Machine vision based soybean quality evaluation

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

Research output: Contribution to journalArticlepeer-review


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
StatePublished - Aug 2017


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

ASJC Scopus subject areas

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


Dive into the research topics of 'Machine vision based soybean quality evaluation'. Together they form a unique fingerprint.

Cite this