Comparison of VGG16 and ResNet50 Performance in Rice Leaf Disease Classification

Valda Laura Uswary; Amriana Amriana

doi:10.30871/jaic.v10i4.13628

Authors

Valda Laura Uswary Universitas Tadulako
Amriana Amriana Universitas Tadulako

DOI:

https://doi.org/10.30871/jaic.v10i4.13628

Keywords:

Convolutional Neural Network, Image Classification, ResNet50, Rice Leaf Disease, Transfer Learning, VGG16

Abstract

Paddy (Oryza sativa L.) is a strategic staple food commodity in Indonesia, yet its production is frequently disrupted by various plant diseases that cause significant yield losses each year. Conventional visual disease identification is inefficient and prone to error, necessitating the adoption of more reliable, automated diagnostic technology. This study compares the performance of two pre-trained convolutional neural network architectures, VGG16 and ResNet50, in classifying rice leaf images into four categories: Brown Spot, Leaf Blast, Healthy Rice Leaf, and Rice Hispa. Both models were fine-tuned using transfer learning under an identical experimental configuration, including the same data split, optimizer, learning-rate schedule, and augmentation pipeline, to ensure a controlled architectural comparison. Model evaluation was conducted using accuracy, precision, recall, F1-score, the Matthews Correlation Coefficient (MCC), confusion matrix analysis, training convergence behaviour, inference-time computational efficiency, and Grad-CAM interpretability visualization. Experimental results show that ResNet50 achieved a test accuracy of 99% and an MCC of 0.9874, outperforming VGG16, which achieved a test accuracy of 95% and an MCC of 0.9306. Confusion matrix analysis revealed that ResNet50's errors were concentrated almost exclusively within the visually similar brown spot–leaf blast class pair, whereas VGG16 exhibited additional confusion between the healthy rice leaf and rice hispa classes. ResNet50 also demonstrated faster and more stable training convergence, more spatially coherent Grad-CAM activation patterns, and substantially higher throughput under batched inference (356.27 vs. 207.63 images/second at batch size 32), while VGG16 retained a marginal latency advantage under single-image inference. These findings indicate that, under the configuration examined in this study, ResNet50 is the more suitable architecture for rice leaf disease classification, offering an advantageous combination of accuracy, interpretability, and computational efficiency for potential deployment in agricultural monitoring systems.

Downloads

Download data is not yet available.

References

[1] P. Sitompul, H. Okprana, A. Prasetio, and G. Artikel, “Identifikasi Penyakit Tanaman Padi Melalui Citra Daun Menggunakan DenseNet 201,” JOMLAI: Journal of Machine Learning and Artificial Intelligence, vol. 1, no. 2, pp. 2828–9099, Sept. 2022.

[2] K. H. F. Ningrum. (2025) Mengenal Penyakit Penting pada Tanaman Padi on Mtanigroup. [Online]. Tersedia: https://mtanigroup.com/2025/03/11/mengenal-penyakit-penting-pada-tanaman-padi/.

[3] R. Suciani, D. A. Anugra, E. Faisal, and D. Nuswantoro, “Deteksi Penyakit Daun Padi Menggunakan Deep Learning Dengan Arsitektur CNN,” Journal of Information Technology and Computer Science (INTECOMS), vol. 8, no. 5, Sept. 2025.

[4] K. Hu, X. Zheng, X. Su, L. Wu, Y. Liu, and Z. Deng, “Identification of rice leaf disease based on DepMulti-Net,” Front. Plant Sci., vol. 16, no. 1522487, Mar. 2025

[5] M. Nawaz, I. Ahmed, S. Ali, and W. Khan, “Multi-model machine learning for automated identification of rice diseases using leaf image data,” PLOS ONE, vol. 19, no. 9, p. e0307461, Sept. 2025.

[6] S. N. Yousafzai, F. N. Al-Wesabi, H. Alsolai, S. A. Ebad, I. M. Nasir, E. Fadhal, and A. Thaljaoui, “Advanced clustering and transfer learning based approach for rice leaf disease segmentation and classification,” PeerJ. Computer science, vol 11, e3018, Jul. 2025.

[7] M. Fahmi, R. Rahim, A. Basri, and S. Samsul, “Penerapan Convolution Neural Network (CNN) Untuk Megalitikum Di Sulawesi Tengah Berbasis Mobile”, Jurnal Ilmiah Penelitian dan Pembelajaran Informatika (JIPI), vol. 10, no 3, pp. 2525-2536, Aug. 2025.

[8] N. A. Afiah, S. Syahrullah, R. Ardiansyah, R. Laila, and R. Pohontu, “Application Of Vgg16 Architecture In Wood Type Classification Using Convolutional Neural Network”, J. Tek. Inform. (JUTIF), vol. 6, no. 1, pp. 335–344, Feb. 2025.

[9] A. Asriani, N. T. Lapatta, D. W. Nugraha, A. Amriana, and W. Wirdayanti, “Implementation of ResNet-50-Based Convolutional Neural Network For Mobile Skin Cancer Classification”, JAIC, vol. 9, no. 4, pp. 1969–1577, Aug. 2025.

[10] I. Pacal, I. Kunduracioglu, M. H. Alma, M. Deveci, S. Kadry, J. Nedoma, V. Slany, and R. Martinek, "A systematic review of deep learning techniques for plant diseases," Artif. Intell. Rev., vol. 57, no. 11, art. 304, Sept. 2024.

[11] A. Upadhyay, N. S. Chandel, K. P. Singh, S. K. Chakraborty, B. M. Nandede, M. Kumar, A. Subeesh, K. Upendar, A. Salem, and A. Elbeltagi, "Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture," Artif. Intell. Rev., vol. 58, no. 3, art. 92, Jan. 2025.

[12] M. Tan and Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proc. 36th Int. Conf. Machine Learning (ICML), Long Beach, CA, USA, 2019, pp. 6105–6114.

[13] Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, "A ConvNet for the 2020s," in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 2022, pp. 11976–11986.

[14] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale," in Proc. 9th Int. Conf. Learning Representations (ICLR), Virtual Event, Austria, 2021.

[15] H. M. Yusuf, A. F. D. Kana, and S. A. Yusuf, "Enhanced rice disease classification through pre-trained densenet model using transfer learning," Franklin Open, vol. 13, Okt. 2025.

[16] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, "Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization," Int. J. Comput. Vis., vol. 128, no. 2, pp. 336–359, 2020.

[17] S. Suara, A. Jha, P. Sinha, and A. A. Sekh, "Is Grad-CAM Explainable in Medical Images?," in Computer Vision and Image Processing (CVIP 2023), Communications in Computer and Information Science, vol. 2009, Springer, Cham, 2024, pp. 124–135.

[18] S. Tehsin, I. M. Nasir, and R. Damaševičius, "Explainability of Disease Classification from Medical Images Using XGrad-CAM," Communications in Computer and Information Science, vol. 2348, pp. 221–236, 2025.

[19] A. M. Fayyaz, S. J. Abdulkadir, N. Talpur, and S. M. Al-Selwi, "Grad-CAM (Gradient-weighted Class Activation Mapping): A Systematic Literature Review," Comput. Biol. Med., vol. 198, part B, art. no. 111200, 2025.