Rice Leaf Diseases Detection Using Dilated Convolutional Support Vector Machine Method with Test-Time Data Augmentation

Uswatun Khasanah; Erna Setiawati; Ahmad Isro'il

doi:10.31764/jtam.v10i4.41132

Rice Leaf Diseases Detection Using Dilated Convolutional Support Vector Machine Method with Test-Time Data Augmentation

Uswatun Khasanah, Erna Setiawati, Ahmad Isro'il

Abstract

In 2023, Indonesia’s rice production declined by approximately 0.23% compared to 2022. A primary cause of reduced crop productivity among Indonesian farmers is the delayed detection of rice leaf diseases. In the era of artificial intelligence, early detection of rice leaf diseases is crucial for improving harvest quality and controlling disease spread. Early detection can be achieved through image data analysis. While the Convolutional Neural Network (CNN) is a popular method for image processing, it can require significant computational resources. This study aims to enhance rice leaf disease detection performance by employing the Dilated CNN method with Support Vector Machine (SVM) and incorporating Test-Time Augmentation (TTA). The dataset used in this study was obtained from Kaggle and consists of 3,364 images distributed across four classes, namely Brown Spot with 532 images, Hispa with 565 images, Leaf Blast with 779 images, and Healthy with 1,488 images. The proposed detection model employs Dilated CNN for feature extraction, SVM for classification, and TTA to improve model robustness to image variations during inference. The evaluation results show that the Dilated CNN-SVM model with randomized TTA achieved an average accuracy of 83.55% ± 0.24% across five independent runs. These results demonstrate the effectiveness of the proposed approach in detecting rice leaf diseases from image data. Furthermore, the findings indicate that incorporating TTA improves the performance of the proposed detection system.

Keywords

Rice Leaf Disease; Detection; Dilated Convolutional Support Vector Machine Method; Test Time Augmentation.

Full Text:

DOWNLOAD [PDF]

References

Aggarwal, S., Suchithra, M., Chandramouli, N., Sarada, M., Verma, A., Vetrithangam, D., Pant, B., & Adugna, B. A. (2022). Rice Disease Detection Using Artificial Intelligence and Machine Learning Techniques to Improvise Agro-Business. Hindawi Scientific Programming, 2022(1), 1–13. https://doi.org/https://doi.org/10.1155/2022/1757888

Ahad, T., Li, Y., Song, B., & Bhuiyan, T. (2023). Comparison of CNN-Based Deep Learning Architectures for Rice Diseases Classification. Artificial Intelligence in Agriculture, 9, 22–35. https://doi.org/10.1016/j.aiia.2023.07.001

Bhujel, S., & Shakya, S. (2022). Rice Leaf Diseases Classification Using Discriminative Fine Tuning and CLR on EfficientNet. Journal of Soft Computing Paradigm, 4(3), 172–187. https://doi.org/10.36548/jscp.2022.3.006

Fitriani, I., Devi, R., Fokker, A., Sajjana, C., & Irfan, M. (2026). Classification of Corn Leaf Disease Images Using Convolutional Neural Network Algorithm. 3(2), 113–125. https://doi.org/10.57152/predatecs.v3i2.2105

Fu’adah, Y. N., Pratiwi, N. C., Pramudito, M. A., & Ibrahim, N. (2020). Convolutional Neural Network (CNN) for Automatic Skin Cancer Classification System. IOP Conference Series: Materials Science and Engineering, 982(1). https://doi.org/10.1088/1757-899X/982/1/012005

Gamage, A., Gangahagedara, R., Subasinghe, S., & Gamage, J. (2024). Advancing Sustainability : The Impact of Emerging Technologies in Agriculture. Current Plant Biology, 40(November), 1–16. https://doi.org/10.1016/j.cpb.2024.100420

Gnanamalar, A. J., Bhavani, R., Arulini, A. S., & Veerraju, M. S. (2023). CNN–SVM Based Fault Detection, Classification and Location of Multi-terminal VSC–HVDC System. Journal of Electrical Engineering and Technology, 18(4), 3335–3347. https://doi.org/10.1007/s42835-023-01391-5

Hamel, L. (2009). Knowledge Discovery with Support Vector Machines (Wiley Series on Methods and Applications in Data Mining). https://doi.org/https://doi.org/10.1002/9780470503065.ch7

Han, T., Zhang, L., Yin, Z., & Tan, A. C. (2021). Rolling bearing fault diagnosis with combined convolutional neural networks and support vector machine. Measurement, 177, 109022. https://doi.org/10.1016/j.measurement.2021.109022

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-Decem, 770–778. https://doi.org/10.1109/CVPR.2016.90

Hiywotu, A. M. (2025). Advancing Sustainable Agriculture for Goal 2: Zero Hunger - A Comprehensive Overview of Practices, Policies, and Technologies. Agroecology and Sustainable Food Systems, 49(7), 1027–1055. https://doi.org/10.1080/21683565.2025.2451344

Indolia, S., Goswami, A. K., Mishra, S. P., & Asopa, P. (2018). Conceptual Understanding of Convolutional Neural Network- A Deep Learning Approach. Procedia Computer Science (ICCIDS), 132, 679–688. https://doi.org/10.1016/j.procs.2018.05.069

Ioffe, S., & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. http://arxiv.org/abs/1502.03167

Khasanah, U., Surarso, B., & Farikhin. (2023). Dilated Convolutional Neural Network for Skin Cancer Classification Based on Image Data. JTAM (Jurnal Teori Dan Aplikasi Matematika), 7(1), 196–207. https://doi.org/10.31764/jtam.v7i1.11667

