Interactive machine learning for soybean seed and seedling quality classification

Author(s)

de Medeiros, Andre Dantas ^[1] ; Capobiango, Nayara Pereira ^[1] ; da Silva, Jose Maria ^[1] ; da Silva, Laercio Junio ^[1] ; da Silva, Clissia Barboza ^[2] ; Fernandes dos Santos Dias, Denise Cunha ^[1]

Affiliation

^[1] Univ Fed Vicosa, Agron Dept, BR-36570900 Vicosa, MG - Brazil

^[2] Univ Sao Paulo, Ctr Nucl Energy Agr CENA, BR-13416000 Piracicaba, SP - Brazil

• Document type: Journal article
• Source: SCIENTIFIC REPORTS; v. 10, n. 1 JUL 9 2020.
• Web of Science Citations: 0

Abstract

New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process. The aim of this study was to propose an approach based on interactive and traditional machine learning methods to classify soybean seeds and seedlings according to their appearance and physiological potential. In addition, we correlated the appearance of seeds to their physiological performance. Images of soybean seeds and seedlings were used to develop models using low-cost approaches and free-access software. The models developed showed high performance, with overall accuracy reaching 0.94 for seeds and seedling classification. The high precision of the models that were developed based on interactive and traditional machine learning demonstrated that the method can easily be used to classify soybean seeds according to their appearance, as well as to classify soybean seedling vigor quickly and non-subjectively. The appearance of soybean seeds is strongly correlated with their physiological performance. (AU)

• FAPESP's process: 17/15220-7 - Non-destructive image analysis methods for seed quality evaluation
• Grantee: Clíssia Barboza Mastrangelo
• Support Opportunities: Research Grants - Young Investigators Grants