Bin level detection using gray level co-occurrence matrix in solid waste collection

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

5 Citations (Scopus)

Abstract

This paper presents the image processing technique gray level co-occurance matrix (GLCM) in solid waste bin level detection and classification. Advanced communication technologies are integrated with GLCM to improve the waste collection operation. The GLCM parameters such as displacement (d) and quantization (G) are investigated to determine the best parameters values of the bin images. The optimum classification accuracy of the system is obtained by investigating the values of d and G. In this paper, the parameters values with selected texture features are used to form the GLCM database. The most appropriate features collected from the GLCM are then used as inputs to the multilayer perception (MLP) and K-nearest neighbor (KNN) for bin image classification and grading. The results demonstrated that the KNN classifier at KNN=3, d=1 and maximum G values performs better than that of using MLP with same database. Based on the results, this new method has the potential to be used in solid waste bin level classification and grading to provide a robust solution for solid waste bin level detection, collection, monitoring and management.

Original languageEnglish
Title of host publicationInternational MultiConference of Engineers and Computer Scientists, IMECS 2012
PublisherNewswood Limited
Pages1019-1024
Number of pages6
Volume2
ISBN (Electronic)9789881925244
ISBN (Print)9789881925190
Publication statusPublished - 1 Jan 2012
Event2012 World Congress on Engineering and Computer Science, WCECS 2012 - San Francisco, United States
Duration: 24 Oct 201226 Oct 2012

Other

Other2012 World Congress on Engineering and Computer Science, WCECS 2012
CountryUnited States
CitySan Francisco
Period24/10/1226/10/12

Fingerprint

Bins
Solid wastes
Multilayers
Image classification
Image processing
Classifiers
Textures
Monitoring
Communication

Keywords

  • Classification and grading
  • GLCM
  • KNN
  • MLP
  • Solid waste monitoring and management

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Arebey, M., M A, H., Basri, H., & Begum, R. A. (2012). Bin level detection using gray level co-occurrence matrix in solid waste collection. In International MultiConference of Engineers and Computer Scientists, IMECS 2012 (Vol. 2, pp. 1019-1024). Newswood Limited.

Bin level detection using gray level co-occurrence matrix in solid waste collection. / Arebey, Maher; M A, Hannan; Basri, Hassan; Begum, Rawshan Ara.

International MultiConference of Engineers and Computer Scientists, IMECS 2012. Vol. 2 Newswood Limited, 2012. p. 1019-1024.

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

Arebey, M, M A, H, Basri, H & Begum, RA 2012, Bin level detection using gray level co-occurrence matrix in solid waste collection. in International MultiConference of Engineers and Computer Scientists, IMECS 2012. vol. 2, Newswood Limited, pp. 1019-1024, 2012 World Congress on Engineering and Computer Science, WCECS 2012, San Francisco, United States, 24/10/12.
Arebey M, M A H, Basri H, Begum RA. Bin level detection using gray level co-occurrence matrix in solid waste collection. In International MultiConference of Engineers and Computer Scientists, IMECS 2012. Vol. 2. Newswood Limited. 2012. p. 1019-1024
Arebey, Maher ; M A, Hannan ; Basri, Hassan ; Begum, Rawshan Ara. / Bin level detection using gray level co-occurrence matrix in solid waste collection. International MultiConference of Engineers and Computer Scientists, IMECS 2012. Vol. 2 Newswood Limited, 2012. pp. 1019-1024
@inproceedings{10c76f1332614156a3cb0544e6addb7e,
title = "Bin level detection using gray level co-occurrence matrix in solid waste collection",
abstract = "This paper presents the image processing technique gray level co-occurance matrix (GLCM) in solid waste bin level detection and classification. Advanced communication technologies are integrated with GLCM to improve the waste collection operation. The GLCM parameters such as displacement (d) and quantization (G) are investigated to determine the best parameters values of the bin images. The optimum classification accuracy of the system is obtained by investigating the values of d and G. In this paper, the parameters values with selected texture features are used to form the GLCM database. The most appropriate features collected from the GLCM are then used as inputs to the multilayer perception (MLP) and K-nearest neighbor (KNN) for bin image classification and grading. The results demonstrated that the KNN classifier at KNN=3, d=1 and maximum G values performs better than that of using MLP with same database. Based on the results, this new method has the potential to be used in solid waste bin level classification and grading to provide a robust solution for solid waste bin level detection, collection, monitoring and management.",
keywords = "Classification and grading, GLCM, KNN, MLP, Solid waste monitoring and management",
author = "Maher Arebey and {M A}, Hannan and Hassan Basri and Begum, {Rawshan Ara}",
year = "2012",
month = "1",
day = "1",
language = "English",
isbn = "9789881925190",
volume = "2",
pages = "1019--1024",
booktitle = "International MultiConference of Engineers and Computer Scientists, IMECS 2012",
publisher = "Newswood Limited",

}

TY - GEN

T1 - Bin level detection using gray level co-occurrence matrix in solid waste collection

AU - Arebey, Maher

AU - M A, Hannan

AU - Basri, Hassan

AU - Begum, Rawshan Ara

PY - 2012/1/1

Y1 - 2012/1/1

N2 - This paper presents the image processing technique gray level co-occurance matrix (GLCM) in solid waste bin level detection and classification. Advanced communication technologies are integrated with GLCM to improve the waste collection operation. The GLCM parameters such as displacement (d) and quantization (G) are investigated to determine the best parameters values of the bin images. The optimum classification accuracy of the system is obtained by investigating the values of d and G. In this paper, the parameters values with selected texture features are used to form the GLCM database. The most appropriate features collected from the GLCM are then used as inputs to the multilayer perception (MLP) and K-nearest neighbor (KNN) for bin image classification and grading. The results demonstrated that the KNN classifier at KNN=3, d=1 and maximum G values performs better than that of using MLP with same database. Based on the results, this new method has the potential to be used in solid waste bin level classification and grading to provide a robust solution for solid waste bin level detection, collection, monitoring and management.

AB - This paper presents the image processing technique gray level co-occurance matrix (GLCM) in solid waste bin level detection and classification. Advanced communication technologies are integrated with GLCM to improve the waste collection operation. The GLCM parameters such as displacement (d) and quantization (G) are investigated to determine the best parameters values of the bin images. The optimum classification accuracy of the system is obtained by investigating the values of d and G. In this paper, the parameters values with selected texture features are used to form the GLCM database. The most appropriate features collected from the GLCM are then used as inputs to the multilayer perception (MLP) and K-nearest neighbor (KNN) for bin image classification and grading. The results demonstrated that the KNN classifier at KNN=3, d=1 and maximum G values performs better than that of using MLP with same database. Based on the results, this new method has the potential to be used in solid waste bin level classification and grading to provide a robust solution for solid waste bin level detection, collection, monitoring and management.

KW - Classification and grading

KW - GLCM

KW - KNN

KW - MLP

KW - Solid waste monitoring and management

UR - http://www.scopus.com/inward/record.url?scp=84903481248&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903481248&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789881925190

VL - 2

SP - 1019

EP - 1024

BT - International MultiConference of Engineers and Computer Scientists, IMECS 2012

PB - Newswood Limited

ER -