Enhanced U-Net Cnn For Multi-Class Segmentation And Classification Of Rice Leaf Diseases In Indonesian Rice Fields

Faturrohman Faturrohman; Odi Nurdiawan; Willy Prihartono; Rully  Herdiana

doi:10.52436/1.jutif.2025.6.5.5258

Authors

Faturrohman Software Engineering, STMIK IKMI Cirebon, Indonesia
Odi Nurdiawan Informatics Management, STMIK IKMI Cirebon, Indonesia
Willy Prihartono Computerized accounting, STMIK IKMI Cirebon, Indonesia
Rully Herdiana Informatics Engineering, STMIK IKMI Cirebon, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2025.6.5.5258

Keywords:

CNN, Image Segmentation, Multi-class Classification, Rice, U-Net

Abstract

Rice is a strategic food crop whose productivity is often threatened by leaf diseases and pests. This study aims to develop an Enhanced U-Net CNN model for multi-class segmentation and classification of rice leaf conditions from field images to support early detection and plant health management. The methodology includes direct field image acquisition of rice leaves, preprocessing for image quality enhancement, expert data labeling, segmentation using a U-Net architecture, and classification using CNN. The dataset was divided into training and testing data with balanced distribution across four classes: Healthy, BrownSpot, Hispa, and LeafBlast. Evaluation results show that the model can identify rice leaf conditions with high accuracy, although signs of overfitting were observed from the performance gap between training and validation data. The implementation of this model is expected to accelerate automatic disease detection in the field, reduce reliance on manual inspection, and support precision agriculture. This study achieved a testing accuracy of 76.36% with a macro-average F1-score of 0.34. While the results indicate limitations in generalization, the proposed Enhanced U-Net CNN demonstrates the feasibility of combining segmentation and classification in field conditions. This research contributes to agricultural informatics by supporting scalable deployment in precision agriculture systems, reducing reliance on manual inspection, and providing a foundation for further optimization studies.

Downloads

Download data is not yet available.

References

S. Deepa, J. Vijayanand, K. Danesh, M. Gomathi, and K. Subramani, “Implementation of Deep CNN Model for the Detection of Plant Leaf Disease,” International Journal on Recent and Innovation Trends in Computing and Communication, vol. 11, pp. 463–470, 2023, doi: 10.17762/ijritcc.v11i9s.7457.

S. M. Hugar and M. A. Waheed, “Using CNN to Identify NPK Deficiencies in Paddy Fields: An Advanced Detection Method,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 2, pp. 665–673, 2024, [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85185961704&partnerID=40&md5=d54ef1a1bb00ee4fede8c5afb2ba0f81

A. K. Dixit and R. Verma, “Advanced Hybrid Model for Multi Paddy diseases detection using Deep Learning,” EAI Endorsed Trans Pervasive Health Technol, vol. 9, no. 1, 2023, doi: 10.4108/eetpht.9.4481.

G. Parasa, M. Arulselvi, and S. Razia, “Identification of Diseases in Paddy Crops Using CNN,” International Journal of Intelligent Systems and Applications in Engineering, vol. 11, no. 6s, pp. 548–557, 2023, [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85168002982&partnerID=40&md5=fd4368405e41d49cb9f690f8472887da

M.-W. Li, Y.-K. Chan, and S.-S. Yu, “Use of CNN for Water Stress Identification in Rice Fields Using Thermal Imagery,” Applied Sciences (Switzerland), vol. 13, no. 9, 2023, doi: 10.3390/app13095423.

A. Chakrabarty, S. T. Ahmed, M. F. U. Islam, S. M. Aziz, and S. S. Maidin, “An interpretable fusion model integrating lightweight CNN and transformer architectures for rice leaf disease identification,” Ecol Inform, vol. 82, 2024, doi: 10.1016/j.ecoinf.2024.102718.

F. A. Shah et al., “Towards Intelligent Detection and Classification of Rice Plant Diseases Based on Leaf Image Dataset,” Computer Systems Science and Engineering, vol. 47, no. 2, pp. 1385–1413, 2023, doi: 10.32604/csse.2023.036144.

N. Soren and P. S. Selvi Rajendran, “Artificial Intelligence Based-Oryza Sativa Leaf Ailment Recognition using DCT with Deep NN,” International Journal of Intelligent Systems and Applications in Engineering, vol. 11, no. 4s, pp. 242–253, 2023, [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85161366278&partnerID=40&md5=4f007115e971b71b07a1c1d557134a30

A. Stephen, A. Punitha, and A. Chandra Sekar, “Designing self attention-based ResNet architecture for rice leaf disease classification,” Neural Comput Appl, vol. 35, no. 9, pp. 6737–6751, 2023, doi: 10.1007/s00521-022-07793-2.

M. T. Ahad, Y. Li, B. Song, and T. Bhuiyan, “Comparison of CNN-based deep learning architectures for rice diseases classification,” Artificial Intelligence in Agriculture, vol. 9, pp. 22–35, 2023, doi: 10.1016/j.aiia.2023.07.001.

G. Parasa, M. Arulselvi, and S. Razia, “An Enhanced CNN-based ELM Classification for Disease Prediction in the Rice Crop,” International Journal on Recent and Innovation Trends in Computing and Communication, vol. 11, no. 7, pp. 737–744, 2023, doi: 10.17762/ijritcc.v11i7s.7556.

