Support vector machine approach to real-time inspection of biscuits on moving conveyor belt

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

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

An intelligent system for colour inspection of biscuit products is proposed. In this system, the state-of-the-art classification techniques based on Support Vector Machines (SVM) and Wilk's λ analysis were used to classify biscuits into one of four distinct groups: under-baked, moderately baked, over-baked, and substantially over-baked. The accuracy of the system was compared with standard discriminant analysis using both direct and multi-step classifications. It was discovered that the radial basis SVM after Wilk's λ was more precise in classification compared to other classifiers. Real-time implementation was achieved by means of multi-core processor with advanced multiple-buffering and multithreading algorithms. The system resulted in correct classification rate of more than 96% for stationary and moving biscuits at 9. m/min. It was discovered that touching and non-touching biscuits did not significantly interfere with accurate assessment of baking. However, image processing of touching biscuits was considerably slower compared to non-touching biscuits, averaging at 36.3. ms and 9.0. ms, respectively. The decrease in speed was due to the complexity of the watershed-based algorithm used to segment touching biscuits. This image computing platform can potentially support the requirements of the high-volume biscuit production.

Original languageEnglish
Pages (from-to)147-158
Number of pages12
JournalComputers and Electronics in Agriculture
Volume75
Issue number1
DOIs
Publication statusPublished - Jan 2011

Fingerprint

biscuits
Support vector machines
Inspection
Discriminant analysis
Intelligent systems
discriminant analysis
buffering
Watersheds
image processing
Image processing
Classifiers
watershed
Color
support vector machines
inspection
support vector machine
artificial intelligence
baking
image analysis
color

Keywords

  • Biscuit
  • Discriminant analysis
  • Image segmentation
  • Machine vision
  • Multi-core processor
  • Support vector machine

ASJC Scopus subject areas

  • Agronomy and Crop Science
  • Horticulture
  • Forestry
  • Computer Science Applications
  • Animal Science and Zoology

Cite this

Support vector machine approach to real-time inspection of biscuits on moving conveyor belt. / Nashat, S.; Abdullah, Azizi; Aramvith, S.; Abdullah, M. Z.

In: Computers and Electronics in Agriculture, Vol. 75, No. 1, 01.2011, p. 147-158.

Research output: Contribution to journalArticle

@article{684505b1bf004f58b313145adecf7260,
title = "Support vector machine approach to real-time inspection of biscuits on moving conveyor belt",
abstract = "An intelligent system for colour inspection of biscuit products is proposed. In this system, the state-of-the-art classification techniques based on Support Vector Machines (SVM) and Wilk's λ analysis were used to classify biscuits into one of four distinct groups: under-baked, moderately baked, over-baked, and substantially over-baked. The accuracy of the system was compared with standard discriminant analysis using both direct and multi-step classifications. It was discovered that the radial basis SVM after Wilk's λ was more precise in classification compared to other classifiers. Real-time implementation was achieved by means of multi-core processor with advanced multiple-buffering and multithreading algorithms. The system resulted in correct classification rate of more than 96{\%} for stationary and moving biscuits at 9. m/min. It was discovered that touching and non-touching biscuits did not significantly interfere with accurate assessment of baking. However, image processing of touching biscuits was considerably slower compared to non-touching biscuits, averaging at 36.3. ms and 9.0. ms, respectively. The decrease in speed was due to the complexity of the watershed-based algorithm used to segment touching biscuits. This image computing platform can potentially support the requirements of the high-volume biscuit production.",
keywords = "Biscuit, Discriminant analysis, Image segmentation, Machine vision, Multi-core processor, Support vector machine",
author = "S. Nashat and Azizi Abdullah and S. Aramvith and Abdullah, {M. Z.}",
year = "2011",
month = "1",
doi = "10.1016/j.compag.2010.10.010",
language = "English",
volume = "75",
pages = "147--158",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Support vector machine approach to real-time inspection of biscuits on moving conveyor belt

AU - Nashat, S.

AU - Abdullah, Azizi

AU - Aramvith, S.

AU - Abdullah, M. Z.

PY - 2011/1

Y1 - 2011/1

N2 - An intelligent system for colour inspection of biscuit products is proposed. In this system, the state-of-the-art classification techniques based on Support Vector Machines (SVM) and Wilk's λ analysis were used to classify biscuits into one of four distinct groups: under-baked, moderately baked, over-baked, and substantially over-baked. The accuracy of the system was compared with standard discriminant analysis using both direct and multi-step classifications. It was discovered that the radial basis SVM after Wilk's λ was more precise in classification compared to other classifiers. Real-time implementation was achieved by means of multi-core processor with advanced multiple-buffering and multithreading algorithms. The system resulted in correct classification rate of more than 96% for stationary and moving biscuits at 9. m/min. It was discovered that touching and non-touching biscuits did not significantly interfere with accurate assessment of baking. However, image processing of touching biscuits was considerably slower compared to non-touching biscuits, averaging at 36.3. ms and 9.0. ms, respectively. The decrease in speed was due to the complexity of the watershed-based algorithm used to segment touching biscuits. This image computing platform can potentially support the requirements of the high-volume biscuit production.

AB - An intelligent system for colour inspection of biscuit products is proposed. In this system, the state-of-the-art classification techniques based on Support Vector Machines (SVM) and Wilk's λ analysis were used to classify biscuits into one of four distinct groups: under-baked, moderately baked, over-baked, and substantially over-baked. The accuracy of the system was compared with standard discriminant analysis using both direct and multi-step classifications. It was discovered that the radial basis SVM after Wilk's λ was more precise in classification compared to other classifiers. Real-time implementation was achieved by means of multi-core processor with advanced multiple-buffering and multithreading algorithms. The system resulted in correct classification rate of more than 96% for stationary and moving biscuits at 9. m/min. It was discovered that touching and non-touching biscuits did not significantly interfere with accurate assessment of baking. However, image processing of touching biscuits was considerably slower compared to non-touching biscuits, averaging at 36.3. ms and 9.0. ms, respectively. The decrease in speed was due to the complexity of the watershed-based algorithm used to segment touching biscuits. This image computing platform can potentially support the requirements of the high-volume biscuit production.

KW - Biscuit

KW - Discriminant analysis

KW - Image segmentation

KW - Machine vision

KW - Multi-core processor

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=78650519991&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650519991&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2010.10.010

DO - 10.1016/j.compag.2010.10.010

M3 - Article

AN - SCOPUS:78650519991

VL - 75

SP - 147

EP - 158

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

IS - 1

ER -