A Multi-Scale Feature Fusion Network for Detecting and Classifying Apple Leaf Diseases

Assad S. Doutoum, Recep Eryigit, Bulent Tugrul

2025

Abstract

Early detection and identification of leaf diseases reduce expenses and increase profits. Thus, it is essential for producers to be aware of the symptoms and indications of these leaf diseases and take the necessary preventative measures. Early diagnosis and treatment can also help prevent the disease from spreading to healthy plants. For successful disease control, regular inspections of orchards are essential. As well as being costly and time-consuming, traditional methods require a great deal of labor. However, the use of modern technologies and methods such as computer vision will both increase successes and reduce costs. Deep learning methods can be used to detect and classify diseases, as well as predict the likelihood of them occurring. Though, a particular CNN architecture may focus on a subset of features, while another may discover other additional features not extracted from the dataset. Robust classification models should be developed that perform consistently well when different environmental factors such as light, angle, background and noise vary. To solve these challenges, this study proposes a multi-scale feature fusion network (MFFN) that combines features from different scales or levels of detail in an image to improve the performance and robustness of classification models. The proposed method is evaluated on a publicly available dataset and is shown to improve the performance of the original models. Four branches applied to CNN architectures were simultaneously trained and merged to accurately classify and predict infected apple leaves. The merged model was able to detect infected leaves with a high degree of accuracy, significantly through the combined models. The merged model was able to accurately predict the unhealthy apple leaves with a 99.36% on the training accuracy, 98.90% on the validation accuracy, and 98.28% on the test accuracy. The results show that combining the models is an effective way to increase the accuracy of predictions under volatile conditions.

Paper Citation

in Harvard Style

Doutoum A., Eryigit R. and Tugrul B. (2025). A Multi-Scale Feature Fusion Network for Detecting and Classifying Apple Leaf Diseases. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-758-0, SciTePress, pages 13-20. DOI: 10.5220/0013447700003967

in Bibtex Style

@conference{data25,
author={Assad Doutoum and Recep Eryigit and Bulent Tugrul},
title={A Multi-Scale Feature Fusion Network for Detecting and Classifying Apple Leaf Diseases},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2025},
pages={13-20},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013447700003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - A Multi-Scale Feature Fusion Network for Detecting and Classifying Apple Leaf Diseases
SN - 978-989-758-758-0
AU - Doutoum A.
AU - Eryigit R.
AU - Tugrul B.
PY - 2025
SP - 13
EP - 20
DO - 10.5220/0013447700003967
PB - SciTePress