Deep Transfer Learning with Hybrid CNN Fusion for Smart Tomato Leaf Disease Diagnosis

Ahmed Waheed Awan; Syed Muhammad Ali; Osama Zafar; Hania Siddiqui; Muhammad Salman; Armughan Ali

Authors

Ahmed Waheed Awan Department of Electrical Engineering, Wah Engineering College, University of Wah, Wah Cantt 47040, Pakistan; ZerothGen, Hasan Abdal 43703, Pakistan
Syed Muhammad Ali Department of Computer Science, University of Wah, Wah Cantt 47040, Pakistan
Osama Zafar Department of Computer Science, COMSATS University Islamabad, Pakistan.
Hania Siddiqui Department of Computer Science, University of Wah, Wah Cantt 47040, Pakistan
Muhammad Salman Department of Electrical Engineering, Wah Engineering College, University of Wah, Wah Cantt 47040, Pakistan, ZerothGen, Hasan Abdal 43703, Pakistan
Armughan Ali Department of Electrical Engineering, Wah Engineering College, University of Wah, Wah Cantt 47040, Pakistan, 2Department of Computer Science, University of Wah, Wah Cantt 47040, Pakistan

Keywords:

Deep Learning, Plant Diseases, Tomato Leaf Disease Detection, Transfer Learning, CNN Fusion, Efficient Net, Mobile Net, Dense Net, Feature-Level Fusion, Precision Agriculture, Explainable AI

Abstract

Tomato plants are highly susceptible to a wide range of bacterial, viral, and fungal diseases that significantly affect crop yield and agricultural productivity, making rapid and accurate identification essential for effective crop management and early intervention. This paper presents Fusion-TLNet, a hybrid deep learning framework that integrates multiple transfer learning models using a feature-level fusion strategy for robust tomato leaf disease classification. The proposed architecture combines three pretrained convolutional neural networks: EfficientNetB0, MobileNetV3-Small, and DenseNet121 to capture complementary hierarchical representations of texture, shape, and color features from tomato leaf images. Experimental results on the PlantVillage dataset demonstrate that Fusion-TLNet achieves an accuracy of 99.34%, precision of 99.28%, recall of 99.22%, and F1-score of 99.25%, outperforming individual backbone models by up to 1.23% in accuracy. In addition, the model maintains a low prediction latency of 9.7 ms per image, making it suitable for real-time deployment in resource-constrained agricultural environments. The proposed model provides an interpretable, efficient, and scalable solution for intelligent plant disease diagnosis, supporting the advancement of data-driven precision agriculture.

References

MD Jiabul Hoque, Md. Saiful Islam, Md. Khaliluzzaman, “AI-Powered Precision in Diagnosing Tomato Leaf Diseases,” Complexity, 2025, doi: https://doi.org/10.1155/cplx/7838841Digital Object Identifier (DOI).

Mesfin Abebe, Zewdu Tiumay, “Development of an SDG-driven Convolutional Neural Network (CNN) model for multi-class classification of Tomato Leaf diseases using combined public and local datasets,” J. Integr. Sci. Technol., vol. 13, no. 3, 2025, doi: 10.62110/sciencein.jist.2025.v13.1063.

Harisu Abdullahi Shehu, Aniebietabasi Ackley, “Early detection of tomato leaf diseases using transformers and transfer learning,” Eur. J. Agron., vol. 168, p. 127625, 2025, doi: https://doi.org/10.1016/j.eja.2025.127625.

Md Assaduzzaman, Prayma Bishshash, “XSE-TomatoNet: An explainable AI based tomato leaf disease classification method using EfficientNetB0 with squeeze-and-excitation blocks and multi-scale feature fusion,” MethodsX, vol. 14, p. 103159, 2025, doi: https://doi.org/10.1016/j.mex.2025.103159.

R. Thangaraj, S. Anandamurugan, and V. K. Kaliappan, “Automated tomato leaf disease classification using transfer learning-based deep convolution neural network,” J. Plant Dis. Prot. 2020 1281, vol. 128, no. 1, pp. 73–86, Nov. 2020, doi: 10.1007/S41348-020-00403-0.

M. Agarwal, A. Singh, S. Arjaria, A. Sinha, and S. Gupta, “ToLeD: Tomato Leaf Disease Detection using Convolution Neural Network,” Procedia Comput. Sci., vol. 167, pp. 293–301, Jan. 2020, doi: 10.1016/J.PROCS.2020.03.225.

Jin Hee Lim, Omneya Attallah, “Tomato Leaf Disease Classification via Compact Convolutional Neural Networks with Transfer Learning and Feature Selection,” Hoticulture, vol. 9, no. 2, p. 149, 2023, doi: https://doi.org/10.3390/horticulturae9020149.

