PLANT LEAF DISEASE CLASSIFICATION USING DEEP TRANSFER LEARNING

Date

2025-8-13

Author

Ishaq, Muhammad Hamza

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

149
views

0
downloads

Cite This

Agriculture is a fundamental pillar of economic development and global food security. For agricultural sustainability, it is important to accurately and early diagnose if a plant is infected by any disease in order to protect the plant. This research proposes two deep learning-based models: a Fusion Deep Neural Network (FDNN) and a Fusion Convolutional Neural Network (FCNN), for multi-class plant leaf disease classification using the publicly available PlantVillage dataset. Features were extracted from three pre-trained architectures (ResNet50, VGG16, and EfficientNetB0), concatenated, and then fed into the proposed models, which were trained on eight balanced disease classes. The FDNN model achieved a test accuracy of 98.25%, and an average 5-fold cross-validation accuracy of 98.76%. Meanwhile, the FCNN model attained a test accuracy of 98.38%, and an average cross-validation accuracy of 97.96%. Both models demonstrate strong effectiveness and robustness, significantly outperforming the individual architectures, indicating their potential contribution to agricultural sustainability. These results demonstrate the potential of deep learning fusion methods.

Subject Keywords

Agricultural Sustainability, Deep Learning, Fusion Model, Plant Leaf Disease, Pattern Classification

URI

https://hdl.handle.net/11511/116185

Collections

Northern Cyprus Campus, Thesis