IRO Journals
Journal of Soft Computing Paradigm

Transfer Learning-based Multi-Class Plant Disease Detection Using MobileNetV2 and EfficientNet-B0

Open Access
Published: 22 June, 2026
Pages: 184-200
  • Hara Gopal V.P. , Hara Gopal V.P.
    Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, Andhra Pradesh, India
    Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, Andhra Pradesh, India
  • Chenna Varun Kumar , Chenna Varun Kumar
    Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, Andhra Pradesh, India
    Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, Andhra Pradesh, India
  • Sree Manvitha Sai P. , Sree Manvitha Sai P.
    Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, Andhra Pradesh, India
    Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, Andhra Pradesh, India
  • Mohan Reddy K. Mohan Reddy K.
    Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, Andhra Pradesh, India
    Department of Computer Science and Engineering and Business Systems, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal, Andhra Pradesh, India
view PDF
view PDF

How to Cite

V.P., Hara Gopal, Chenna Varun Kumar, Sree Manvitha Sai P., and Mohan Reddy K. 2026. “Transfer Learning-Based Multi-Class Plant Disease Detection Using MobileNetV2 and EfficientNet-B0”. Journal of Soft Computing Paradigm 8 (3): 184-200. https://doi.org/10.36548/jscp.2026.3.001.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Plant Leaf Disease Detection
Deep Learning
Convolutional Neural Networks (CNN)
Lightweight Models
Transfer Learning
Multi-Class Classification

Abstract

An early and precise identification of plant diseases helps to increase the efficiency of farming operations and minimize the economic losses associated with plant diseases. Nevertheless, applying deep learning models for plant disease identification in an agricultural setting poses certain difficulties due to high computational costs and insufficient edge device computing power. This paper presents a transfer learning-based framework for multi-class plant disease detection using MobileNetV2 and EfficientNet-B0 models. For the purpose of research, the PlantVillage dataset including potato, bell pepper, and tomato leaves was used. Images from this source underwent pre-processing that included resizing, normalizing, and augmenting images. Both transfer learning approach and fine-tuning helped to modify pre-trained CNNs for multi-class classification of different diseases affecting plants' leaves. Experiments have shown that EfficientNet-B0 model performed much better with accuracy of 95.7% and AUC of 0.98. Moreover, the proposed algorithm was exported as a TensorFlow Lite model and implemented in the Streamlit application for efficient edge deployment.

References

  1. Al Kafi, Md Abdullah, Sumit Kumar Banshal, Raka Moni, Aulia Luqman Aziz, Mohammed Aljuaid, and Rohit Bansal. "LeafAI: Interpretable Plant Disease Detection for Edge Computing." PLoS One 2026, vol. 21, no. 1: e0335956.
  2. Deepa, R., Midhun P. Mathew, and S. Baskar. "L-Net: A Lightweight CNN Framework for Sustainable Multicrop Leaf Disease Detection and Classification on Edge Devices." Sustainable Food Technology 2026, no. 4: 985-1003
  3. Gunasekaran, Harshinisree, Sujatha Rajkumar, and Lincy Kirubhadharsini B. "Lightweight Deep Learning for Tomato Disease Detection: Trends, Challenges, And Edge AI Perspectives." Frontiers in Plant Science 2025, vol. 16: 1737208.
  4. Ahamed, Md Faysal, Abdus Salam, Md Nahiduzzaman, Mohammad Abdullah-Al-Wadud, and SM Riazul Islam. "Streamlining Plant Disease Diagnosis with Convolutional Neural Networks and Edge Devices." Neural Computing and Applications 2024, vol. 36, no. 29: 18445-18477.
  5. Gonçalves, João, Eduardo Silva, Pedro Faria, Telmo Nogueira, Ana Ferreira, Cristina Carlos, and Luís Rosado. "Edge-Compatible Deep Learning Models for Detection of Pest Outbreaks in Viticulture." Agronomy 2022, vol. 12, no. 12: 3052.
  6. Hasan, Mohammad Junayed, Suvodeep Mazumdar, and Sifat Momen. "Deployable Deep Learning for Cross-Domain Plant Leaf Disease Detection via Ensemble Learning, Knowledge Distillation, And Quantization." Digital Object Identifier, IEEE Access 2025, vol. 13, 140313- 140336.
  7. Khan, Ameer Tamoor, Signe Marie Jensen, Abdul Rehman Khan, and Shuai Li. "Plant Disease Detection Model for Edge Computing Devices." Frontiers in Plant Science 2023, vol. 14: 1308528.
  8. Gookyi, Dennis Agyemanh Nana, Fortunatus Aabangbio Wulnye, Michael Wilson, Paul Danquah, Samuel Akwasi Danso, and Awudu Amadu Gariba. "Enabling Intelligence on the Edge: Leveraging Edge Impulse to Deploy Multiple Deep Learning Models on Edge Devices for Tomato Leaf Disease Detection." AgriEngineering 2024, vol. 6, no. 4: 3563-3585.
  9. Javaid, Yasir, Sana Cheema, Akkasha Latif, Atiqa Faiz ur Rehman, Aisha Tariq Khan, Qandeel Nasir, and Hafiz Farrukh Abbas. "Explainable Edge AI for Early Detection of Plant Diseases in Smart Agriculture Using Lightweight Mobilenetv2 with Gradient Saliency." Spectrum of Engineering Sciences 2026, vol. 4, no. 4: 167-192.
  10. Rashid, Mohammad Rifat Ahmmad, Md AL Ehtesum Korim, Mahamudul Hasan, Md Sawkat Ali, Mohammad Manzurul Islam, Taskeed Jabid, Raihan Ul Islam, and Maheen Islam. "An Ensemble Learning Framework with Explainable AI for Interpretable Leaf Disease Detection." Array 2025, vol. 26: 100386.
  11. Dataset: https://www.kaggle.com/datasets/abdallahalidev/plantvillage-dataset