Machine vision for crack inspection of biscuits featuring pyramid detection scheme

S. Nashat, Azizi Abdullah, M. Z. Abdullah

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

One of the challenges associated with machine vision inspection of biscuits or baked products with non-uniform colour distributions and textured background is the detection of a small and minute crack. In this study, a pyramid automatic crack detection scheme was proposed. This requires an enhancement method to properly distinguish the crack and intact samples. Canny-Deriche filter was used to emphasis the crack and reduce the noise. In order to segment minute crack pattern with less noise, a unimodal thresholding technique was developed and tested. The detection was based on support vector machine (SVM) featuring Wilk's λ selection criteria. The accuracy of the system was compared with standard discriminant analysis. It was discovered that the pyramid SVM after Wilk's λ analysis was more precise in detection compared to other classifiers, resulting in the specificity and sensitivity of 98% and 96% respectively, and average correct classification of consistently more than 97%.

Original languageEnglish
Pages (from-to)233-247
Number of pages15
JournalJournal of Food Engineering
Volume120
Issue number1
DOIs
Publication statusPublished - 2014

Fingerprint

biscuits
computer vision
Noise
Discriminant Analysis
Patient Selection
Color
Sensitivity and Specificity
selection criteria
discriminant analysis
Support Vector Machine
color
methodology
sampling
support vector machines

Keywords

  • Canny-Deriche filter
  • Concentricity measure
  • Crack detection
  • Machine vision system
  • Pyramid Hough transform
  • Support vector machine

ASJC Scopus subject areas

  • Food Science

Cite this

Machine vision for crack inspection of biscuits featuring pyramid detection scheme. / Nashat, S.; Abdullah, Azizi; Abdullah, M. Z.

In: Journal of Food Engineering, Vol. 120, No. 1, 2014, p. 233-247.

Research output: Contribution to journalArticle

@article{002a6db11fda46bf8500002673aff00a,
title = "Machine vision for crack inspection of biscuits featuring pyramid detection scheme",
abstract = "One of the challenges associated with machine vision inspection of biscuits or baked products with non-uniform colour distributions and textured background is the detection of a small and minute crack. In this study, a pyramid automatic crack detection scheme was proposed. This requires an enhancement method to properly distinguish the crack and intact samples. Canny-Deriche filter was used to emphasis the crack and reduce the noise. In order to segment minute crack pattern with less noise, a unimodal thresholding technique was developed and tested. The detection was based on support vector machine (SVM) featuring Wilk's λ selection criteria. The accuracy of the system was compared with standard discriminant analysis. It was discovered that the pyramid SVM after Wilk's λ analysis was more precise in detection compared to other classifiers, resulting in the specificity and sensitivity of 98{\%} and 96{\%} respectively, and average correct classification of consistently more than 97{\%}.",
keywords = "Canny-Deriche filter, Concentricity measure, Crack detection, Machine vision system, Pyramid Hough transform, Support vector machine",
author = "S. Nashat and Azizi Abdullah and Abdullah, {M. Z.}",
year = "2014",
doi = "10.1016/j.jfoodeng.2013.08.006",
language = "English",
volume = "120",
pages = "233--247",
journal = "Journal of Food Engineering",
issn = "0260-8774",
publisher = "Elsevier Limited",
number = "1",

}

TY - JOUR

T1 - Machine vision for crack inspection of biscuits featuring pyramid detection scheme

AU - Nashat, S.

AU - Abdullah, Azizi

AU - Abdullah, M. Z.

PY - 2014

Y1 - 2014

N2 - One of the challenges associated with machine vision inspection of biscuits or baked products with non-uniform colour distributions and textured background is the detection of a small and minute crack. In this study, a pyramid automatic crack detection scheme was proposed. This requires an enhancement method to properly distinguish the crack and intact samples. Canny-Deriche filter was used to emphasis the crack and reduce the noise. In order to segment minute crack pattern with less noise, a unimodal thresholding technique was developed and tested. The detection was based on support vector machine (SVM) featuring Wilk's λ selection criteria. The accuracy of the system was compared with standard discriminant analysis. It was discovered that the pyramid SVM after Wilk's λ analysis was more precise in detection compared to other classifiers, resulting in the specificity and sensitivity of 98% and 96% respectively, and average correct classification of consistently more than 97%.

AB - One of the challenges associated with machine vision inspection of biscuits or baked products with non-uniform colour distributions and textured background is the detection of a small and minute crack. In this study, a pyramid automatic crack detection scheme was proposed. This requires an enhancement method to properly distinguish the crack and intact samples. Canny-Deriche filter was used to emphasis the crack and reduce the noise. In order to segment minute crack pattern with less noise, a unimodal thresholding technique was developed and tested. The detection was based on support vector machine (SVM) featuring Wilk's λ selection criteria. The accuracy of the system was compared with standard discriminant analysis. It was discovered that the pyramid SVM after Wilk's λ analysis was more precise in detection compared to other classifiers, resulting in the specificity and sensitivity of 98% and 96% respectively, and average correct classification of consistently more than 97%.

KW - Canny-Deriche filter

KW - Concentricity measure

KW - Crack detection

KW - Machine vision system

KW - Pyramid Hough transform

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84883399948&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883399948&partnerID=8YFLogxK

U2 - 10.1016/j.jfoodeng.2013.08.006

DO - 10.1016/j.jfoodeng.2013.08.006

M3 - Article

AN - SCOPUS:84883399948

VL - 120

SP - 233

EP - 247

JO - Journal of Food Engineering

JF - Journal of Food Engineering

SN - 0260-8774

IS - 1

ER -