Optimal feature selection for SVM based weed classification via visual analysis

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

3 Citations (Scopus)

Abstract

Weed classification is a serious issue in the agricultural research. Weed classification is a necessity in identifying weed species for control. Many classification techniques have been used to identify weed based on images, however, most of the techniques only measure the percentages of accuracy but the detailed of classifier parameter are not analyzed and discussed. Therefore, in this work, feature vectors of weed images extracted using Gabor Wavelet and Fast Fourier Transform (FFT) were employed in analyzing weed pattern based on images using Support Vector Machines (SVM). The decision boundaries of the categorized extracted feature vectors are illustrated and optimal feature vectors are identified. Results are discussed and displayed with illustrations to prove the SVM classifier performance.

Original languageEnglish
Title of host publicationIEEE Region 10 Annual International Conference, Proceedings/TENCON
Pages1647-1650
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 IEEE Region 10 Conference, TENCON 2010 - Fukuoka
Duration: 21 Nov 201024 Nov 2010

Other

Other2010 IEEE Region 10 Conference, TENCON 2010
CityFukuoka
Period21/11/1024/11/10

Fingerprint

Support vector machines
Feature extraction
Classifiers
Fast Fourier transforms

Keywords

  • Fast fourier transform
  • Gabor wavelet
  • Support vector machine optimal feature
  • Weed classification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications

Cite this

Shahbudin, S., Hussain, A., Abdul Samad, S., Mustafa, M. M., & Ishak, A. J. (2010). Optimal feature selection for SVM based weed classification via visual analysis. In IEEE Region 10 Annual International Conference, Proceedings/TENCON (pp. 1647-1650). [5686770] https://doi.org/10.1109/TENCON.2010.5686770

Optimal feature selection for SVM based weed classification via visual analysis. / Shahbudin, S.; Hussain, Aini; Abdul Samad, Salina; Mustafa, Mohd. Marzuki; Ishak, A. J.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. p. 1647-1650 5686770.

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

Shahbudin, S, Hussain, A, Abdul Samad, S, Mustafa, MM & Ishak, AJ 2010, Optimal feature selection for SVM based weed classification via visual analysis. in IEEE Region 10 Annual International Conference, Proceedings/TENCON., 5686770, pp. 1647-1650, 2010 IEEE Region 10 Conference, TENCON 2010, Fukuoka, 21/11/10. https://doi.org/10.1109/TENCON.2010.5686770
Shahbudin S, Hussain A, Abdul Samad S, Mustafa MM, Ishak AJ. Optimal feature selection for SVM based weed classification via visual analysis. In IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. p. 1647-1650. 5686770 https://doi.org/10.1109/TENCON.2010.5686770
Shahbudin, S. ; Hussain, Aini ; Abdul Samad, Salina ; Mustafa, Mohd. Marzuki ; Ishak, A. J. / Optimal feature selection for SVM based weed classification via visual analysis. IEEE Region 10 Annual International Conference, Proceedings/TENCON. 2010. pp. 1647-1650
@inproceedings{d79c13e7567a424eaae360b28c273dbe,
title = "Optimal feature selection for SVM based weed classification via visual analysis",
abstract = "Weed classification is a serious issue in the agricultural research. Weed classification is a necessity in identifying weed species for control. Many classification techniques have been used to identify weed based on images, however, most of the techniques only measure the percentages of accuracy but the detailed of classifier parameter are not analyzed and discussed. Therefore, in this work, feature vectors of weed images extracted using Gabor Wavelet and Fast Fourier Transform (FFT) were employed in analyzing weed pattern based on images using Support Vector Machines (SVM). The decision boundaries of the categorized extracted feature vectors are illustrated and optimal feature vectors are identified. Results are discussed and displayed with illustrations to prove the SVM classifier performance.",
keywords = "Fast fourier transform, Gabor wavelet, Support vector machine optimal feature, Weed classification",
author = "S. Shahbudin and Aini Hussain and {Abdul Samad}, Salina and Mustafa, {Mohd. Marzuki} and Ishak, {A. J.}",
year = "2010",
doi = "10.1109/TENCON.2010.5686770",
language = "English",
isbn = "9781424468904",
pages = "1647--1650",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

}

TY - GEN

T1 - Optimal feature selection for SVM based weed classification via visual analysis

AU - Shahbudin, S.

AU - Hussain, Aini

AU - Abdul Samad, Salina

AU - Mustafa, Mohd. Marzuki

AU - Ishak, A. J.

PY - 2010

Y1 - 2010

N2 - Weed classification is a serious issue in the agricultural research. Weed classification is a necessity in identifying weed species for control. Many classification techniques have been used to identify weed based on images, however, most of the techniques only measure the percentages of accuracy but the detailed of classifier parameter are not analyzed and discussed. Therefore, in this work, feature vectors of weed images extracted using Gabor Wavelet and Fast Fourier Transform (FFT) were employed in analyzing weed pattern based on images using Support Vector Machines (SVM). The decision boundaries of the categorized extracted feature vectors are illustrated and optimal feature vectors are identified. Results are discussed and displayed with illustrations to prove the SVM classifier performance.

AB - Weed classification is a serious issue in the agricultural research. Weed classification is a necessity in identifying weed species for control. Many classification techniques have been used to identify weed based on images, however, most of the techniques only measure the percentages of accuracy but the detailed of classifier parameter are not analyzed and discussed. Therefore, in this work, feature vectors of weed images extracted using Gabor Wavelet and Fast Fourier Transform (FFT) were employed in analyzing weed pattern based on images using Support Vector Machines (SVM). The decision boundaries of the categorized extracted feature vectors are illustrated and optimal feature vectors are identified. Results are discussed and displayed with illustrations to prove the SVM classifier performance.

KW - Fast fourier transform

KW - Gabor wavelet

KW - Support vector machine optimal feature

KW - Weed classification

UR - http://www.scopus.com/inward/record.url?scp=79951615110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951615110&partnerID=8YFLogxK

U2 - 10.1109/TENCON.2010.5686770

DO - 10.1109/TENCON.2010.5686770

M3 - Conference contribution

SN - 9781424468904

SP - 1647

EP - 1650

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

ER -