A Lightweight Classical Machine Learning Pipeline for Rice NPK Deficiency Classification Using Hand-Crafted Feature Fusion
DOI:
https://doi.org/10.63158/journalisi.v8i2.1486Keywords:
classical machine learning, hand-crafted features, feature fusion, NPK deficiency classification, rice leafAbstract
Many high-accuracy deep learning solutions for plant nutrient deficiency remain impractical in resource-limited settings due to computational cost and limited explainability. This study proposes a lightweight classical machine learning pipeline for rice leaf NPK (nitrogen, phosphorus, potassium) deficiency classification on the publicly available Kaggle Nutrient-Deficiency-Symptoms-in-Rice dataset (1,156 images); all results should be interpreted in this dataset context rather than as field-validated performance. The pipeline applies HSV-based leaf segmentation to reduce background influence. It extracts a 126-dimensional feature set combining masked color moments, HSV histograms, vegetation indices, LBP and GLCM texture descriptors, and spatial symptom ratios. Hyperparameters are tuned via RandomizedSearchCV with 5-fold StratifiedKFold and macro-F1 scoring; final evaluation uses a held-out 80/20 stratified test set kept separate throughout tuning. XGBoost achieves the best test performance (accuracy 0.9267; macro-F1 0.9233), followed by SVM-RBF (0.9224; 0.9187) and Random Forest. Feature importance analysis confirms that color moments dominate class separability, with texture and spatial features providing complementary support. The dominant remaining error is phosphorus–potassium confusion. The novelty lies in integrating leaf-focused preprocessing with a structured, low-cost feature representation suitable for mobile or edge deployment.
Downloads
References
[1] X. Liao and H. Yang, “Diagnosis of early nitrogen, phosphorus and potassium deficiency categories in rice based on multimodal integration and knowledge distillation,” Sci. Rep., vol. 15, no. 1, p. 13014, Apr. 2025, doi: 10.1038/s41598-025-97585-0.
[2] M. S. H. Talukder and A. K. Sarkar, “Nutrients deficiency diagnosis of rice crop by weighted average ensemble learning,” Smart Agric. Technol., vol. 4, no. 100155, 2023, doi: 10.1016/j.atech.2022.100155.
[3] L. Chen et al., “Identification of nitrogen, phosphorus, and potassium deficiencies in rice based on static scanning technology and hierarchical identification method,” PLoS One, vol. 9, no. 11, pp. 1–17, 2014, doi: 10.1371/journal.pone.0113200.
[4] A. Y. Reddy and T. R. Balaga, “Enhancing Precision Agriculture Based on Explainable AI for Automated Nutrient Deficiency Diagnosis in Rice Using Attention SqueezeNet,” Ing. des Syst. d’Information, vol. 30, no. 1, pp. 181–190, 2025, doi: 10.18280/isi.300115.
[5] M. Sobhana, V. R. Sindhuja, V. Tejaswi, and Durgesh, “Deep Ensemble Mobile Application for Recommendation of Fertilizer Based on Nutrient Deficiency in Rice Plants Using Transfer Learning Models,” Int. J. Interact. Mob. Technol., vol. 16, no. 16, pp. 100–112, 2022, doi: 10.3991/ijim.v16i16.31497.
[6] N. Ahmad, H. M. S. Asif, G. Saleem, M. U. Younus, S. Anwar, and M. R. Anjum, “Leaf Image-Based Plant Disease Identification Using Color and Texture Features,” Wirel. Pers. Commun., vol. 121, no. 2, pp. 1139–1168, 2021, doi: 10.1007/s11277-021-09054-2.
[7] J. Mkhatshwa, T. Kavu, and O. Daramola, “Analysing the Performance and Interpretability of CNN-Based Architectures for Plant Nutrient Deficiency Identification,” Computation, vol. 12, no. 6, 2024, doi: 10.3390/computation12060113.
[8] M. J. Sulastri, D. R. Sulistyaningrum, and H. Nurhadi, “Detection of Nutrient Deficiency in Rice Plants Based on Leaf Image,” 2021 Int. Conf. Adv. Mechatronics, Intell. Manuf. Ind. Autom. ICAMIMIA 2021 - Proceeding, pp. 143–148, 2021, doi: 10.1109/ICAMIMIA54022.2021.9807811.
[9] S. Supreetha, R. Premalathamma, and M. S. H., “Deep learning techniques to detect nutrient deficiency in rice plants,” in Proc. Int. Conf. Inventive Comput. Technol. (ICICT), Apr. 2024, pp. 699–705.
[10] B. Naresh Kumar and S. Sakthivel, “Rice leaf disease classification using a fusion vision approach,” Sci. Rep., vol. 15, no. 1, p. 8692, Mar. 2025, doi: 10.1038/s41598-025-87800-3.
