Image-Based Tomato Leaves Diseases Detection Using Deep Learning

Download Edit this record How to cite View on PhilPapers
Abstract
: Crop diseases are a key danger for food security, but their speedy identification still difficult in many portions of the world because of the lack of the essential infrastructure. The mixture of increasing worldwide smartphone dispersion and current advances in computer vision made conceivable by deep learning has cemented the way for smartphone-assisted disease identification. Using a public dataset of 9000 images of infected and healthy Tomato leaves collected under controlled conditions, we trained a deep convolutional neural network to identify 5 diseases. The trained model achieved an accuracy of 99.84% on a held-out test set, demonstrating the feasibility of this approach. Overall, the approach of training deep learning models on increasingly large and publicly available image dataset presents a clear path toward smartphone-assisted crop disease diagnosis on a massive global scale.
Categories
(categorize this paper)
PhilPapers/Archive ID
ASHITL-3
Revision history
Archival date: 2019-02-09
View upload history
References found in this work BETA
Diabetes Prediction Using Artificial Neural Network.Nesreen Samer El_Jerjawi & Samy S. Abu-Naser - 2018 - International Journal of Advanced Science and Technology 121:54-64.
Email Classification Using Artificial Neural Network.Ahmed Alghoul, Sara Al Ajrami, Ghada Al Jarousha, Ghayda Harb & Samy S. Abu-Naser - 2018 - International Journal of Academic Engineering Research (IJAER) 2 (11):8-14.
Developing an Expert System for Plant Disease Diagnosis.Abu-Naser, S. S.; Kashkash, K. A. & Fayyad, M.

Add more references

Citations of this work BETA

No citations found.

Add more citations

Added to PP index
2019-02-09

Total views
287 ( #10,466 of 39,984 )

Recent downloads (6 months)
287 ( #1,130 of 39,984 )

How can I increase my downloads?

Downloads since first upload
This graph includes both downloads from PhilArchive and clicks to external links.