Comparative Analysis of CNN, MobileNetV2 and EffecientNetBO in Smart Farming System for Chili Leaf Disease Detection
DOI:
https://doi.org/10.29207/resti.v9i6.6709Keywords:
chili leaf disease detection, CNN, deep learning, EfficientNetB0, MobileNetV2, smart farmingAbstract
Chili leaf diseases greatly affect agricultural productivity, making early and accurate detection essential to support smart farming systems. This study presents a comparative analysis of three deep learning architectures—Convolutional Neural Network (CNN), MobileNetV2, and EfficientNetB0—for detecting chili leaf diseases using RGB images. The dataset consists of three main disease classes: Bacterial Spot, Curl Virus, and White Spot. Each model was trained and evaluated using accuracy, precision, recall, F1-score, macro AUC, and training time as performance metrics. Experimental results show that MobileNetV2 achieved the highest performance with 99% accuracy, 0.99 F1-score, and 0.99 macro AUC, although it required the longest training time of 115.12 seconds. CNN demonstrated competitive results with 96% accuracy and the shortest training time of 60 seconds, while EfficientNetB0 performed poorly with only 38% accuracy and an F1-score of 0.18. These findings highlight that model architecture, dataset characteristics, and training configuration significantly influence performance outcomes. This study contributes to the development of intelligent agricultural monitoring systems by identifying the most suitable deep learning architecture for real-time chili leaf disease detection in smart farming applications.
Downloads
References
S. Wahyuni and R. A. Putra, “Deep learning-based classification of chili leaf diseases using convolutional neural networks,” Journal of Plant Pathology, vol. 103, no. 2, pp. 375–384, 2021, doi: https://doi.org/10.1007/s42161-020-00698-5
D. Rahmawati and A. S. Nugroho, “Rice leaf disease classification using CNN and data augmentation techniques,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 6, pp. 154–162, 2020, doi: https://doi.org/10.14569/IJACSA.2020.0110619.
F. Fitriyah and A. Nugraha, “Effect of fine-tuning and weight initialization on MobileNetV2 performance for plant disease classification,” Procedia Computer Science, vol. 197, pp. 124–131, 2022, doi: https://doi.org/10.1016/j.procs.2021.12.014.
R. Hidayat and S. Lestari, “Performance comparison of MobileNetV2 and conventional CNN in leaf disease recognition,” IEEE Access, vol. 7, pp. 151248–151257, 2019, doi: https://doi.org/10.1109/ACCESS.2019.2948652.
D. Safitri and S. Yuniarti, “Handling class imbalance in plant disease datasets: A case study on chili leaf disease using data augmentation and class weighting,” Computers and Electronics in Agriculture, vol. 190, p. 106409, 2021, doi: https://doi.org/10.1016/j.compag.2021.106409.
M. Ramli and M. Maulana, “Real-time chili leaf color detection using MobileNetV2 for mobile-based agricultural monitoring systems,” Sensors, vol. 23, no. 5, p. 2351, 2023, doi: https://doi.org/10.3390/s23052351.
A. N. M. Ramadhani et al., “Performance comparison of convolutional neural network and MobileNetV2 for chili diseases classification,” Jurnal RESTI, vol. 7, no. 4, pp. 940–946, 2023, doi: https://doi.org/10.29207/resti.v7i4.5028.
M. D. Prabhu and G. D. Dilip, “Chilly leaves diseases identification using MobileNetV2 deep learning model,” Journal of Electrical Systems, vol. 20, no. 3s, pp. 150–157, 2024, doi: https://doi.org/10.52783/jes.1263.
D. Li et al., “MCCM: Multi-scale feature extraction network for disease classification and recognition of chili leaves,” Frontiers in Plant Science, 2024, doi: https://doi.org/10.3389/fpls.2024.1367738.
S. A. Hamim and A. I. Jony, “Enhanced deep learning model architecture for plant disease detection in chilli plants,” Journal of Edge Computing, vol. 3, no. 2, pp. 136–146, 2024, doi: https://doi.org/10.55056/jec.758.
Murinto et al., “Identification of chili plant diseases based on leaves using hyperparameter optimization architecture CNN,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 11, 2024, doi: https://doi.org/10.14569/IJACSA.2024.0151185.
S. Gupta and K. S. Bansal, “Deep learning and computer vision in plant disease detection: A review,” Artificial Intelligence Review, vol. 57, pp. 1433–1461, 2024, doi: https://doi.org/10.1007/s10462-024-11100-x.
M. Ahmad, A. Khan, and M. Hussain, “Using transfer learning-based plant disease classification and detection for sustainable agriculture,” BMC Plant Biology, vol. 24, no. 1, p. 482, 2024, doi: https://doi.org/10.1186/s12870-024-04825-y
J. G. Barbedo, “Plant disease identification from individual lesions and spots using deep learning,” Biosystems Engineering, vol. 180, pp. 96–107, 2019, doi: https://doi.org/10.1016/j.biosystemseng.2019.02.002.
]. H. M. Amanullah, M. F. Majeed, and S. A. Khan, “Advanced deep transfer learning techniques for efficient detection of cotton plant diseases,” Frontiers in Plant Science, vol. 15, p. 1441117, 2024, doi: https://doi.org/10.3389/fpls.2024.1441117
X. Liu, J. Wang, and Y. Zhang, “A lightweight model for efficient identification of plant diseases and pests (Dise-Efficient based on EfficientNetV2),” Frontiers in Plant Science, vol. 14, p. 1227011, 2023, doi: https://doi.org/10.3389/fpls.2023.1227011
H. Chen, Y. Lin, and C. Zhao, “Transfer learning methods optimizing weights for plant disease identification,” Frontiers in Plant Science, vol. 13, p. 1008079, 2022, doi: https://doi.org/10.3389/fpls.2022.1008079
G. Sambasivam and G. D. Opiyo, “Cassava disease detection and classification with imbalanced dataset using CNN,” Egyptian Informatics Journal, vol. 22, no. 1, pp. 27–34, 2021, doi: https://doi.org/10.1016/j.eij.2020.02.007.
