Content-based image retrieval system for solid waste bin level detection and performance evaluation

Hannan M A, M. Arebey, Rawshan Ara Begum, Hassan Basri, Md Abdulla Al Mamun

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper presents a CBIR system to investigate the use of image retrieval with an extracted texture from the image of a bin to detect the bin level. Various similarity distances like Euclidean, Bhattacharyya, Chi-squared, Cosine, and EMD are used with the CBIR system for calculating and comparing the distance between a query image and the images in a database to obtain the highest performance. In this study, the performance metrics is based on two quantitative evaluation criteria. The first one is the average retrieval rate based on the precision-recall graph and the second is the use of F1 measure which is the weighted harmonic mean of precision and recall. In case of feature extraction, texture is used as an image feature for bin level detection system. Various experiments are conducted with different features extraction techniques like Gabor wavelet filter, gray level co-occurrence matrix (GLCM), and gray level aura matrix (GLAM) to identify the level of the bin and its surrounding area. Intensive tests are conducted among 250. bin images to assess the accuracy of the proposed feature extraction techniques. The average retrieval rate is used to evaluate the performance of the retrieval system. The result shows that, the EMD distance achieved high accuracy and provides better performance than the other distances.

Original languageEnglish
JournalWaste Management
DOIs
Publication statusAccepted/In press - 21 Oct 2015

Fingerprint

solid waste
texture
matrix
wavelet
detection
evaluation
waste bin
filter
experiment
rate

Keywords

  • CBIR
  • Feature extraction
  • Gabor
  • GLAM
  • GLCM
  • Solid waste bin level

ASJC Scopus subject areas

  • Waste Management and Disposal

Cite this

Content-based image retrieval system for solid waste bin level detection and performance evaluation. / M A, Hannan; Arebey, M.; Begum, Rawshan Ara; Basri, Hassan; Al Mamun, Md Abdulla.

In: Waste Management, 21.10.2015.

Research output: Contribution to journalArticle

@article{65b2d5fc7a7e4c1ab1710e9a5ede66b8,
title = "Content-based image retrieval system for solid waste bin level detection and performance evaluation",
abstract = "This paper presents a CBIR system to investigate the use of image retrieval with an extracted texture from the image of a bin to detect the bin level. Various similarity distances like Euclidean, Bhattacharyya, Chi-squared, Cosine, and EMD are used with the CBIR system for calculating and comparing the distance between a query image and the images in a database to obtain the highest performance. In this study, the performance metrics is based on two quantitative evaluation criteria. The first one is the average retrieval rate based on the precision-recall graph and the second is the use of F1 measure which is the weighted harmonic mean of precision and recall. In case of feature extraction, texture is used as an image feature for bin level detection system. Various experiments are conducted with different features extraction techniques like Gabor wavelet filter, gray level co-occurrence matrix (GLCM), and gray level aura matrix (GLAM) to identify the level of the bin and its surrounding area. Intensive tests are conducted among 250. bin images to assess the accuracy of the proposed feature extraction techniques. The average retrieval rate is used to evaluate the performance of the retrieval system. The result shows that, the EMD distance achieved high accuracy and provides better performance than the other distances.",
keywords = "CBIR, Feature extraction, Gabor, GLAM, GLCM, Solid waste bin level",
author = "{M A}, Hannan and M. Arebey and Begum, {Rawshan Ara} and Hassan Basri and {Al Mamun}, {Md Abdulla}",
year = "2015",
month = "10",
day = "21",
doi = "10.1016/j.wasman.2016.01.046",
language = "English",
journal = "Waste Management",
issn = "0956-053X",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Content-based image retrieval system for solid waste bin level detection and performance evaluation

AU - M A, Hannan

AU - Arebey, M.

AU - Begum, Rawshan Ara

AU - Basri, Hassan

AU - Al Mamun, Md Abdulla

PY - 2015/10/21

Y1 - 2015/10/21

N2 - This paper presents a CBIR system to investigate the use of image retrieval with an extracted texture from the image of a bin to detect the bin level. Various similarity distances like Euclidean, Bhattacharyya, Chi-squared, Cosine, and EMD are used with the CBIR system for calculating and comparing the distance between a query image and the images in a database to obtain the highest performance. In this study, the performance metrics is based on two quantitative evaluation criteria. The first one is the average retrieval rate based on the precision-recall graph and the second is the use of F1 measure which is the weighted harmonic mean of precision and recall. In case of feature extraction, texture is used as an image feature for bin level detection system. Various experiments are conducted with different features extraction techniques like Gabor wavelet filter, gray level co-occurrence matrix (GLCM), and gray level aura matrix (GLAM) to identify the level of the bin and its surrounding area. Intensive tests are conducted among 250. bin images to assess the accuracy of the proposed feature extraction techniques. The average retrieval rate is used to evaluate the performance of the retrieval system. The result shows that, the EMD distance achieved high accuracy and provides better performance than the other distances.

AB - This paper presents a CBIR system to investigate the use of image retrieval with an extracted texture from the image of a bin to detect the bin level. Various similarity distances like Euclidean, Bhattacharyya, Chi-squared, Cosine, and EMD are used with the CBIR system for calculating and comparing the distance between a query image and the images in a database to obtain the highest performance. In this study, the performance metrics is based on two quantitative evaluation criteria. The first one is the average retrieval rate based on the precision-recall graph and the second is the use of F1 measure which is the weighted harmonic mean of precision and recall. In case of feature extraction, texture is used as an image feature for bin level detection system. Various experiments are conducted with different features extraction techniques like Gabor wavelet filter, gray level co-occurrence matrix (GLCM), and gray level aura matrix (GLAM) to identify the level of the bin and its surrounding area. Intensive tests are conducted among 250. bin images to assess the accuracy of the proposed feature extraction techniques. The average retrieval rate is used to evaluate the performance of the retrieval system. The result shows that, the EMD distance achieved high accuracy and provides better performance than the other distances.

KW - CBIR

KW - Feature extraction

KW - Gabor

KW - GLAM

KW - GLCM

KW - Solid waste bin level

UR - http://www.scopus.com/inward/record.url?scp=84956855230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956855230&partnerID=8YFLogxK

U2 - 10.1016/j.wasman.2016.01.046

DO - 10.1016/j.wasman.2016.01.046

M3 - Article

JO - Waste Management

JF - Waste Management

SN - 0956-053X

ER -