[11] N. Islam and P. Richhariya, “Deep Learning-Based Classification of Rice Leaf Diseases Using Hybrid Ensemble Models,” Int. J. Innov. Sci. Eng. Manag., pp. 34–41, Dec. 2024, doi: 10.69968/ijisem.2024v3i434-41.
[12] A. Purnama, E. Fauzi, and B. A. Prasetyo, “Implementing PSO-based Image Segmentation for Detecting Sweet Potato Leaf Disease,” Int. J. Multidiscip. Approach Res. Sci., vol. 3, no. 02, pp. 447–457, 2025, doi: 10.59653/ijmars.v3i02.1482.
[13] B. S. Riza, R. Rosnelly, and V. H. S. Edy, “Application of Digital Image Processing for Orchid Image Segmentation in Morphological Plant Analysis,” J. Appl. Sci. Eng. Technol. Educ., vol. 7, no. 1, pp. 94–101, 2025, doi: 10.35877/454RI.asci3772.
[14] C. Fang, X. Wang, and Q. Wang, “Adaptive morphology structural element construction algorithm based on local pixel density and symmetry,” Multimed. Tools Appl., vol. 82, no. 1, pp. 195–215, 2023, doi: 10.1007/s11042-022-13259-3.
[15] J. Yan, K. Liang, C. Liu, and M. Gao, “Citrus recognition in orchard scene based on modified HSV-morphology method,” Appl. Comput. Eng., vol. 88, no. 1, pp. 69–76, 2024, doi: 10.54254/2755-2721/88/20241637.
[16] T. Xu, L. Yao, L. Xu, Q. Chen, and Z. Yang, “Image Segmentation of Cucumber Seedlings Based on Genetic Algorithm,” Sustainability, vol. 15, no. 4, 2023, doi: 10.3390/su15043089.
[17] M. A. Hutchison and C. M. Koepferl, “Contour Analysis Tool: An Interactive Tool for Background and Morphology Analysis,” Astrophys. J., vol. 975, no. 1, p. 27, 2024, doi: 10.3847/1538-4357/ad779f.
[18] S. Zhiwei et al., “Image-based Pretreatment Study of Rice Blast Disease,” J. Adv. Appl. Sci. Res., vol. 6, no. 3, pp. 1–15, 2024, doi: 10.46947/joaasr632024945.
[19] H. Rezvan, M. J. Valadan Zoej, F. Youssefi, and E. Ghaderpour, “Automated Rice Seedling Segmentation and Unsupervised Health Assessment Using Segment Anything Model with Multi-Modal Feature Analysis,” Sensors, vol. 25, no. 17, 2025, doi: 10.3390/s25175546.
[20] M. Keskar and D. D. Maktedar, “Hybrid deep-spatio textural feature model for medicinal plant disease classification,” Indones. J. Electr. Eng. Comput. Sci., vol. 30, no. 1, pp. 356–365, 2023, doi: 10.11591/ijeecs.v30.i1.pp356-365.
[21] M. J. Hoque, M. S. Islam, and M. Khaliluzzaman, “AI‐Powered Precision in Diagnosing Tomato Leaf Diseases,” Complexity, vol. 2025, no. 1, Jan. 2025, doi: 10.1155/cplx/7838841.
[22] R. S. Krishnan and E. G. Julie, “Computer aided detection of leaf disease in agriculture using convolution neural network based squeeze and excitation network,” Automatika, vol. 64, no. 4, pp. 1038–1053, 2023, doi: 10.1080/00051144.2023.2241792.
[23] B. Luna‐Benoso, J. C. Martínez‐Perales, J. Cortés‐Galicia, R. Flores‐Carapia, and V. M. Silva‐García, “Detection of diseases in tomato leaves by color analysis,” Electron., vol. 10, no. 9, pp. 1–16, 2021, doi: 10.3390/electronics10091055.
[24] N. S. B. Mat Said, H. Madzin, S. K. Ali, and N. S. Beng, “Comparison of color-based feature extraction methods in banana leaf diseases classification using SVM and K-NN,” Indones. J. Electr. Eng. Comput. Sci., vol. 24, no. 3, pp. 1523–1533, 2021, doi: 10.11591/ijeecs.v24.i3.pp1523-1533.
[25] B. Yue et al., “Research on SPAD Inversion of Rice Leaves at a Field Scale Based on Machine Vision and Leaf Segmentation Techniques,” Agric., vol. 15, no. 12, pp. 1–24, 2025, doi: 10.3390/agriculture15121270.
[26] P. Pradhan, B. Kumar, K. Kumar, and R. Bhutiani, “Plant leaf disease detection using local binary pattern and deep convolutional neural networks,” Environ. Conserv. J., vol. 26, no. 1, pp. 66–78, 2025, doi: 10.36953/ECJ.29292943.
[27] J. D. Thiagarajan et al., “Analysis of banana plant health using machine learning techniques,” Sci. Rep., vol. 14, no. 1, pp. 1–23, 2024, doi: 10.1038/s41598-024-63930-y.
