Abstract
For food security in future, precise measurements of disease incidence and severity are crucial for suitable treatments and adopting preventive measures. In this paper, the authors have implemented three well known CNN models, namely, AlexNet, SqueezeNet and Inception V3, for evaluating disease severity in Tomato Late Blight disease. The images utilized were selected from the PlantVillage dataset and separated into three stages (early, middle and end) of disease severity. The CNN architectures were implemented in two different modes, i.e. transfer learning and feature extraction (where the extracted feature set was used to train a multiclass SVM). As compared to the other two networks, AlexNet achieved the highest accuracy in both approaches, 89.69% and 93.4% respectively.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of Discrete Mathematical Sciences and Cryptography
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
