Fruit Disease Detection Using Lightweight Transfer Learning Techniques

Anuradha Varal, Anuradha Varal, Shabnam Sayyad

2025

Abstract

Fruit disease identification is crucial and must be performed quickly to enhance the productivity of agriculture and reduce crop losses. In this context, fruit disease classification with CNN, powered by efficient transfer learning, is proposed. The pre-trained weights for both MobileNetV2 and VGG16 models are used; some of the initial layers are selectively frozen to create a trade-off between model performance and computational efficiency. This approach will allow us to retain critical features learned from large-scale datasets with reduced training loads on limited hardware. By optimizing the model, high classification accuracy can be achieved with a reduction in processing time and lower RAM consumption, which eventually will make the approach most suitable for deployment on devices with limited resources. To develop variability within the dataset and limit overfitting, augmentations like rotation, flipping, and zooming would be performed on the augmented data. Experimental sessions were carried out on a publicly available dataset of fruit disease images from several classes, showing healthy and diseased conditions. The results clearly describe how, among all, MobileNetV2 ensures the best trade-off between accuracy and efficiency for such applications in real time. Overall, this work showed a proper approach on how to conduct the detection of fruit diseases with lightweight transfer learning models and provided useful insights into implementing the technology for precision agriculture in resource-constrained settings.

Paper Citation

in Harvard Style

Varal A. and Sayyad S. (2025). Fruit Disease Detection Using Lightweight Transfer Learning Techniques. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 498-505. DOI: 10.5220/0013595600004664

in Bibtex Style

@conference{incoft25,
author={Anuradha Varal and Shabnam Sayyad},
title={Fruit Disease Detection Using Lightweight Transfer Learning Techniques},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT},
year={2025},
pages={498-505},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013595600004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT
TI - Fruit Disease Detection Using Lightweight Transfer Learning Techniques
SN - 978-989-758-763-4
AU - Varal A.
AU - Sayyad S.
PY - 2025
SP - 498
EP - 505
DO - 10.5220/0013595600004664
PB - SciTePress