S. Tyagi, S. R. N. Reddy, R. Anand, and A. Sabharwal, “Enhancing rice crop health: a light weighted CNN-based disease detection system with mobile application integration,” Multimed Tools Appl, vol. 83, no. 16, pp. 48799–48829, 2024, doi: 10.1007/s11042-023-17449-5.

W. G. Pamungkas, M. I. P. Wardhana, Z. Sari, and Y. Azhar, “Leaf Image Identification: CNN with EfficientNet-B0 and ResNet-50 Used to Classified Corn Disease,” Jurnal RESTI, vol. 7, no. 2, pp. 326–333, 2023, doi: 10.29207/resti.v7i2.4736.

S. Lamba, V. Kukreja, A. Baliyan, S. Rani, and S. H. Ahmed, “A Novel Hybrid Severity Prediction Model for Blast Paddy Disease Using Machine Learning,” Sustainability (Switzerland), vol. 15, no. 2, 2023, doi: 10.3390/su15021502.

P. S. Thakur, T. Sheorey, and A. Ojha, “VGG-ICNN: A Lightweight CNN model for crop disease identification,” Multimed Tools Appl, vol. 82, no. 1, pp. 497–520, 2023, doi: 10.1007/s11042-022-13144-z.

C. Zhang, R. Ni, Y. Mu, Y. Sun, and T. L. Tyasi, “Lightweight Multi-scale Convolutional Neural Network for Rice Leaf Disease Recognition,” Computers, Materials and Continua, vol. 74, no. 1, pp. 983–994, 2023, doi: 10.32604/cmc.2023.027269.

S. Sakhamuri and K. K. Kumar, “Optimal Training Ensemble of Classifiers for Classification of Rice Leaf Disease,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 3, pp. 94–105, 2023, doi: 10.14569/IJACSA.2023.0140311.

D. Singh and A. Kumar, “A Deep Recurrent Neural Network for Plant Disease Classification,” SN Comput Sci, vol. 5, no. 8, 2024, doi: 10.1007/s42979-024-03400-4.

P. Kulkarni and S. Shastri, “Rice Leaf Diseases Detection Using Machine Learning,” JSRT, pp. 17–22, 2024, doi: 10.61808/jsrt81.

N. Anggraini, “Classification of Rice Plant Disease Image Using Convolutional Neural Network (CNN) Algorithm Based on Amazon Web Service (AWS),” Building of Informatics Technology and Science (Bits), vol. 6, no. 3, pp. 1293–1300, 2024, doi: 10.47065/bits.v6i3.5883.

M. Dutta et al., “Rice Leaf Disease Classification—A Comparative Approach Using Convolutional Neural Network (CNN), Cascading Autoencoder With Attention Residual U-Net (CAAR-U-Net), and MobileNet-V2 Architectures,” Technologies (Basel), vol. 12, no. 11, p. 214, 2024, doi: 10.3390/technologies12110214.

D. J. Chaudhari and K. Malathi, “Detection and Prediction of Rice Leaf Disease Using a Hybrid CNN-SVM Model,” Optical Memory and Neural Networks (Information Optics), vol. 32, no. 1, pp. 39–57, 2023, doi: 10.3103/S1060992X2301006X.

Y. Lu, P. Liu, S. Xu, Q. Liu, F. Gu, and P. Wang, “Simulation of Rice Disease Recognition Based on Improved Attention Mechanism Embedded in PR-Net Model,” Xitong Fangzhen Xuebao / Journal of System Simulation, vol. 36, no. 6, pp. 1322–1333, 2024, doi: 10.16182/j.issn1004731x.joss.23-0322.

R. Poorni, P. Kalaiselvan, N. A. Thomas, and T. Srinivasan, “Detection of Rice Leaf Diseases Using Convolutional Neural Network,” ECS Trans, vol. 107, no. 1, pp. 5069–5080, 2022, doi: 10.1149/10701.5069ecst.

M. H. Bijoy et al., “Towards Sustainable Agriculture: A Novel Approach for Rice Leaf Disease Detection Using dCNN and Enhanced Dataset,” Ieee Access, vol. 12, pp. 34174–34191, 2024, doi: 10.1109/access.2024.3371511.

Md. M. Hasan et al., “Enhancing Rice Crop Management: Disease Classification Using Convolutional Neural Networks and Mobile Application Integration,” Agriculture, vol. 13, no. 8, p. 1549, 2023, doi: 10.3390/agriculture13081549.

S. Prathima, N. G. Praveena, K. Kasiviswanathan, S. S. Nath, and B. Sarala, “Generic Paddy Plant Disease Detector (GP2D2): An Application of the Deep-CNN Model,” International Journal of Electrical and Computer Engineering Systems, vol. 14, no. 6, pp. 647–656, 2023, doi: 10.32985/IJECES.14.6.4.

U. Bhimavarapu, “Prediction and classification of rice leaves using the improved PSO clustering and improved CNN,” Multimed Tools Appl, vol. 82, no. 14, pp. 21701–21714, 2023, doi: 10.1007/s11042-023-14631-7.

O. Oktay et al., “Attention U-Net: Learning Where to Look for the Pancreas,” 2018, doi: 10.48550/arxiv.1804.03999.

B. Sarıtürk and D. Z. Şeker, “A Residual-Inception U-Net (RIU-Net) Approach and Comparisons With U-Shaped CNN and Transformer Models for Building Segmentation From High-Resolution Satellite Images,” Sensors, vol. 22, no. 19, p. 7624, 2022, doi: 10.3390/s22197624.