Claim · model-written summary
Moderate model size gave the best kernel selection.
Zea maysNot reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingValueQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The size of the network model has an effect on the accurate selection of maize kernels, and a moderate-size model is the best”
Title
Chengshun Zhao; Longzhe Quan; Hailong Li; et al. Transactions of the ASABE 2020. doi:10.13031/trans.13389
Other claims from this paper (8)
- Method / resource Model 1.0 had the highest recall, 98.42%.
- Method / resource Model 1.0 reached 97.27% mAP for excellent kernels only.
- Method / resource Model 1.0 required fewer computer resources.
- Method / resource Model 2.0 precision exceeded Faster R-CNN by 3.73%.
- Method / resource Model 2.0 recall exceeded Faster R-CNN by 3.55%.
- Method / resource Model 2.0 F1 exceeded Faster R-CNN by 3.79%.
- Method / resource Model 2.0 false positive rate was reduced by 1.31% versus Faster R-CNN.
- Method / resource Model 2.0 had the best overall performance among three variants.