Gray level aura matrix: An image processing approach for waste bin level detection

Hannan M A, Maher Arebey, Rawshan Ara Begum, Hassan Basri

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

4 Citations (Scopus)

Abstract

An advanced image processing approach integrated with communication technologies and a camera for bin level detection has been presented. The proposed system is developed to overcome the environmental situation of bin and variety of waste being thrown inside it. Gray Level Aura Matrix (GLAM) approach is proposed to extract the bin image texture. The GLAM parameter such as neighboring system is investigated to determine the best parameters values. To evaluate the performance of the system, the extracted image is trained and tested using MLP and KNN classifiers. The results have shown that the bin level classification accuracies reach acceptable performance levels for class and grade classification with rate of 98.98% and 90.19% using MLP classifier and 96.91% and 89.14% using KNN classifier, respectively. The results demonstrated that the proposed system is a robust and can work with variety of waste and various bin situations.

Original languageEnglish
Title of host publication2011 World Congress on Sustainable Technologies, WCST 2011
Pages77-82
Number of pages6
Publication statusPublished - 2011
Event2011 World Congress on Sustainable Technologies, WCST 2011 - London
Duration: 7 Nov 201110 Nov 2011

Other

Other2011 World Congress on Sustainable Technologies, WCST 2011
CityLondon
Period7/11/1110/11/11

Fingerprint

Bins
Image processing
Classifiers
Image texture
Cameras
Communication

Keywords

  • bin level detection
  • GLAM
  • KNN
  • MLP
  • solid waste monitoring and management

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Renewable Energy, Sustainability and the Environment

Cite this

M A, H., Arebey, M., Begum, R. A., & Basri, H. (2011). Gray level aura matrix: An image processing approach for waste bin level detection. In 2011 World Congress on Sustainable Technologies, WCST 2011 (pp. 77-82). [6114243]

Gray level aura matrix : An image processing approach for waste bin level detection. / M A, Hannan; Arebey, Maher; Begum, Rawshan Ara; Basri, Hassan.

2011 World Congress on Sustainable Technologies, WCST 2011. 2011. p. 77-82 6114243.

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

M A, H, Arebey, M, Begum, RA & Basri, H 2011, Gray level aura matrix: An image processing approach for waste bin level detection. in 2011 World Congress on Sustainable Technologies, WCST 2011., 6114243, pp. 77-82, 2011 World Congress on Sustainable Technologies, WCST 2011, London, 7/11/11.
M A H, Arebey M, Begum RA, Basri H. Gray level aura matrix: An image processing approach for waste bin level detection. In 2011 World Congress on Sustainable Technologies, WCST 2011. 2011. p. 77-82. 6114243
M A, Hannan ; Arebey, Maher ; Begum, Rawshan Ara ; Basri, Hassan. / Gray level aura matrix : An image processing approach for waste bin level detection. 2011 World Congress on Sustainable Technologies, WCST 2011. 2011. pp. 77-82
@inproceedings{f559186163f54d46a140f0772b286183,
title = "Gray level aura matrix: An image processing approach for waste bin level detection",
abstract = "An advanced image processing approach integrated with communication technologies and a camera for bin level detection has been presented. The proposed system is developed to overcome the environmental situation of bin and variety of waste being thrown inside it. Gray Level Aura Matrix (GLAM) approach is proposed to extract the bin image texture. The GLAM parameter such as neighboring system is investigated to determine the best parameters values. To evaluate the performance of the system, the extracted image is trained and tested using MLP and KNN classifiers. The results have shown that the bin level classification accuracies reach acceptable performance levels for class and grade classification with rate of 98.98{\%} and 90.19{\%} using MLP classifier and 96.91{\%} and 89.14{\%} using KNN classifier, respectively. The results demonstrated that the proposed system is a robust and can work with variety of waste and various bin situations.",
keywords = "bin level detection, GLAM, KNN, MLP, solid waste monitoring and management",
author = "{M A}, Hannan and Maher Arebey and Begum, {Rawshan Ara} and Hassan Basri",
year = "2011",
language = "English",
isbn = "9780956426345",
pages = "77--82",
booktitle = "2011 World Congress on Sustainable Technologies, WCST 2011",

}

TY - GEN

T1 - Gray level aura matrix

T2 - An image processing approach for waste bin level detection

AU - M A, Hannan

AU - Arebey, Maher

AU - Begum, Rawshan Ara

AU - Basri, Hassan

PY - 2011

Y1 - 2011

N2 - An advanced image processing approach integrated with communication technologies and a camera for bin level detection has been presented. The proposed system is developed to overcome the environmental situation of bin and variety of waste being thrown inside it. Gray Level Aura Matrix (GLAM) approach is proposed to extract the bin image texture. The GLAM parameter such as neighboring system is investigated to determine the best parameters values. To evaluate the performance of the system, the extracted image is trained and tested using MLP and KNN classifiers. The results have shown that the bin level classification accuracies reach acceptable performance levels for class and grade classification with rate of 98.98% and 90.19% using MLP classifier and 96.91% and 89.14% using KNN classifier, respectively. The results demonstrated that the proposed system is a robust and can work with variety of waste and various bin situations.

AB - An advanced image processing approach integrated with communication technologies and a camera for bin level detection has been presented. The proposed system is developed to overcome the environmental situation of bin and variety of waste being thrown inside it. Gray Level Aura Matrix (GLAM) approach is proposed to extract the bin image texture. The GLAM parameter such as neighboring system is investigated to determine the best parameters values. To evaluate the performance of the system, the extracted image is trained and tested using MLP and KNN classifiers. The results have shown that the bin level classification accuracies reach acceptable performance levels for class and grade classification with rate of 98.98% and 90.19% using MLP classifier and 96.91% and 89.14% using KNN classifier, respectively. The results demonstrated that the proposed system is a robust and can work with variety of waste and various bin situations.

KW - bin level detection

KW - GLAM

KW - KNN

KW - MLP

KW - solid waste monitoring and management

UR - http://www.scopus.com/inward/record.url?scp=84856202828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856202828&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84856202828

SN - 9780956426345

SP - 77

EP - 82

BT - 2011 World Congress on Sustainable Technologies, WCST 2011

ER -