A machine vision approach to the grading of crushed aggregate

Fionn Murtagh, Xiaoyu Qiao, Danny Crookes, Paul Walsh, P. A Muhammed Basheer, Adrian Long, Jean Luc Starck

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

The grading of crushed aggregate is carried out usually by sieving. We describe a new image-based approach to the automatic grading of such materials. The operational problem addressed is where the camera is located directly over a conveyor belt. Our approach characterizes the information content of each image, taking into account relative variation in the pixel data, and resolution scale. In feature space, we find very good class separation using a multidimensional linear classifier. The innovation in this work includes (i) introducing an effective image-based approach into this application area, and (ii) our supervised classification using wavelet entropy-based features.

LanguageEnglish
Pages229-235
Number of pages7
JournalMachine Vision and Applications
Volume16
Issue number4
Early online date10 Jun 2005
DOIs
Publication statusPublished - 1 Sep 2005
Externally publishedYes

Fingerprint

Computer vision
Classifiers
Entropy
Innovation
Pixels
Cameras

Cite this

Murtagh, F., Qiao, X., Crookes, D., Walsh, P., Basheer, P. A. M., Long, A., & Starck, J. L. (2005). A machine vision approach to the grading of crushed aggregate. Machine Vision and Applications, 16(4), 229-235. https://doi.org/10.1007/s00138-005-0176-7
Murtagh, Fionn ; Qiao, Xiaoyu ; Crookes, Danny ; Walsh, Paul ; Basheer, P. A Muhammed ; Long, Adrian ; Starck, Jean Luc. / A machine vision approach to the grading of crushed aggregate. In: Machine Vision and Applications. 2005 ; Vol. 16, No. 4. pp. 229-235.
@article{82e98d1877834cc7a746db91185e426c,
title = "A machine vision approach to the grading of crushed aggregate",
abstract = "The grading of crushed aggregate is carried out usually by sieving. We describe a new image-based approach to the automatic grading of such materials. The operational problem addressed is where the camera is located directly over a conveyor belt. Our approach characterizes the information content of each image, taking into account relative variation in the pixel data, and resolution scale. In feature space, we find very good class separation using a multidimensional linear classifier. The innovation in this work includes (i) introducing an effective image-based approach into this application area, and (ii) our supervised classification using wavelet entropy-based features.",
keywords = "Aggregate, Construction, Entropy, Image database, Information, Machine vision, Wavelet transform",
author = "Fionn Murtagh and Xiaoyu Qiao and Danny Crookes and Paul Walsh and Basheer, {P. A Muhammed} and Adrian Long and Starck, {Jean Luc}",
year = "2005",
month = "9",
day = "1",
doi = "10.1007/s00138-005-0176-7",
language = "English",
volume = "16",
pages = "229--235",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer Verlag",
number = "4",

}

Murtagh, F, Qiao, X, Crookes, D, Walsh, P, Basheer, PAM, Long, A & Starck, JL 2005, 'A machine vision approach to the grading of crushed aggregate', Machine Vision and Applications, vol. 16, no. 4, pp. 229-235. https://doi.org/10.1007/s00138-005-0176-7

A machine vision approach to the grading of crushed aggregate. / Murtagh, Fionn; Qiao, Xiaoyu; Crookes, Danny; Walsh, Paul; Basheer, P. A Muhammed; Long, Adrian; Starck, Jean Luc.

In: Machine Vision and Applications, Vol. 16, No. 4, 01.09.2005, p. 229-235.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A machine vision approach to the grading of crushed aggregate

AU - Murtagh, Fionn

AU - Qiao, Xiaoyu

AU - Crookes, Danny

AU - Walsh, Paul

AU - Basheer, P. A Muhammed

AU - Long, Adrian

AU - Starck, Jean Luc

PY - 2005/9/1

Y1 - 2005/9/1

N2 - The grading of crushed aggregate is carried out usually by sieving. We describe a new image-based approach to the automatic grading of such materials. The operational problem addressed is where the camera is located directly over a conveyor belt. Our approach characterizes the information content of each image, taking into account relative variation in the pixel data, and resolution scale. In feature space, we find very good class separation using a multidimensional linear classifier. The innovation in this work includes (i) introducing an effective image-based approach into this application area, and (ii) our supervised classification using wavelet entropy-based features.

AB - The grading of crushed aggregate is carried out usually by sieving. We describe a new image-based approach to the automatic grading of such materials. The operational problem addressed is where the camera is located directly over a conveyor belt. Our approach characterizes the information content of each image, taking into account relative variation in the pixel data, and resolution scale. In feature space, we find very good class separation using a multidimensional linear classifier. The innovation in this work includes (i) introducing an effective image-based approach into this application area, and (ii) our supervised classification using wavelet entropy-based features.

KW - Aggregate

KW - Construction

KW - Entropy

KW - Image database

KW - Information

KW - Machine vision

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=27744554854&partnerID=8YFLogxK

U2 - 10.1007/s00138-005-0176-7

DO - 10.1007/s00138-005-0176-7

M3 - Article

VL - 16

SP - 229

EP - 235

JO - Machine Vision and Applications

T2 - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 4

ER -