Maha Altalak, Mohammad Ammad Uddin, “A Hybrid Approach for the Detection and Classification of Tomato Leaf Diseases,” Appl. Sci., vol. 12, no. 16, p. 8182, 2022, doi: https://doi.org/10.3390/app12168182.

N. K. Trivedi et al., “Early detection and classification of tomato leaf disease using high-performance deep neural network,” Sensors, vol. 21, no. 23, 2021, doi: 10.3390/s21237987.

M. A. I. Neloy, F. Mahamud, N. Nahar, M. S. Hossain, and K. Andersson, “Tomato Leaf Disease Classification Using Transfer Learning Method,” Lect. Notes Networks Syst., vol. 569 LNNS, pp. 231–241, 2023, doi: 10.1007/978-3-031-19958-5_22/SAVE-RESEARCH.

S. Kalaivani, C. Tharini, T. M. S. Viswa, K. Z. F. Sara, and S. T. Abinaya, “ResNet-Based Classification for Leaf Disease Detection,” J. Inst. Eng. Ser. B 2024 1061, vol. 106, no. 1, pp. 1–14, May 2024, doi: 10.1007/S40031-024-01062-7.

S. Ahmed, M. B. Hasan, T. Ahmed, M. R. K. Sony and M. H. Kabir, “Less is More: Lighter and Faster Deep Neural Architecture for Tomato Leaf Disease Classification,” IEEE Access, vol. 10, pp. 68868–68884, 2022, doi: 10.1109/ACCESS.2022.3187203.

Tiancan Jian, Haixia Qi, “Identification of tomato leaf diseases based on DGP-SNNet,” Crop Prot., vol. 187, p. 106975, 2025, doi: https://doi.org/10.1016/j.cropro.2024.106975.

Aritra Das, Fahad Pathan, “XLTLDisNet: A novel and lightweight approach to identify tomato leaf diseases with transparency,” Heliyon, vol. 11, no. 4, 2025, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2405844025009557

B. Aminu Suleiman, S. Luka, and J. Nda Ndabula, “A CNN-SVM based model for detection and classification of Tomato leaf diseases,” J. Basics Appl. Sci. Res., vol. 3, no. 3, pp. 8–15, Jun. 2025, doi: 10.4314/JOBASR.V3I3.2.

Divas Karimanzira, “Context-Aware Tomato Leaf Disease Detection Using Deep Learning in an Operational Framework,” Electronics, vol. 14, no. 4, p. 661, 2025, doi: https://doi.org/10.3390/electronics14040661.

Aarthi Chelladurai, D. P. Manoj Kumar, “Classification of tomato leaf disease using Transductive Long Short-Term Memory with an attention mechanism,” Front. Plant Sci., vol. 15, 2024, doi: https://doi.org/10.3389/fpls.2024.1467811.

A. Ali, H. Shahbaz, S. M. Ganie, and M. M. Alfuraydan, “X-vitcnn: A novel network-level fusion of transfer learning and customized vision transformer for multi-stage alzheimer’s disease prediction using mri scans,” Diagnostics, vol. 16, no. 6, 2026.

Abdelaaziz Bellout, Mohamed Zarboubi, “LT-YOLOv10n: A lightweight IoT-integrated deep learning model for real-time tomato leaf disease detection and management,” Internet of Things, vol. 33, 2025, doi: 10.1016/j.iot.2025.101663.

S. Yadav and A. S. Tewari, “CONF-RCNN: a conformer and faster region-based convolutional neural network model for multi-label classification of tomato leaves disease in real field environment,” J. Plant Dis. Prot. 2025 1322, vol. 132, no. 2, pp. 61-, Jan. 2025, doi: 10.1007/S41348-024-01057-Y.

Hao Sun, Rui Fu, Xuewei Wang, Yongtang Wu, Mohammed Abdulhakim Al-Absi, Zhenqi Cheng, Qian Chen & Yumei Sun, “Efficient deep learning-based tomato leaf disease detection through global and local feature fusion,” BMC Plant Biol., vol. 25, no. 311, 2025, [Online]. Available: https://link.springer.com/article/10.1186/s12870-025-06247-w

David. P. Hughes, Marcel Salathe, “An open access repository of images on plant health to enable the development of mobile disease diagnostics,” arXiv:1511.08060, 2016, [Online]. Available: https://arxiv.org/abs/1511.08060

Jatin Sharma, Asma A. Al-Huqail, Ahmad Almogren, Hardik Doshi, B. Jayaprakash, B. Bharathi, Ateeq Ur Rehman & Seada Hussen, “Deep learning based ensemble model for accurate tomato leaf disease classification by leveraging ResNet50 and MobileNetV2 architectures,” Sci. Rep., vol. 15, 2025, [Online]. Available: https://www.nature.com/articles/s41598-025-98015-x