Comparative Analysis of Convolutional Neural Network, MobileNetV2, and EfficientNet for Tomato Leaf Disease Classification

Guntur Guntur; Abdul Latief Arda; Andy Lukman  Affandy; Syamsu  Alam; Matalangi Matalangi

doi:10.52436/1.jutif.2026.7.4.5704

Authors

Guntur Undergraduate Program in Computer Systems, Universitas Handayani Makassar, Indonesia
Abdul Latief Arda Postgraduate Program in Computer Systems, Universitas Handayani Makassar, Indonesia
Andy Lukman Affandy Undergraduate Program in Computer Systems, Universitas Handayani Makassar, Indonesia
Syamsu Alam Undergraduate Program in Computer Systems, Universitas Handayani Makassar, Indonesia
Matalangi Department of Information Systems, Indonesian Christian University Paulus, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.4.5704

Keywords:

CNN, Deep Learning, Image Classification, Tomato Leaf Disease, Transfer Learning

Abstract

Tomato leaf diseases pose a serious threat to crop productivity and require accurate and efficient identification methods. Traditional visual inspection is time-consuming and prone to human error, motivating the need for automated image-based classification approaches. This study aims to evaluate the effectiveness of deep learning models for tomato leaf disease classification by comparing a custom Convolutional Neural Network and a transfer learning–based EfficientNet-B0 model. An experimental methodology was employed using a publicly available tomato leaf image dataset comprising nine disease classes and one healthy class. Images were preprocessed and augmented before being used to train a custom CNN and an EfficientNet-B0 model with a two-stage fine-tuning strategy. Model performance was evaluated using accuracy, precision, recall, F1-score, confusion matrices, and Receiver Operating Characteristic–Area Under Curve analysis. The experimental results demonstrate that the transfer learning approach significantly outperformed the custom CNN, with EfficientNet-B0 achieving the highest classification accuracy of 95.73% and improved class separability across disease categories.This research contributes to the field of Informatics and Computer Science by providing empirical evidence on the effectiveness of efficient transfer learning architectures for agricultural image classification. The findings support the development of resource-efficient artificial intelligence systems suitable for smart agriculture and edge-based deployment.

Downloads

Download data is not yet available.

References

H. Cheng and J. Lee, “Deep Learning-Based Crop Disease Diagnosis Using Convolutional Neural Networks,” Computers and Electronics in Agriculture, vol. 198, p. 107010, 2022, doi: 10.1016/j.compag.2022.107010.

A. Kamilaris and F. X. Prenafeta-Boldú, “Deep Learning in Agriculture: A Survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018, doi: 10.1016/j.compag.2018.02.016.

M. Zemati, L. Boussaid, and A. Douik, “CNN-Based Plant Disease Classification under Complex Backgrounds,” Neural Computing and Applications, vol. 36, pp. 2123–2137, 2024, doi: 10.1007/s00521-023-09011-4.

A. Fuentes, S. Yoon, J. Lee, and D. S. Park, “Robust Plant Disease Detection Using Deep Learning,” Frontiers in Plant Science, vol. 12, p. 653344, 2021, doi: 10.3389/fpls.2021.653344.

I. Pacal, D. Karaboga, and A. Basturk, “Overfitting Issues in CNN-Based Plant Disease Recognition,” Artificial Intelligence Review, vol. 57, 2024, doi: 10.1007/s10462-023-10456-7.

T. Nguyen and H. Vo, “ImageNet-Based Transfer Learning for Plant Disease Recognition,” Remote Sensing, vol. 15, no. 4, p. 1023, 2023, doi: 10.3390/rs15041023.

D. Singh and A. Kaur, “Transfer Learning for Small-Scale Agricultural Datasets,” Sensors, vol. 22, no. 18, p. 6952, 2022, doi: 10.3390/s22186952.

S. Basu and R. Mukherjee, “Deep Learning Applications in Smart Agriculture,” Agronomy, vol. 13, no. 9, p. 2145, 2023, doi: 10.3390/agronomy13092145.

M. Alam, A. Rahman, and M. Hasan, “EfficientNet-Based Crop Disease Classification,” Computers and Electronics in Agriculture, vol. 214, p. 108256, 2024, doi: 10.1016/j.compag.2024.108256.

