Plant diseases are a huge danger to food security, yet owing to the lack of infrastructure in several regions of the world, timely detection is challenging. Smartphone-assisted detection of disease is now achievable thanks to a combination of rising global smartphone usage & recent advancements in machine vision facilitated by depth learning. They trained a depth convolutional neural network to detect 16 crops & 25 diseases utilizing a public dataset for 64,412 pictures of damaged & normal leaf tissue taken under controlled settings (absence thereof). On the held-out testing set, the training set achieved an accuracy of 99.35 percent, showing the practicality of this strategy. The method of training deep learning techniques increasingly vast & available to the public specific sequence points to a clear route to widespread global smartphone assisted plant disease detection.
Digital Object Identifier (DOI)
Nandhini, S. and Ashokkumar, K.
"Machine Learning Technique for Crop Disease Prediction Through Crop Leaf Image,"
Applied Mathematics & Information Sciences: Vol. 16:
2, Article 2.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol16/iss2/2