[28] C. Nyasulu et al., “A comparative study of Machine Learning-based classification of Tomato fungal diseases: Application of GLCM texture features,” Heliyon, vol. 9, no. 11, p. e21697, 2023, doi: 10.1016/j.heliyon.2023.e21697.
[29] Z. Hou et al., “Selection of Optimal Diagnostic Positions for Early Nutrient Deficiency in Cucumber Leaves Based on Spatial Distribution of Raman Spectra,” Plants, vol. 14, no. 8, pp. 1–17, 2025, doi: 10.3390/plants14081199.
[30] D. Ma, L. Wang, L. Zhang, Z. Song, T. U. Rehman, and J. Jin, “Stress distribution analysis on hyperspectral corn leaf images for improved phenotyping quality,” Sensors, vol. 20, no. 13, pp. 1–13, 2020, doi: 10.3390/s20133659.
[31] M. Saberi Anari, “A Hybrid Model for Leaf Diseases Classification Based on the Modified Deep Transfer Learning and Ensemble Approach for Agricultural AIoT-Based Monitoring,” Comput. Intell. Neurosci., vol. 2022, no. 1, 2022, doi: 10.1155/2022/6504616.
[32] F. Budiman and E. Sugiarto, “Non-linear Multiclass SVM Classification Optimization using Large Datasets of Geometric Motif Image,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 9, pp. 284–290, 2021, doi: 10.14569/IJACSA.2021.0120932.
[33] Dhiyaussalam, A. Wibowo, F. A. Nugroho, E. A. Sarwoko, and I. M. A. Setiawan, “Classification of Headache Disorder Using Random Forest Algorithm,” in 2020 4th International Conference on Informatics and Computational Sciences (ICICoS), IEEE, Nov. 2020, pp. 1–5. doi: 10.1109/ICICoS51170.2020.9299105.
[34] Dhiyaussalam and S. Uyun, “Optimization of Random Forest Hyperparameters with Genetic Algorithm in Classification of Lung Cancer,” in 2023 6th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), 2023, pp. 82–88. doi: 10.1109/ISRITI60336.2023.10467686.
[35] D. Boldini, F. Grisoni, D. Kuhn, L. Friedrich, and S. A. Sieber, “Practical guidelines for the use of gradient boosting for molecular property prediction,” J. Cheminform., vol. 15, no. 1, pp. 1–13, 2023, doi: 10.1186/s13321-023-00743-7.
[36] A. Eley, T. T. Hlaing, D. Breininger, Z. Helforoush, and N. N. Kachouie, “Monte Carlo Gradient Boosted Trees for Cancer Staging: A Machine Learning Approach,” Cancers (Basel)., vol. 17, no. 15, pp. 1–27, 2025, doi: 10.3390/cancers17152452.
[37] J. Edin et al., “Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study,” SIGIR 2023 - Proc. 46th Int. ACM SIGIR Conf. Res. Dev. Inf. Retr., pp. 2572–2582, 2023, doi: 10.1145/3539618.3591918.
[38] Y. Liu et al., “Development and external validation of machine learning models for the early prediction of malnutrition in critically ill patients: a prospective observational study,” BMC Med. Inform. Decis. Mak., vol. 25, no. 1, 2025, doi: 10.1186/s12911-025-03082-9.
[39] C. Chen et al., “Application of GA-WELM Model Based on Stratified Cross-Validation in Intrusion Detection,” Symmetry (Basel)., vol. 15, no. 9, pp. 1–14, 2023, doi: 10.3390/sym15091719.
[40] V. Teodorescu and L. Obreja Brașoveanu, “Assessing the Validity of k-Fold Cross-Validation for Model Selection: Evidence from Bankruptcy Prediction Using Random Forest and XGBoost,” Computation, vol. 13, no. 5, 2025, doi: 10.3390/computation13050127.
[41] O. M. Alyasiri and Y. N. Cheah, “Multi-Class Text Classification using Machine Learning Techniques,” Eng. Technol. Appl. Sci. Res., vol. 15, no. 3, pp. 22598–22604, 2025, doi: 10.48084/etasr.9994.
[42] M. Amudha and K. Brindha, “Rice Leaf Nutrient Deficiency Classification System Using CAR-Capsule Network,” IEEE Access, vol. 12, pp. 169518–169532, 2024, doi: 10.1109/ACCESS.2024.3498606.
[43] M. Sharma, K. Nath, R. K. Sharma, C. J. Kumar, and A. Chaudhary, “Ensemble Averaging of Transfer Learning Models for Identification of Nutritional Deficiency in Rice Plant,” Electron., vol. 11, no. 1, 2022, doi: 10.3390/electronics11010148.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors Declaration
- 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.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- 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.
- 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.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- 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.
- 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.
- 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
