Skip to main navigation menu Skip to main content Skip to site footer
Plant Science Today (PST)

Research Articles

Vol. 13 No. 3 (2026)

Hybrid convolutional neural network–random forest framework for automated detection of bell pepper leaf diseases using image analysis

DOI
https://doi.org/10.14719/pst.14121
Submitted
16 February 2026
Published
14-09-2026 — Updated on 30-09-2026
Versions

Abstract

Diseases that affect plants considerably lower the production of crops and pose a significant threat to global food security, particularly in high-value crops like bell pepper (Capsicum annuum L.). The timely and sensitive identification of the disease is essential in reducing losses related to yield and paving the way to sustainable management of crops. Although automated plant disease diagnosis has been improved by artificial intelligence (AI)-driven image analysis, single-model methods are not always robust or generalisable. The study proposes a hybrid convolutional neural network-random forest (CNN-RF) framework for the early detection of bell pepper leaf diseases. Deep visual features of leaf images were extracted and subsequently used with a pretrained ResNet50 model and then used to classify the images with the help of a RF ensemble algorithm. Experiments were conducted on a publicly available PlantVillage bell pepper dataset comprising 495 leaf images (199 bacterial spot and 296 healthy samples). The classification accuracy of the proposed hybrid model was 97.98 % with high class-wise precision, recall and F1-scores. Receiver operating characteristic (ROC) analysis produced an area under the curve (AUC) of 0.98, indicating excellent discriminative performance. The dataset was evaluated using a stratified 80 : 20 train-test split. The results show that deep feature extraction combined with an ensemble learning method can improve classification accuracy and offer a scalable solution to assist in precision
agriculture and timely disease control. However, the framework was evaluated only on the PlantVillage dataset and has not yet been validated under real-field agricultural conditions. The framework demonstrates potential for extension to multi-disease classification tasks, although further validation on field-acquired datasets is required.