Krishna, M. M., Neelima, M., Harshali, M., & Rao, M. V. G. (2018). Image Classification Using Deep Learning. International Journal of Engineering and Technology(UAE), 7(March), 614–617. https://doi.org/10.14419/ijet.v7i2.7.10892

Kulkarni, P., & Shastri, S. (2024). Rice Leaf Diseases Detection Using Machine Learning. Journal of Scientific Research and Technology, 1(10), 17–22. https://doi.org/https://doi.org/10.61808/jsrt81

Lei, X., Pan, H., & Huang, X. (2019). A Dilated CNN Model for Image Classification. IEEE Access, 7, 124087–124095. https://doi.org/10.1109/ACCESS.2019.2927169

Li, X., Zhai, M., & Sun, J. (2021). DDCNNC: Dilated and Depthwise Separable Convolutional Neural Network for Diagnosis COVID-19 Via Chest X-ray Images. International Journal of Cognitive Computing in Engineering, 2(March), 71–82. https://doi.org/10.1016/j.ijcce.2021.04.001

Paula, B., & Pribadi, M. R. (2026). Rice Leaf Disease Classification Using ResNet-50: A Comparative Study of Adam, SGD, and RMSProp. Brilliance: Research of Artificial Intelligence, 6(1), 11–20. https://doi.org/10.47709/brilliance.v6i1.7582

Perry, R., Panigrahi, S., Bien, J., & Witten, D. (2026). Inference on the proportion of variance explained in principal component analysis. Journal of the American Statistical Association, 121(553), 667-677. https://doi.org/10.1080/01621459.2025.2538895

Pradana, A. I., & Pamekas, B. W. (2025). Optimalisasi Akurasi Model Identifikasi Penyakit Pada Daun Padi Dengan Fine-Tuning YOLOv11 Untuk Ketahanan Pangan Berkelanjutan. Jurnal Algoritma, 22(2), 782–792. https://doi.org/10.33364/algoritma/v.22-2.2945

Pratt, H., Coenen, F., Broadbent, D. M., Harding, S. P., & Zheng, Y. (2016). Convolutional Neural Networks for Diabetic Retinopathy. Procedia Computer Science, 90(July), 200–205. https://doi.org/10.1016/j.procs.2016.07.014

Putra, R. E., Tjandrasa, H., & Suciati, N. (2020). Severity Classification of Non-Proliferative Diabetic Retinopathy using Convolutional Support Vector Machine. International Journal of Intelligent Engineering and Systems, 13(4), 156–170. https://doi.org/10.22266/IJIES2020.0831.14

Ragab, D. A., Sharkas, M., Marshall, S., & Ren, J. (2019). Breast cancer detection using deep convolutional neural networks and support vector machines. PeerJ, 2019(1), 1–23. https://doi.org/10.7717/peerj.6201

Rana, M. E., Hameed, V. A., Eng, I. K. Y., Tripathy, H. K., & Mallik, S. (2025). Harnessing artificial intelligence for sustainable rice leaf disease classification. Frontiers in Plant Science, 16, 1594329. https://doi.org/10.3389/fpls.2025.1594329

Rijal, M., Yani, A. M., & Rahman, A. (2024). Deteksi Citra Daun untuk Klasifikasi Penyakit Padi Menggunakan Pendekatan Deep Learning dengan Model CNN. Jurnal Teknologi Terpadu, 10(1), 56–62. https://doi.org/https://doi.org/10.54914/jtt.v10i1.1224

Rizkyansyah, M. D., & Susilawati, I. (2024). Sistem Pakar Diagnosa Penyakit Pada Tanaman Padi ( Oryza ) Menggunakan Metode Naïve Bayes Expert System For Diagnosing Diseases In Rice Plants ( Oryza ) Using The Naïve Bayes Method. JIKOM: Jurnal Informatika Dan Komputer, 14(2), 168–181. https://doi.org/https://doi.org/10.55794/jikom.v14i2.206

Uvdal, P., & Mirkhalaf, M. (2025). Test-time data augmentation: Improving predictions of recurrent neural network models of composites. Engineering Applications of Artificial Intelligence, 160, 111983. http://arxiv.org/abs/2409.02478

Venkata Sai Abhishek, A., Rao Gurrala, V., Sahoo, L., Scholar, R., & Professor, S. (2022). Resnet18 model with sequential layer for computing accuracy on image classification dataset. Int. J. Creat. Res. Thoughts, 10(5), 176-181. https://api.semanticscholar.org/CorpusID:249060401

Wang, X., Lu, Y., Wang, Y., & Chen, W. B. (2018). Diabetic retinopathy stage classification using convolutional neural networks. Proceedings - 2018 IEEE 19th International Conference on Information Reuse and Integration for Data Science, IRI 2018, 465–471. https://doi.org/10.1109/IRI.2018.00074

Wardani, G. T. (2024). Potensi Gen Z dalam Pengembangan Teknologi Berbasis Sistem Pertanian Presisi Guna Meningkatkan Produktivitas Pertanian di Indonesia. Flora: Jurnal Kajian Ilmu Pertanian dan Perkebunan, 1(2), 22-31. https://doi.org/https://doi.org/10.62951/flora.v1i2.52

Zheng, J., Cheung, K., Sit, P., & Lam, C. (2025). Unfolding key factors of resilience in ICT cognitive-motivational engagement: Global evidence from machine learning techniques. International Journal of Educational Research, 131, 102607. https://doi.org/10.1016/j.ijer.2025.102607

DOI: https://doi.org/10.31764/jtam.v10i4.41132