Improved Grape Leaf Disease Detection with GAN- Augmented ResNet and EfficientNet

DOI

10.2991/978-94-6463-738-0_53How to use a DOI?

Keywords

Grape Leaf Disease Detection; Deep Learning; ResNet; EfficientNetB5; Ensemble Learning; Precision Agriculture; Image Classification; GAN; CNN; Neural Network

Abstract

This research focuses on leveraging deep learning models to detect grape leaf diseases with high precision and accuracy, addressing a critical challenge in the viticulture industry. Analyzing a dataset of 5779 training images and 360 test images, a deep learning model based on convolutional neural networks such as ResNet, EfficientNetB5, a two-meter model consisting of an EfficientNetB5 and a ResNet model were used to distinguish between diseased and healthy grape leaves. It has been established that the proposed ensemble model was accurate with a level of 98.06% while surpassing ResNet (91.23%) and EfficientNetB5 (93.12%). Performance indicators were also higher in the ensemble model with high specificities of 0.98, Recall of 0.99 and the F1 score at 0.98, this predisposed the model to the lowest number of false positives and false negatives. The training and validation loss curves showed how the model was trained to learn the output data well, and how well the ensemble model generalized from the training stage by having a loss close to 0.1. These results reveal that ensemble learning can serve for accurate disease identification in precision agriculture to minimize crop yield damages by timely intervention.

Copyright

© 2025 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  - Sarah Khursheed
AU  - Balwinder Kaur
PY  - 2025
DA  - 2025/06/22
TI  - Improved Grape Leaf Disease Detection with GAN- Augmented ResNet and EfficientNet
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 654
EP  - 669
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_53
DO  - 10.2991/978-94-6463-738-0_53
ID  - Khursheed2025
ER  -