Fostering Crop Health - Investigating state-of-art CNNs for Corn and Maize leaf disease Analysis

DOI

10.2991/978-94-6463-471-6_95How to use a DOI?

Keywords

VGG; ResNet; Inception; EfficientNet and MobileNet

Abstract

The fast detection and sorting of plant diseases are really important to make sure we have enough food and keep farming productive. In this study, we're using the latest technology called Convolutional Neural Networks (CNNs) to figure out what's wrong with maize leaves. We're using five different CNN models to do this and making them work better for identifying maize leaf diseases. Our main goals are to compare how well these models perform, see how accurate they are, and find the best one for identifying maize leaf diseases. We're looking at a big collection of pictures of maize leaves, some healthy and some sick, for our study. We're using popular models like VGG, ResNet, Inception, EfficientNet, and MobileNet which are really good at understanding pictures. We're making these models better at finding diseases on maize leaves by adjusting their settings. Our study shows that these modern models are really good at spotting plant diseases. We're checking how accurate each model is and comparing them to find the one that's the best at knowing which disease is on a maize leaf. We're using different ways to measure their performance, like how well they remember things, how exact they are, and other factors. Among all the models we studied, VGG is the most accurate and promising for identifying maize leaf diseases. This model could be really helpful in real farms because it's really good at finding problems in the pictures. It's especially good to see small details that show which disease is on the leaf. To sum it up, our study shows that using advanced CNN models is really important for finding plant diseases. The results make it clear that picking the right model is key to knowing what disease is there. These models could also make farming better in the future.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Johnbee Shaik
AU  - Srihari Babu Gole
AU  - P. Nagamani
AU  - M. Gayathri
AU  - M. D. Sajid Pasha
AU  - Ravi Regula Gadda
PY  - 2024
DA  - 2024/07/30
TI  - Fostering Crop Health - Investigating state-of-art CNNs for Corn and Maize leaf disease Analysis
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 990
EP  - 1001
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_95
DO  - 10.2991/978-94-6463-471-6_95
ID  - Shaik2024
ER  -