ESRGAN-Enhanced YOLOv12 for Rice Leaf Disease Detection with Dataset Partitioning Analysis

Authors

  • Ahmad Fathir Muhammadiyah University of Makassar, Indonesia
  • Ida Mulyadi Muhammadiyah University of Makassar, Indonesia
  • Fahrim Irhamna Muhammadiyah University of Makassar, Indonesia
Pages Icon

DOI:

https://doi.org/10.63158/journalisi.v8i3.1648

Keywords:

Plant Disease Detection, Super-Resolution, Object Detection, Agricultural Computer Vision, ESRGAN, YOLOv12, Precision Agriculture

Abstract

Rice leaf diseases pose a significant threat to agricultural productivity, yet accurate automated detection remains challenging due to low image quality in field conditions. This study proposes the integration of ESRGAN-based super-resolution with YOLOv12 for rice leaf disease detection using a dataset of 6,204 annotated field images spanning five classes: bacterial leaf blight, brown spot, healthy leaves, hispa, and leaf blast. To prevent data leakage, all images were partitioned into training, validation, and testing subsets prior to augmentation; under the S3 scenario (75:10:15), the training set was expanded from 4,653 to 13,959 images through augmentation. ESRGAN RRDB 4× enhancement was applied exclusively to all test-set images, enabling a clean before-and-after comparison without contaminating training data. The primary finding is that ESRGAN produces a modest but consistent improvement in detection performance: mAP@0.5 increased from 0.949 to 0.955, and mAP@0.5:0.95 increased from 0.910 to 0.925. Per-class analysis shows the largest gains in visually challenging classes, particularly Leaf Blast (+0.073) and Hispa (+0.060). Additionally, four dataset partitioning scenarios (S1–S4) were trained and evaluated under identical settings; as a preliminary observation, the S3 configuration offered a balanced trade-off between training data availability and test-set reliability, though definitive conclusions require further validation through repeated experimental runs.

Downloads

Download data is not yet available.

References

[1] K. Fang, R. Zhou, N. Deng, C. Li, and X. Zhu, “RLDD-YOLOv11n: Research on Rice Leaf Disease Detection Based on YOLOv11,” Agronomy, vol. 15, no. 6, 2025, doi: 10.3390/agronomy15061266.

[2] A. B. Ayyappan, T. Gobinath, M. Kumar, and A. Sivaramakrishnan, “Rice Plant Disease Detection using Convolutional Neural Networks,” Discov. Artif. Intell., vol. 5, no. 1, 2025, doi: 10.1007/s44163-025-00277-x.

[3] P. Seelwal, P. Dhiman, Y. Gulzar, A. Kaur, S. Wadhwa, and C. W. Onn, “A systematic review of deep learning applications for rice disease diagnosis: current trends and future directions,” Front. Comput. Sci., vol. 6, 2024, doi: 10.3389/fcomp.2024.1452961.

[4] P. Pai et al., “Deep learning-based automatic diagnosis of rice leaf diseases using ensemble CNN models,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-13079-z.

[5] C. Pan, S. Wang, Y. Wang, and C. Liu, “SSD-YOLO: a lightweight network for rice leaf disease detection,” Front. Plant Sci., vol. 16, 2025, doi: 10.3389/fpls.2025.1643096.

[6] Y. Tian et al., “Development and evolution of YOLO in object detection: A survey,” Neurocomputing, vol. 669, 2026, doi: 10.1016/j.neucom.2025.132436.

[7] H. Deng, S. Zhang, X. Wang, T. Han, and Y. Ye, “USD-YOLO: An Enhanced YOLO Algorithm for Small Object Detection in Unmanned Systems Perception,” Appl. Sci., vol. 15, no. 7, 2025, doi: 10.3390/app15073795.

[8] M. Nikouei et al., “Small object detection: A comprehensive survey on challenges, techniques and real-world applications,” Intell. Syst. with Appl., vol. 27, 2025, doi: 10.1016/j.iswa.2025.200561.

[9] H. K. Kondaveeti and C. G. Simhadri, “Evaluation of deep learning models using explainable AI with qualitative and quantitative analysis for rice leaf disease detection,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-14306-3.

[10] M. Belmir, “Improved plant leaf disease detection architecture using unmanned aerial vehicle images and hybrid YOLOv11,” Egypt. Informatics J., vol. 34, no. November 2025, p. 100941, 2026, doi: 10.1016/j.eij.2026.100941.

[11] M. B. a B and bdelkader G. C, Wafa Difallah aAA, “Improved plant leaf disease detection architecture using unmanned aerial vehicle images and hybrid YOLOv11,” 2026, doi: https://doi.org/10.1016/j.eij.2026.100941.

[12] S. Malladi and P. Kulkarni, “Integrating Real-ESRGAN with CNN Models for UAV Image Based Plant Disease Detection,” Position Pap. 20th Conf. Comput. Sci. Intell. Syst., vol. 44, pp. 69–73, 2025, doi: 10.15439/2025f2775.

[13] K. K. *ORCID andDamian WierzbickiORCID, “Modified ESRGAN with Uformer for Video Satellite Imagery Super-Resolution,” MDPI, 2024, doi: https://www.mdpi.com/2072-4292/16/11/1926.

[14] A. Toosi, F. Samadzadegan, and F. D. Javan, “S3-ESRGAN: Enhanced Super-Resolution Generative Adversarial Network for Remote Sensing Imagery Spatial Resolution Improvement—An Application Using Sentinel-2 and UAV Images,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 19, pp. 2149–2172, 2026, doi: 10.1109/JSTARS.2025.3640940.

[15] L. Zha, Y. Shi, and J. Wen, “A Lightweight Image Super-Resolution Network Based on ESRGAN for Rapid Tomato Leaf Disease Classification,” Lect. Notes Electr. Eng., vol. 813, pp. 97–110, 2022, doi: 10.1007/978-981-16-6963-7_9.

[16] C. G. Simhadri, H. K. Kondaveeti, V. K. Vatsavayi, A. Mitra, and P. Ananthachari, “Deep learning for rice leaf disease detection: A systematic literature review on emerging trends, methodologies and techniques,” Inf. Process. Agric., vol. 12, no. 2, pp. 151–168, 2025, doi: 10.1016/j.inpa.2024.04.006.

[17] J. Peng, Y. Wang, P. Jiang, R. Zhang, and H. Chen, “RiceDRA-Net: Precise Identification of Rice Leaf Diseases with Complex Backgrounds Using a Res-Attention Mechanism,” Appl. Sci., vol. 13, no. 8, 2023, doi: 10.3390/app13084928.

[18] R. A. Ida Mulyadi1, Fahrim Irhamna2, Chyquitha Danuputri3, Ridwang4, “View of Enhancing YOLOv12-Based Rice Leaf Disease Detection through Evaluation of Three Data-Split Scenarios.pdf.” 2026.

Downloads

Published

2026-06-22

Issue

Vol. 8 No. 3 (2026): June

Section

Articles

License

Copyright (c) 2026 Journal of Information Systems and Informatics

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors Declaration

  1. The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
  2. The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
  3. The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
  4. The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
  5. The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
  6. The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
  7. If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
  8. The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights

Most read articles by the same author(s)