References

  1. 1. Hossain MM, Sultana F, Mostafa M, Ferdus H, Rahman M, Rana JA, et al. Plant disease dynamics in a changing climate: Impacts, molecular mechanisms, and climate-informed strategies for sustainable management. Discover Agric. 2024;2:132. https://doi.org/10.1007/s44279-024-00144-w
  2. 2. Mwangi RW, Mustafa M, Charles K, Wagara IW, Kappel N. Selected emerging and reemerging plant pathogens affecting the food basket: A threat to food security. J Agric Food Res. 2023;14:100827. https://doi.org/10.1016/j.jafr.2023.100827
  3. 3. Sam-on MFS, Mustafa S, Yusof MT, Hashim AM, Ku Aizuddin KNA. Exploring global trends of Bacillus, Trichoderma and entomopathogenic fungi for pathogen and pest control in chili cultivation. Saudi J Biol Sci. 2024;31(8):104046. https://doi.org/10.1016/j.sjbs.2024.104046
  4. 4. Lisboa LAM, Galindo FS, Pagliari PH, Goncalves JIUP, Okazuka MH, Cunha MLO, et al. Morpho-physiological assessment of tomato and bell pepper in response to nutrient restriction. Stresses. 2024;4(1):172–84. https://doi.org/10.3390/stresses4010010
  5. 5. Reddy LV, Ganesh D, Madhavi A, Ahmad I, Madamala R, Logeshwari P. Plant disease detection and classification using advanced artificial intelligence and machine learning approaches. AIP Conf Proc. 2024;3101:060002. https://doi.org/10.1063/5.0221328
  6. 6. Isinkaye FO, Olusanya MO, Singh PK. Deep learning and content-based filtering techniques for improving plant disease identification and treatment recommendations: A comprehensive review. Heliyon. 2024;10(9):e29583. https://doi.org/10.1016/j.heliyon.2024.e29583
  7. 7. Sambana B, Nnadi HS, Wajid MA, Fidelia NO, Camacho-Zuñiga C, Ajuzie HD, et al. An efficient plant disease detection using transfer learning approach. Sci Rep. 2025;15(1):19082. https://doi.org/10.1038/s41598-025-02271-w
  8. 8. Virginia VV, Mbanaso UM, Chaku ES, Clementina IO, Aimufua G. Deep learning and convolutional neural networks (CNNs). GAS J Eng Technol. 2025;2(11). https://doi.org/10.5281/zenodo.17552650
  9. 9. Ashtagi R. Fusion of AI techniques: A hybrid approach for precise plant leaf disease classification. J Electr Syst. 2024;20(1 Suppl):850–61. https://doi.org/10.52783/jes.836
  10. 10. Chaudhary P, Verma A, Kukreja V, Sharma R. Integrating deep learning and ensemble methods for robust tomato disease detection: A hybrid CNN-RF model analysis. In: Proceedings of the 11th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO). IEEE; 2024. p. 1–4. https://doi.org/10.1109/ICRITO61523.2024.10522213
  11. 11. Sharma G, Anand V, Malhotra S, Kukreti S, Gupta S. CNN-based intelligent classification of bell pepper plant diseases: A novel approach for precision agriculture. In: Proceedings of the 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON). IEEE; 2023. p. 1–5. https://doi.org/10.1109/SMARTGENCON60755.2023.10442079
  12. 12. Mori Y, Limbasia B, Gupta RK, Bharti SK. AI-based potato and tomato leaf disease detection using CNN and pre-trained model. In: Proceedings of the 7th International Conference on Computing, Communication, Control and Automation (ICCUBEA). IEEE; 2023. p. 1–6. https://doi.org/10.1109/ICCUBEA58933.2023.10392028
  13. 13. Kumar V, Riturani. Integrative framework for accurate coriander disease classification: Unifying deep learning and machine learning approaches with feature-rich hybrid models. In: Proceedings of the 4th International Conference on Technological Advancements in Computational Sciences (ICTACS). IEEE; 2024. p. 121–7. https://doi.org/10.1109/ICTACS62700.2024.10841134
  14. 14. Fathima MD, Gupta A, Jain K. Deep-transfer learning for multi-crop leaf disease prediction using ResNet and ConvNet. In: Proceedings of the 2024 International Conference on Advancements in Power, Communication and Intelligent Systems (APCI). IEEE; 2024. p. 1–6. https://doi.org/10.1109/APCI61480.2024.10616983
  15. 15. Pinem J, Astuti W. Enhancing plant disease classification with transfer learning and data augmentation: A comprehensive evaluation of deep learning architectures. In: Proceedings of the International Seminar on Intelligent Technology and Its Applications (ISITIA). IEEE; 2025. p. 1–6. https://doi.org/10.1109/ISITIA66279.2025.11137537
  16. 16. Mishra U, Pandey A, G L, K T. Deep learning-based disease detection in potato and mango leaves: A comparative study of CNN, AlexNet, ResNet, and EfficientNet. Sci Rep. 2025;16(1):32607. https://doi.org/10.1038/s41598-025-32607-5
  17. 17. Charisis C, Argyropoulos D. Deep learning-based instance segmentation architectures in agriculture: A review of the scopes and challenges. Smart Agric Technol. 2024;8:100448. https://doi.org/10.1016/j.atech.2024.100448
  18. 18. Laxmi SS, Lincy MM. A comprehensive survey of deep learning methods for Capsicum (bell pepper) leaf disease detection. Plant Sci Today. 2025;12(Suppl 4). https://doi.org/10.14719/pst.10384
  19. 19. Thirumalraj A, Chandrashekar R, G B, Balasubramanian PK. Detection of pepper plant leaf disease using Tom and Jerry algorithm with MSTNet. In: Srivastava P, Yadav A, editors. Machine Learning Techniques and Industry Applications. Hershey (PA): IGI Global; 2024. p. 143–68. https://doi.org/10.4018/979-8-3693-5271-7.ch008
  20. 20. Gondal HAH, Jeong SI, Jang WH, Kim JS, Akram R, Irfan M, et al. Artificial intelligence-based plant disease classification in low-light environments. Fractal Fract. 2025;9(11):691. https://doi.org/10.3390/fractalfract9110691
  21. 21. Rezaei M, Diepeveen D, Laga H, Jones MGK, Sohel F. Plant disease recognition in a low data scenario using few-shot learning. Comput Electron Agric. 2024;219:108812. https://doi.org/10.1016/j.compag.2024.108812
  22. 22. Murugesan S, Chinnadurai J, Srinivasan S, Mathivanan SK, Chandan RR, Moorthy U. Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability. Sci Rep. 2025;15(1):29955. https://doi.org/10.1038/s41598-025-14847-7
  23. 23. Upadhyay A, Chandel NS, Singh KP, Chakraborty SK, Nandede BM, Kumar M, et al. Deep learning and computer vision in plant disease detection: A comprehensive review of techniques, models, and trends in precision agriculture. Artif Intell Rev. 2025;58:92. https:// doi.org/10.1007/s10462-024-11100-x
  24. 24. Murugavalli S, Gopi R. Plant leaf disease detection using vision transformers for precision agriculture. Sci Rep. 2025;15(1):22361. https://doi.org/10.1038/s41598-025-05102-0
  25. 25. Alsubai S, Almadhor A, Al Hejaili A, Gadekallu TR. Intelligent smart sensing with ResNet-PCA and hybrid ML-DNN for sustainable and accurate plant disease detection. Front Plant Sci. 2025;16:1691415. https://doi.org/10.3389/fpls.2025.1691415
  26. 26. He K, Girshick R, Dollár P. Rethinking ImageNet pre-training. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). IEEE; 2019. p. 4917–26. https://doi.org/10.1109/ICCV.2019.00502
  27. 27. Kumar S, Aravinth SS, Kollem S, Kumar M, Naveed QN, Mubarakali A, et al. Spatial attention-guided pre-trained networks for accurate identification of crop diseases. Sci Rep. 2025;15:23213. https://doi.org/10.1038/s41598-025-08004-3
  28. 28. Taye MM. Understanding of machine learning with deep learning: Architectures, workflow, applications and future directions. Computers. 2023;12(5):91. https://doi.org/10.3390/computers12050091
  29. 29. Dhannya J, Veni S. Deep neural networks for plant disease detection: Insights from VGG16, U-Net, and ResNet. J Wirel Mob Netw Ubiquitous Comput Dependable Appl. 2026;17(1):34–46. https://doi.org/10.58346/JOWUA.2026.I1.003
  30. 30. Kazi SS, Palkar B, Mishra D. VCNet: Optimized deep learning framework with deep feature extraction and genetic algorithm for multiclass rice crop disease detection. MethodsX. 2025;15:103551. https://doi.org/10.1016/j.mex.2025.103551
  31. 31. Bazrafkan A, Worral H, Bandillo N, Flores P. Multispectral data and random forest model outperform deep learning in predicting lentil maturity using UAS imagery. J Agric Food Res. 2025;23:102202. https://doi.org/10.1016/j.jafr.2025.102202
  32. 32. Imani M, Beikmohammadi A, Arabnia HR. Comprehensive analysis of random forest and XGBoost performance with SMOTE, ADASYN, and GNUS under varying imbalance levels. Technologies. 2025;13(3):88. https://doi.org/10.3390/technologies13030088

Downloads

Download data is not yet available.