Machine vision based soybean quality evaluation

Md Abdul Momin, Kazuya Yamamoto, Munenori Miyamoto, Naoshi Kondo, Tony E Grift

Research output: Contribution to journalArticle

Abstract

A novel proof of concept was developed targeted at the detection of Materials Other than Grain (MOGs) in soybean harvesting. Front lit and back lit images were acquired, and image processing algorithms were applied to detect various forms of MOG, also known as dockage fractions, such as split beans, contaminated beans, defect beans, and stem/pods. The HSI (hue, saturation and intensity) colour model was used to segment the image background and subsequently, dockage fractions were detected using median blurring, morphological operators, watershed transformation, and component labelling based on projected area and circularity. The algorithms successfully identified the dockage fractions with an accuracy of 96% for split beans, 75% for contaminated beans, and 98% for both defect beans and stem/pods.

Original languageEnglish (US)
Pages (from-to)452-460
Number of pages9
JournalComputers and Electronics in Agriculture
Volume140
DOIs
StatePublished - Aug 2017

Fingerprint

computer vision
Computer vision
defect
soybean
beans
stem
soybeans
Defects
Watersheds
image processing
Labeling
Image processing
watershed
saturation
Color
pods
material forms
stems
evaluation
material

Keywords

  • Backlit
  • Foreign materials identification
  • Front lit
  • Image processing

ASJC Scopus subject areas

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

Cite this

Machine vision based soybean quality evaluation. / Momin, Md Abdul; Yamamoto, Kazuya; Miyamoto, Munenori; Kondo, Naoshi; Grift, Tony E.

In: Computers and Electronics in Agriculture, Vol. 140, 08.2017, p. 452-460.

Research output: Contribution to journalArticle

Momin, Md Abdul ; Yamamoto, Kazuya ; Miyamoto, Munenori ; Kondo, Naoshi ; Grift, Tony E. / Machine vision based soybean quality evaluation. In: Computers and Electronics in Agriculture. 2017 ; Vol. 140. pp. 452-460.
@article{5bbdaf8aad1347cc8df8d753993ecee4,
title = "Machine vision based soybean quality evaluation",
abstract = "A novel proof of concept was developed targeted at the detection of Materials Other than Grain (MOGs) in soybean harvesting. Front lit and back lit images were acquired, and image processing algorithms were applied to detect various forms of MOG, also known as dockage fractions, such as split beans, contaminated beans, defect beans, and stem/pods. The HSI (hue, saturation and intensity) colour model was used to segment the image background and subsequently, dockage fractions were detected using median blurring, morphological operators, watershed transformation, and component labelling based on projected area and circularity. The algorithms successfully identified the dockage fractions with an accuracy of 96{\%} for split beans, 75{\%} for contaminated beans, and 98{\%} for both defect beans and stem/pods.",
keywords = "Backlit, Foreign materials identification, Front lit, Image processing",
author = "Momin, {Md Abdul} and Kazuya Yamamoto and Munenori Miyamoto and Naoshi Kondo and Grift, {Tony E}",
year = "2017",
month = "8",
doi = "10.1016/j.compag.2017.06.023",
language = "English (US)",
volume = "140",
pages = "452--460",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",

}

TY - JOUR

T1 - Machine vision based soybean quality evaluation

AU - Momin, Md Abdul

AU - Yamamoto, Kazuya

AU - Miyamoto, Munenori

AU - Kondo, Naoshi

AU - Grift, Tony E

PY - 2017/8

Y1 - 2017/8

N2 - A novel proof of concept was developed targeted at the detection of Materials Other than Grain (MOGs) in soybean harvesting. Front lit and back lit images were acquired, and image processing algorithms were applied to detect various forms of MOG, also known as dockage fractions, such as split beans, contaminated beans, defect beans, and stem/pods. The HSI (hue, saturation and intensity) colour model was used to segment the image background and subsequently, dockage fractions were detected using median blurring, morphological operators, watershed transformation, and component labelling based on projected area and circularity. The algorithms successfully identified the dockage fractions with an accuracy of 96% for split beans, 75% for contaminated beans, and 98% for both defect beans and stem/pods.

AB - A novel proof of concept was developed targeted at the detection of Materials Other than Grain (MOGs) in soybean harvesting. Front lit and back lit images were acquired, and image processing algorithms were applied to detect various forms of MOG, also known as dockage fractions, such as split beans, contaminated beans, defect beans, and stem/pods. The HSI (hue, saturation and intensity) colour model was used to segment the image background and subsequently, dockage fractions were detected using median blurring, morphological operators, watershed transformation, and component labelling based on projected area and circularity. The algorithms successfully identified the dockage fractions with an accuracy of 96% for split beans, 75% for contaminated beans, and 98% for both defect beans and stem/pods.

KW - Backlit

KW - Foreign materials identification

KW - Front lit

KW - Image processing

UR - http://www.scopus.com/inward/record.url?scp=85021683623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021683623&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2017.06.023

DO - 10.1016/j.compag.2017.06.023

M3 - Article

AN - SCOPUS:85021683623

VL - 140

SP - 452

EP - 460

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

ER -