Soybean Quality Evaluation Using Machine Vision
Year: 2026
Type: article
Abstract: This study presents a proof-of-concept method for identifying materials other than grain (MOG) during soybean harvest. Images of grain samples were taken using front-lighting and back-lighting techniques, and various image processing techniques were used to identify different dockage fractions, namely split, contaminated, and defective beans and stems/pods. The image background was segmented using the HSI color space model, followed by the identification of the dockage fractions using median filtering, morphological operations, watershed transformation, and component labeling based on projective area and circularity. Split, contaminated, and defective beans and stems/pods were accurately identified by the algorithms with 96%, 75%, 98%, and 98% accuracy, respectively.
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: green
OpenAlex ID: W7230603238
