Real-time recognition system of soybean seed full-surface defects based on deep learning

•Method of combining alternate circumrotating mechanisms and deep learning.•Quantitative summary of defects in soybean seeds at different scales.•Model comparison, selection and optimization.•Full-surface recognition rate of defects in different scales exceeds 97.7%•Realize real-time classification...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computers and electronics in agriculture 2021-08, Vol.187, p.106230, Article 106230
Hauptverfasser:	Zhao, Guoyang, Quan, Longzhe, Li, Hailong, Feng, Huaiqu, Li, Songwei, Zhang, Shuhan, Liu, Ruiqi
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Brightness Deep learning Defect scale Edge system Full surface Image classification Machine learning Machine vision Real time Recognition Seeds Soybean seed Soybeans Surface defects Technology assessment
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!