M. Alam and S. Rahman, “Evaluation of Pretrained CNN Models for Plant Disease Detection,” Agronomy, vol. 14, no. 2, p. 411, 2024, doi: 10.3390/agronomy14020411.

M. Tan, Q. Le, and R. Pang, “EfficientNetV2: Smaller Models and Faster Training,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 6, pp. 6937–6954, 2023, doi: 10.1109/TPAMI.2022.3203316.

H. Kibriya and others, “Baseline CNN Architectures for Crop Disease Classification,” IEEE Access, vol. 9, pp. 112345–112356, 2021, doi: 10.1109/ACCESS.2021.3058212.

I. Pacal, D. Karaboga, and A. Basturk, “Comparative Analysis of CNN and Transfer Learning Models for Plant Disease Classification,” Artificial Intelligence Review, vol. 57, pp. 145–178, 2024, doi: 10.1007/s10462-023-10478-1.

D. P. Hughes and M. Salathé, “An Open Access Repository of Images on Plant Health,” Scientific Data, vol. 2, p. 150032, 2015, doi: 10.1038/sdata.2015.32.

C. Shorten and T. Khoshgoftaar, “A Survey on Image Data Augmentation,” Journal of Big Data, vol. 6, p. 60, 2019, doi: 10.1186/s40537-019-0197-0.

Z. Zhang, “Improved Adam Optimizer for Deep Neural Networks,” Neural Processing Letters, vol. 54, pp. 1–15, 2022, doi: 10.1007/s11063-021-10631-4.

A. L. Arda, Syamsu Alam, and Matalangi, “Comparative Analysis of CNN, MobileNetV2 and EffecientNetBO in Smart Farming System for Chili Leaf Disease Detection,” J. RESTI (Rekayasa Sist. Teknol. Inf.), vol. 9, no. 6, pp. 1417–1430, Dec. 2025, doi: 10.29207/resti.v9i6.6709.

T. Fawcett, “An Introduction to ROC Analysis,” Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006, doi: 10.1016/j.patrec.2005.10.010.

J. G. Arnal Barbedo, “Plant disease identification from individual lesions and spots using deep learning,” Biosystems Engineering, vol. 180, pp. 96–107, Apr. 2019, doi: 10.1016/j.biosystemseng.2019.02.002.

O. Attallah, “Plant Disease Detection Using Convolutional Neural Networks: A Survey,” Agriculture, vol. 13, no. 2, p. 312, 2023, doi: 10.3390/agriculture13020312.

S. Sladojevic and others, “Deep Neural Networks for Plant Disease Recognition,” Computational Intelligence and Neuroscience, p. 3289801, 2016, doi: 10.1155/2016/3289801.

K. P. Ferentinos, “Deep Learning Models for Plant Disease Detection and Diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018, doi: 10.1016/j.compag.2018.01.009.

N. Khan and others, “Edge-Aware Deep Learning Models for Smart Agriculture Applications,” Sensors, vol. 24, no. 3, p. 1123, 2024, doi: 10.3390/s24031123.

M. Hasan and others, “A Comprehensive Review on Deep Learning-Based Plant Disease Detection,” Expert Systems with Applications, vol. 216, p. 119471, 2023, doi: 10.1016/j.eswa.2022.119471.

A. Saleem, M. Raza, and Y. Khan, “Deep Learning-Based Plant Disease Recognition: Recent Advances and Challenges,” Computers and Electronics in Agriculture, vol. 221, p. 108973, 2025, doi: 10.1016/j.compag.2025.108973.

M. A. Rahman and others, “Transfer Learning with EfficientNet for Plant Disease Classification,” IEEE Access, vol. 11, pp. 45678–45690, 2023, doi: 10.1109/ACCESS.2023.3276543.

K. Li, X. Zhang, and Y. Wang, “Deep Learning-Based Plant Disease Detection: A Review,” Sensors, vol. 24, no. 1, p. 155, 2024, doi: 10.3390/s24010155.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, pp. 436–444, 2015, doi: 10.1038/nature14539.

A. Krizhevsky, I. Sutskever, and G. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017, doi: 10.1145/3065386.