A Robust Integrated DenseNet201-SVM Approach for Wheat Leaf Disease Detection

Hooria Shahbaz

Authors

Hooria Shahbaz Capital University of Science and Technology

Keywords:

Wheat Leaf Disease Classification, DenseNet201, Support Vector Machine (SVM), Deep Learning, Computer Vision

Abstract

Wheat leaf diseases significantly affect agricultural productivity, crop quality, and global food security. Manual disease inspection is time-consuming, subjective, and less reliable for large-scale field monitoring. This study proposes a robust DenseNet201-SVM integrated framework for automated wheat leaf disease classification. “DenseNet201 is used as a deep feature extractor, while a Support Vector Machine (SVM) performs the final classification. The dataset contains 54,306 images from four classes: Healthy, Yellow Rust, Brown Rust, and Powdery Mildew. The proposed DenseNet201-SVM model achieved 98.64% accuracy, 98.5% precision, 98.7% recall, and 98.6% F1-score. Confusion matrix analysis showed strong class-wise performance, with most errors occurring between visually similar rust categories. The ensemble model further improved accuracy to 99.1%. Statistical validation using a paired t-test produced a p-value of 0.001, confirming that the improvement was statistically significant. The results demonstrate that the proposed framework is accurate, robust, and suitable for intelligent wheat disease monitoring systems.

References

M. Nagaraju, G. Jahnavi, V. Sri Vaishnavi, and M. Vaishnavi, “TLNet: A Novel Model to Detect Wheat Leaf Diseases using Deep Neural Network Architecture,” 3rd Int. Conf. Intell. Data Commun. Technol. Internet Things, IDCIoT 2025, pp. 1394–1399, 2025, doi: 10.1109/IDCIOT64235.2025.10915128.

Hongyan Zang, Annie Anak Joseph, Shourong Zhang, Haiyan Fu, Lili Huang, and Zhen Huang, “FCA-ResNet: An Improved Model with Enhanced Multi-Scale Feature Fusion and Coordinate Attention for Wheat Leaf Disease Classification,” Int. j. eng. technol. innov, vol. 15, no. 2, pp. 195–209, 2025, [Online]. Available: https://ojs.imeti.org/index.php/IJETI/article/view/14304

D. Kumar and V. Kukreja, “CaiT-YOLOv9: hybrid transformer model for wheat leaf fungal head prediction and diseases classification,” Int. J. Inf. Technol. 2025 175, vol. 17, no. 5, pp. 2749–2763, Feb. 2025, doi: 10.1007/s41870-025-02443-x.

Amna Hassan, Rafia Mumtaz, “Wheat leaf localization and segmentation for yellow rust disease detection in complex natural backgrounds,” Alexandria Eng. J., vol. 107, pp. 786–798, 2024, doi: https://doi.org/10.1016/j.aej.2024.09.018.

X. Yao, F. Yang and J. Yao, “YOLO-Wheat: A Wheat Disease Detection Algorithm Improved by YOLOv8s,” IEEE Access, vol. 12, 2024, doi: 10.1109/ACCESS.2024.3460394.

Ruiheng Li, Wenjie Hong, “Enhancing Wheat Spike Counting and Disease Detection Using a Probability Density Attention Mechanism in Deep Learning Models for Precision Agriculture,” Plants, vol. 13, no. 24, p. 3462, 2024, doi: https://doi.org/10.3390/plants13243462.

Eray Önler, Nagehan Desen Köycü, “Wheat Powdery Mildew Detection with YOLOv8 Object Detection Model,” Appl. Sci., vol. 14, no. 16, p. 7073, 2024, doi: https://doi.org/10.3390/app14167073.

Xiaojie Wen, Muzaipaer Maimaiti, “MnasNet-SimAM: An Improved Deep Learning Model for the Identification of Common Wheat Diseases in Complex Real-Field Environments,” Plants, vol. 13, no. 16, p. 2334, 2024, doi: https://doi.org/10.3390/plants13162334.

A. Ali, H. Shahbaz, S. M. Ganie, and M. M. Alfuraydan, “X-vitcnn: A novel network-level fusion of transfer learning and customized vision transformer for multi-stage alzheimer’s disease prediction using mri scans,” Diagnostics, vol. 16, no. 6, 2026.