Abstract
The paper proposes a Post-processing Fusion Framework (PFF) for crop disease detection. The framework combines the prediction matrices produced by the multiple deep learning models and increases the overall classification accuracy of the system. The model is tested on the Plant Village dataset covering 14 plants and 26 diseases in 54,305 images, divided into 38 classes. Five deep learning models are used in the classification stage. Further, the PFF is applied to the results of the classification stage. Post-processing enhanced the efficiency of the system and achieved an accuracy of 99.33%. It secures 99.99%, 99.61% and 99.42% scores for top-5 accuracy, Mean Reciprocal Rank and Mean Average Precision values, respectively. Additionally, the classification rate of the approach is less than one second per test image. The high speed and accuracy make the technique highly suitable for real cultivation early warning systems.
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: IOP Conference Series: Materials Science and Engineering
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.
