Development of a low cost machine vision system for sorting of tomatoes

Md Rokunuzzaman, H. P W Jayasuriya

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Sorting of tomatoes has been an issue faced by producers as well as sellers due to the sheer volumes handled and the delicate nature of the fruit. This paper describes the development of a low cost machine vision system using webcams and image processing algorithms for defect detection and sorting of tomatoes. In the case of agricultural products, good efforts and appropriate techniques are necessary to distinguish between defected and good ones when using machine vision for sorting. Tomatoes having two major defects namely Blossom End Rot (BER) and Cracks could be separated from good tomatoes with calyx. The sorting decision was based on three features extracted by the image processing algorithms. The color features were used for detecting the BER from good tomatoes and shape factor combined with the number of green objects was used for differentiating the calyxes from crack defects. Two methods, rule based and neural network approaches, were developed for decision based sorting. A control system was developed with a belt conveyor to transport the tomatoes and a cylinder pushrod coupled to a solenoid was used to push the defective tomatoes after determining their defect by the algorithms. The color image threshold method with shape factor were found efficient for differentiating good and defective tomatoes. The overall accuracy of defect detection attained by the rule based approach and the neural network method were 84 and 87.5% respectively. The inspection speed of 180 tomatoes min-1 was achieved by the algorithms and the prototype developed. Comparison of the results obtained by the rule based and neural network approaches are also presented in this paper.

Original languageEnglish
Pages (from-to)173-180
Number of pages8
JournalAgricultural Engineering International: CIGR Journal
Volume15
Issue number1
Publication statusPublished - 2013

Fingerprint

computer vision
Sorting
sorting
Computer vision
tomatoes
Costs
Neural networks
Defects
Image processing
neural networks
Color
Cracks
Agricultural products
Solenoids
calyx
Fruits
image analysis
solenoids
Inspection
Control systems

Keywords

  • Defect detection
  • Machine vision
  • Neural network
  • Rule based approach
  • Tomato sorting

ASJC Scopus subject areas

  • Energy (miscellaneous)
  • Industrial and Manufacturing Engineering
  • Automotive Engineering
  • Agronomy and Crop Science

Cite this

Development of a low cost machine vision system for sorting of tomatoes. / Rokunuzzaman, Md; Jayasuriya, H. P W.

In: Agricultural Engineering International: CIGR Journal, Vol. 15, No. 1, 2013, p. 173-180.

Research output: Contribution to journalArticle

@article{3d62f7a224d14f668a132983eed478c2,
title = "Development of a low cost machine vision system for sorting of tomatoes",
abstract = "Sorting of tomatoes has been an issue faced by producers as well as sellers due to the sheer volumes handled and the delicate nature of the fruit. This paper describes the development of a low cost machine vision system using webcams and image processing algorithms for defect detection and sorting of tomatoes. In the case of agricultural products, good efforts and appropriate techniques are necessary to distinguish between defected and good ones when using machine vision for sorting. Tomatoes having two major defects namely Blossom End Rot (BER) and Cracks could be separated from good tomatoes with calyx. The sorting decision was based on three features extracted by the image processing algorithms. The color features were used for detecting the BER from good tomatoes and shape factor combined with the number of green objects was used for differentiating the calyxes from crack defects. Two methods, rule based and neural network approaches, were developed for decision based sorting. A control system was developed with a belt conveyor to transport the tomatoes and a cylinder pushrod coupled to a solenoid was used to push the defective tomatoes after determining their defect by the algorithms. The color image threshold method with shape factor were found efficient for differentiating good and defective tomatoes. The overall accuracy of defect detection attained by the rule based approach and the neural network method were 84 and 87.5{\%} respectively. The inspection speed of 180 tomatoes min-1 was achieved by the algorithms and the prototype developed. Comparison of the results obtained by the rule based and neural network approaches are also presented in this paper.",
keywords = "Defect detection, Machine vision, Neural network, Rule based approach, Tomato sorting",
author = "Md Rokunuzzaman and Jayasuriya, {H. P W}",
year = "2013",
language = "English",
volume = "15",
pages = "173--180",
journal = "Agricultural Engineering International: CIGR Journal",
issn = "1682-1130",
publisher = "International Commission of Agricultural and Biosystems Engineering",
number = "1",

}

TY - JOUR

T1 - Development of a low cost machine vision system for sorting of tomatoes

AU - Rokunuzzaman, Md

AU - Jayasuriya, H. P W

PY - 2013

Y1 - 2013

N2 - Sorting of tomatoes has been an issue faced by producers as well as sellers due to the sheer volumes handled and the delicate nature of the fruit. This paper describes the development of a low cost machine vision system using webcams and image processing algorithms for defect detection and sorting of tomatoes. In the case of agricultural products, good efforts and appropriate techniques are necessary to distinguish between defected and good ones when using machine vision for sorting. Tomatoes having two major defects namely Blossom End Rot (BER) and Cracks could be separated from good tomatoes with calyx. The sorting decision was based on three features extracted by the image processing algorithms. The color features were used for detecting the BER from good tomatoes and shape factor combined with the number of green objects was used for differentiating the calyxes from crack defects. Two methods, rule based and neural network approaches, were developed for decision based sorting. A control system was developed with a belt conveyor to transport the tomatoes and a cylinder pushrod coupled to a solenoid was used to push the defective tomatoes after determining their defect by the algorithms. The color image threshold method with shape factor were found efficient for differentiating good and defective tomatoes. The overall accuracy of defect detection attained by the rule based approach and the neural network method were 84 and 87.5% respectively. The inspection speed of 180 tomatoes min-1 was achieved by the algorithms and the prototype developed. Comparison of the results obtained by the rule based and neural network approaches are also presented in this paper.

AB - Sorting of tomatoes has been an issue faced by producers as well as sellers due to the sheer volumes handled and the delicate nature of the fruit. This paper describes the development of a low cost machine vision system using webcams and image processing algorithms for defect detection and sorting of tomatoes. In the case of agricultural products, good efforts and appropriate techniques are necessary to distinguish between defected and good ones when using machine vision for sorting. Tomatoes having two major defects namely Blossom End Rot (BER) and Cracks could be separated from good tomatoes with calyx. The sorting decision was based on three features extracted by the image processing algorithms. The color features were used for detecting the BER from good tomatoes and shape factor combined with the number of green objects was used for differentiating the calyxes from crack defects. Two methods, rule based and neural network approaches, were developed for decision based sorting. A control system was developed with a belt conveyor to transport the tomatoes and a cylinder pushrod coupled to a solenoid was used to push the defective tomatoes after determining their defect by the algorithms. The color image threshold method with shape factor were found efficient for differentiating good and defective tomatoes. The overall accuracy of defect detection attained by the rule based approach and the neural network method were 84 and 87.5% respectively. The inspection speed of 180 tomatoes min-1 was achieved by the algorithms and the prototype developed. Comparison of the results obtained by the rule based and neural network approaches are also presented in this paper.

KW - Defect detection

KW - Machine vision

KW - Neural network

KW - Rule based approach

KW - Tomato sorting

UR - http://www.scopus.com/inward/record.url?scp=84878243613&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878243613&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84878243613

VL - 15

SP - 173

EP - 180

JO - Agricultural Engineering International: CIGR Journal

JF - Agricultural Engineering International: CIGR Journal

SN - 1682-1130

IS - 1

ER -