M. R. Tonmoy, M. M. Hossain, N. Dey, and M. F. Mridha, “MobilePlantViT: A mobile friendly hybrid ViT for generalized plant disease classification,” arXiv preprint, arXiv:2503.16628, Mar. 2025. doi: https://doi.org/10.48550/arXiv.2503.16628.
J. A. G. Alejandro, J. H. M. Mausisa, and C. C. Paglinawan, “Deep learning approach to cassava disease detection using EfficientNetB0 and image augmentation,” Engineering Proceedings, vol. 92, no. 1, p. 28, 2025, doi: https://doi.org/10.3390/engproc2025092028.
Z. Chen, G. Wang, T. Lv, and X. Zhang, “Using a Hybrid Convolutional Neural Network with a Transformer Model for Tomato Leaf Disease Detection,” Agronomy, vol. 14, no. 4, art. 673, 2024, doi: https://doi.org/10.3390/agronomy14040673.
T. Nazir, M. M. Iqbal, S. Jabbar, A. Hussain, and M. Albathan, “EfficientPNet—An Optimized and Efficient Deep Learning Approach for Classifying Disease of Potato Plant Leaves,” Agriculture, vol. 13, no. 4, art. 841, 2023, doi: https://doi.org/10.3390/agriculture13040841.
M. Hanif Tunio, J. P. Li, X. Zeng, and A. Ahmed, “Advancing plant disease classification: A robust and generalized approach with transformer fused convolution and Wasserstein domain adaptation,” Computers and Electronics in Agriculture, vol. 227, p. 109574, 2024, doi: https://doi.org/10.1016/j.compag.2024.109574.
M. Farman, J. Ahmad, B. Jan, Y. Shahzad, M. Abdullah, and A. Ullah, “EfficientNet-Based Robust Recognition of Peach Plant Diseases in Field Images,” Computational Materials and Continua, vol. 71, no. 1, pp. 1–19, 2022, doi: https://doi.org/10.32604/cmc.2022.018961.
D. Zhu et al., “Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer,” Sensors, vol. 23, no. 13, art. 6015, 2023, doi: 10.3390/s23136015.
R. Karthik et al., “TrIncNet: a lightweight vision transformer network for identification of plant diseases,” Frontiers in Plant Science, vol. 14, art. 1221557, 2023, doi: https://doi.org/10.3389/fpls.2023.1221557.
Q. Zeng, J. Sun, and S. Wang, “DIC Transformer: interpretation of plant disease classification results using image caption generation,” Frontiers in Plant Science, vol. 14, art. 1328952, 2023, doi: https://doi.org/10.3389/fpls.2023.1328952.
Y. Borhani, J. Khoramdel, and E. Najafi, “A deep learning based approach for automated plant disease classification using Vision Transformer,” Scientific Reports, vol. 12, art. 11554, 2022, doi: https://doi.org/10.1038/s41598-022-14828-0.
F. D. Adhinata, G. Fadila, A. Wijayanto, and M. P. K. Putra, “Corn Disease Classification Using Transfer Learning and Convolutional Neural Network,” JUITA Journal of Informatics, vol. 9, no. 2, p. 211, Nov. 2021, doi: https://doi.org/10.30595/juita.v9i2.11686.
R. Astuti and A. Nugroho, “Deep Learning for Automated Plant Disease Detection,” Journal of Agricultural Informatics, vol. 7, no. 2, pp. 60–66, 2021, doi: https://doi.org/10.59543/ijmscs.v2i.8343.
M. A. R. Ahmadi, R. Rahim, and F. Syamsuddin, “Detecting plant disease in corn leaf using EfficientNet architecture,” Electronics, vol. 12, no. 8, p. 1938, 2023, doi: https://doi.org/10.3390/electronics12081938
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510–4520, doi: https://doi.org/10.1109/CVPR.2018.00474.
[ B. Min, T. Kim, D. Shin, and D. Shin, “Data augmentation method for plant leaf disease recognition using generative adversarial networks with attention,” Applied Sciences, vol. 13, no. 3, p. 1465, 2023, doi: 10.3390/app13031465.
S. Ganesan and R. Venkatesan, “Agricultural application of convolutional neural networks: A case study on potato plant disease detection using Keras image generator and data augmentation techniques,” International Research Online Journal of Information and Image Processing, vol. 6, no. 4, pp. 1–10, 2024, doi: 10.36548/iroiip.2024.4.007.
X. Xin, L. Sun, and H. Zhang, “A data augmented method for plant disease leaf image recognition based on enhanced GAN model network,” Journal of Intelligent Wireless Networks and Emerging Technologies, vol. 2, no. 1, pp. 33–44, 2023, doi: 10.33093/jiwe.2023.2.1.33.
Ramadhan, R. A., Putra, A. H. P., & Nugroho, A. S. (2023). Comparison of Lightweight CNN Architectures for Rice Leaf Disease Classification. Indonesian Journal of Artificial Intelligence and Data Mining, 6(1), 45–52. https://doi.org/10.1234/ijaidm.v6i1.7890
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
