ER -