MangoLeafXNet: An Explainable Deep Learning Model for Accurate Mango Leaf Disease Classification

Citation

Rayed, Md. Eshmam and Jim, Jamin Rahman and Islam, Md Juniadul and Mridha, M. F. and Kabir, Md Mohsin and Hossen, Md. Jakir (2025) MangoLeafXNet: An Explainable Deep Learning Model for Accurate Mango Leaf Disease Classification. IEEE Access, 13. pp. 93977-94008. ISSN 2169-3536

[img] Text
2.pdf - Published Version
Restricted to Repository staff only

Download (6MB)

Abstract

Addressing the global challenge of ensuring a consistent and abundant supply of fresh fruit, particularly in the context of fruit crops, is hindered by the prevalence of plant diseases. These diseases directly impact the quality of fruits, leading to a decline in overall agricultural production. Mango leaf diseases pose significant threats to global mango production, necessitating accurate and efficient classification techniques for timely disease management. Our study focuses on introducing MangoLeafXNet, a customized Convolutional Neural Network (CNN) architecture specifically tailored for the classification of mango leaf diseases, along with a healthy class. Our proposed model comprises six layers optimized to capture intricate disease patterns, demonstrating superior performance compared with prevalent pre-trained models. The model is trained and evaluated on three publicly available datasets: MangoLeafBD (4000 images across 8 classes), MangoPest (16 pest classes including healthy leaves), and MLDID (3000 high-resolution images across 5 classes). Our model demonstrated exceptional classification performance, attaining 99.8% accuracy, 99.62% recall, 99.5% precision, and an F1-score of 99.56%. Further validation on the MangoPest dataset and the Mango Leaf Disease Identification Dataset (MLDID) resulted in accuracies of 96.31% and 96.33%, respectively, confirming the robustness and adaptability of MangoLeafXNet across different datasets. Additionally, we incorporate Explainable AI techniques, including GRAD-CAM, Saliency Map, and LIME to enhance the interpretability of our model. We deployed Gradio web interface to create an interactive interface that allows users to upload images of mango leaves and get real-time classification and validation results along with confidence scores. This contribution not only advances the state-of-the-art in mango leaf disease classification but also offers promising prospects for real-time disease diagnosis and precision agriculture applications, contributing to enhanced crop health monitoring and sustainable mango cultivation practices.

Item Type: Article
Uncontrolled Keywords: Image processing, convolutional neural network, deep learning, mango leaf disease, image classification, explainable AI.
Subjects: T Technology > TD Environmental technology. Sanitary engineering > TD194-195 Environmental effects of industries and plants
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 30 Jun 2025 06:55
Last Modified: 30 Jun 2025 06:55
URII: http://shdl.mmu.edu.my/id/eprint/14174

Downloads

Downloads per month over past year

View ItemEdit (login required)