Claim · model-written summary
SSD MobileNet v2 took less processing time but had lower accuracy.
- Taxon
- PlantsViridiplantaet0
- Outcome
- time to processe0
- Direction
- lesse0
- Comparator
- SSD Mobilenet v2 modele1
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingValueQualifier
Verbatim
e0“this model took less time to process, its accuracy level was lower”
e1“SSD Mobilenet v2 model”
t0“Plants”
Title
Using Deep Learning Model to Identify Iron Chlorosis in Plants
Munir Majdalawieh; Shafaq Khan; Md. T. Islam IEEE Access 2023. doi:10.1109/access.2023.3273607
Other claims from this paper (4)
- Method / resource SSD MobileNet v2 classification accuracy ranged from 93% to 98%.
- Method / resource EfficientDet D0 accuracy ranged from 87% to 98.4%.
- Method / resource EfficientDet D0 required more processing time.
- Recommendation The authors conclude that both models are useful for real-time classification and EfficientDet D0 may perform better.