Gradient field distribution and grey level co-occurrence matrix techniques for automatic weed classification

Asnor Juraiza Ishak, Mohd. Marzuki Mustafa, Aini Hussain

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

4 Citations (Scopus)

Abstract

Nowadays it is a requirement to adopt a greener approach in the management of plantation especially when dealing with chemical herbicide to control weed infestation. To do so, selective patch spraying method is a necessity since it can help in minimizing the volume of usage of the herbicide. As such, an intelligent system that can differentiate the different weed is desirable. In this work, we have adopted an image processing approach to detect and classify weed according to its class, namely as either broad or narrow, such that the selective patch spraying strategy can be implemented. This paper describes the procedures involved and its main focus is on the combined use of Gradient Field Distribution (GFD) and Grey Level Co-occurrence Matrix (GLCM) algorithms to extract new feature vector set. The results obtained suggest that the new feature vectors, derived from the GFD and GLCM techniques combined, has unique characteristics that enable perfect discrimination between the two types of weed. Thus, perfect classification was possible when tested with 400 samples of weed images comprising of both types of weed.

Original languageEnglish
Title of host publicationProceeding of the 5th International Symposium on Mechatronics and its Applications, ISMA 2008
DOIs
Publication statusPublished - 2008
Event5th International Symposium on Mechatronics and its Applications, ISMA 2008 - Amman
Duration: 27 May 200829 May 2008

Other

Other5th International Symposium on Mechatronics and its Applications, ISMA 2008
CityAmman
Period27/5/0829/5/08

Fingerprint

Herbicides
Spraying
Weed control
Intelligent systems
Image processing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Ishak, A. J., Mustafa, M. M., & Hussain, A. (2008). Gradient field distribution and grey level co-occurrence matrix techniques for automatic weed classification. In Proceeding of the 5th International Symposium on Mechatronics and its Applications, ISMA 2008 [4648846] https://doi.org/10.1109/ISMA.2008.4648846

Gradient field distribution and grey level co-occurrence matrix techniques for automatic weed classification. / Ishak, Asnor Juraiza; Mustafa, Mohd. Marzuki; Hussain, Aini.

Proceeding of the 5th International Symposium on Mechatronics and its Applications, ISMA 2008. 2008. 4648846.

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

Ishak, AJ, Mustafa, MM & Hussain, A 2008, Gradient field distribution and grey level co-occurrence matrix techniques for automatic weed classification. in Proceeding of the 5th International Symposium on Mechatronics and its Applications, ISMA 2008., 4648846, 5th International Symposium on Mechatronics and its Applications, ISMA 2008, Amman, 27/5/08. https://doi.org/10.1109/ISMA.2008.4648846
Ishak AJ, Mustafa MM, Hussain A. Gradient field distribution and grey level co-occurrence matrix techniques for automatic weed classification. In Proceeding of the 5th International Symposium on Mechatronics and its Applications, ISMA 2008. 2008. 4648846 https://doi.org/10.1109/ISMA.2008.4648846
Ishak, Asnor Juraiza ; Mustafa, Mohd. Marzuki ; Hussain, Aini. / Gradient field distribution and grey level co-occurrence matrix techniques for automatic weed classification. Proceeding of the 5th International Symposium on Mechatronics and its Applications, ISMA 2008. 2008.
@inproceedings{bb2753f889b7444dbad48bb42efe35fc,
title = "Gradient field distribution and grey level co-occurrence matrix techniques for automatic weed classification",
abstract = "Nowadays it is a requirement to adopt a greener approach in the management of plantation especially when dealing with chemical herbicide to control weed infestation. To do so, selective patch spraying method is a necessity since it can help in minimizing the volume of usage of the herbicide. As such, an intelligent system that can differentiate the different weed is desirable. In this work, we have adopted an image processing approach to detect and classify weed according to its class, namely as either broad or narrow, such that the selective patch spraying strategy can be implemented. This paper describes the procedures involved and its main focus is on the combined use of Gradient Field Distribution (GFD) and Grey Level Co-occurrence Matrix (GLCM) algorithms to extract new feature vector set. The results obtained suggest that the new feature vectors, derived from the GFD and GLCM techniques combined, has unique characteristics that enable perfect discrimination between the two types of weed. Thus, perfect classification was possible when tested with 400 samples of weed images comprising of both types of weed.",
author = "Ishak, {Asnor Juraiza} and Mustafa, {Mohd. Marzuki} and Aini Hussain",
year = "2008",
doi = "10.1109/ISMA.2008.4648846",
language = "English",
isbn = "9781424420346",
booktitle = "Proceeding of the 5th International Symposium on Mechatronics and its Applications, ISMA 2008",

}

TY - GEN

T1 - Gradient field distribution and grey level co-occurrence matrix techniques for automatic weed classification

AU - Ishak, Asnor Juraiza

AU - Mustafa, Mohd. Marzuki

AU - Hussain, Aini

PY - 2008

Y1 - 2008

N2 - Nowadays it is a requirement to adopt a greener approach in the management of plantation especially when dealing with chemical herbicide to control weed infestation. To do so, selective patch spraying method is a necessity since it can help in minimizing the volume of usage of the herbicide. As such, an intelligent system that can differentiate the different weed is desirable. In this work, we have adopted an image processing approach to detect and classify weed according to its class, namely as either broad or narrow, such that the selective patch spraying strategy can be implemented. This paper describes the procedures involved and its main focus is on the combined use of Gradient Field Distribution (GFD) and Grey Level Co-occurrence Matrix (GLCM) algorithms to extract new feature vector set. The results obtained suggest that the new feature vectors, derived from the GFD and GLCM techniques combined, has unique characteristics that enable perfect discrimination between the two types of weed. Thus, perfect classification was possible when tested with 400 samples of weed images comprising of both types of weed.

AB - Nowadays it is a requirement to adopt a greener approach in the management of plantation especially when dealing with chemical herbicide to control weed infestation. To do so, selective patch spraying method is a necessity since it can help in minimizing the volume of usage of the herbicide. As such, an intelligent system that can differentiate the different weed is desirable. In this work, we have adopted an image processing approach to detect and classify weed according to its class, namely as either broad or narrow, such that the selective patch spraying strategy can be implemented. This paper describes the procedures involved and its main focus is on the combined use of Gradient Field Distribution (GFD) and Grey Level Co-occurrence Matrix (GLCM) algorithms to extract new feature vector set. The results obtained suggest that the new feature vectors, derived from the GFD and GLCM techniques combined, has unique characteristics that enable perfect discrimination between the two types of weed. Thus, perfect classification was possible when tested with 400 samples of weed images comprising of both types of weed.

UR - http://www.scopus.com/inward/record.url?scp=69549116727&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69549116727&partnerID=8YFLogxK

U2 - 10.1109/ISMA.2008.4648846

DO - 10.1109/ISMA.2008.4648846

M3 - Conference contribution

SN - 9781424420346

BT - Proceeding of the 5th International Symposium on Mechatronics and its Applications, ISMA 2008

ER -