Millions of people depend on wheat as a staple food, especially in agrarian nations like Bangladesh. It is a crop of global importance. Many foliar diseases, such as Septoria Tritici Blotch (STB), a fungal infection that causes tan lesions and yellow halos, pose a threat to its productivity. Manual inspection for traditional disease diagnosis is labor-intensive, prone to mistakes, and not scalable. Recent developments in deep learning and image processing provide a promising substitute for highly accurate automated plant disease detection. With an emphasis on Septoria, this study suggests a thorough deep-learning framework for the identification and categorization of wheat leaf diseases. The methodology entails gathering high-resolution images of wheat leaves from public and research institutions. The images are subjected to color-based and threshold segmentation to isolate infected regions following initial preprocessing, which includes noise reduction, enhancement, and standardization. After that, thirteen texture features that represent color and structural patterns are extracted using the Gray-Level Co-occurrence Matrix (GLCM) technique. Multiple classification models, such as Random Forest (RF), Support Vector Machine (SVM), k-nearest Neighbors (k-NN), and Naïve Bayes (NB), are then trained and assessed using these features. Python and the TensorFlow, Keras, and Mahotas libraries are used to implement the system. Confusion matrices are used to calculate performance metrics like accuracy, sensitivity, specificity, precision, and error rate. Based on experimental results, the Random Forest classifier performed better than the others, achieving 98.9% accuracy, 100% precision and specificity, and 98.1% sensitivity. This validates the suggested method's resilience in comparison to conventional classifiers. The results point to the possibility of implementing deep learning-based technology in actual agricultural environments, supporting sustainable farming, yield enhancement, and early disease detection.
| Published in | Machine Learning Research (Volume 10, Issue 1) |
| DOI | 10.11648/j.mlr.20251001.16 |
| Page(s) | 53-68 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
Deep Learning, Agriculture, Septoria, Wheat Leaf Disease, Classification, Image Processing
| [1] | Pakholkova, E. V., Zhelezova, A. D., Sonyushkin, A. V., & Glinushkin, A. (2023). Hyperspectral Non-Imaging Measurements and Perceptron Neural Network for Pre-Harvesting Assessment of Damage Degree Caused by Septoria/Stagonospora Blotch Diseases of Wheat. Agronomy, 13(4), 1045. |
| [2] | Genaev, M. A., Skolotneva, E., Gultyaeva, E. I., Orlova, E. A., Bechtold, N. P., Afonnikov, D. A., & Afonnikov, D. A. (2021). Image-Based Wheat Fungi Diseases Identification by Deep Learning. 10(8), 1500. |
| [3] | Long, M., Hartley, M., Morris, R. J., & Brown, J. K. M. (2022). Deep Learning for Wheat Disease Classification by Using Deep Learning Networks with Field and Glasshouse Images. Plant Pathology, 72(3), 536–547. |
| [4] | Dong, M., Mu, S., Shi, A., Mu, W., & Sun, W. (2020). Novel method for identifying wheat leaf disease images based on differential amplification convolutional neural network. International Journal of Agricultural and Biological Engineering, 13(4), 205–210. |
| [5] | Arinicheva, I., Arinichev, I. V., & Darmilova, Z. D. (2022). Cereal fungal diseases detection using autoencoders. IOP Conference Series: Earth and Environmental Science, 949(1), 012048. |
| [6] | Albattah, W., Nawaz, M., Javed, A., Masood, M., & Albahli, S. (2021). A novel deep learning method for detection and classification of plant diseases. Complex & Intelligent Systems, 1–18. |
| [7] | Soo, Jun, Wei., Dimas, Firmanda, Al, Riza., Hermawan, Eko, Nugroho. (2022). Comparative study on the performance of deep learning implementation in the edge computing: Case study on the plant leaf disease identification. Journal of agriculture and food research, |
| [8] | Chakraborty, A., Chakraborty, A., Sobhan, A., & Pathak, A. Deep Learning for Precision Agriculture: Detecting Tomato Leaf Diseases with VGG-16 Model. International Journal of Computer Applications, 975, 8887. |
| [9] | Ghazanfar, Latif., Sherif, Elmeligy, Abdelhamid., Roxane, Elias, Mallouhy., Jaafar, Alghazo., Z., A., Kazimi. (2022). Deep Learning Utilization in Agriculture: Detection of Rice Plant Diseases Using an Improved CNN Model. Plants, |
| [10] | Seyam, T. A., Pathak, A. AgriScan: Next.js powered cross-platform solution for automated plant disease diagnosis and crop health management. Journal of Electrical Systems and Inf Technol 11, 45 (2024). |
| [11] | Hossain, S., Seyam, T. A., Chowdhury, A., Ghose, R., Rahaman, A., et al. (2025). Enhancing Agricultural Diagnostics: Advanced Training of Pre-Trained CNN Models for Paddy Leaf Disease Detection. Machine Learning Research, 10(1), 1-13. |
| [12] | A. Chowdhury, ”Advancing Multi-Class Arc Welding Defect Classification: DEEPTLWELD Intelligent System Utilizing Computer Vision, Deep Learning, and Transfer Learning on Radiographic X-ray Images for Bangladesh’s Manufacturing Sector,” 2024 IEEE International Conference on Computing, Applications and Systems (COMPAS), Cox’s Bazar, Bangladesh, 2024, pp. 1-6, |
| [13] | Monoronjon, Dutta., Md, Rashedul, Islam, Sujan., Mayen, Uddin, Mojumdar., Narayan, Ranjan, Chakraborty., Ahmed, Al, Marouf., Jon, Rokne., Reda, Alhajj. (2024). 1. Rice Leaf Disease ClassificationaˆA Comparative Approach Using Convolutional Neural Network (CNN), Cascading Autoencoder with Attention Residual U-Net (CAAR-U-Net), and MobileNet- V2 Architectures. Technologies (Basel), |
| [14] | Alam, T. S., Jowthi, C. B. & Pathak, A. Comparing pre-trained models for efficient leaf disease detection: a study on custom CNN. Journal of Electrical Systems and Inf Technol 11, 12 (2024). |
| [15] | Salma, Akter., Rashedul, Islam, Sumon., Haider, Ali., HeeaˆCheol, Kim. (2024). 2. Utilizing Convolutional Neural Networks for the Effective Classification of Rice Leaf Diseases Through a Deep Learning Approach. Electronics, |
| [16] | J. K. V, D. Tauro, P. M. R, C. DSouza and B. Correia, ”Paddy Care: Paddy Disease Identification and Classification Using Deep DenseNet Network,” 2024 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER), Mangalore, India, 2024, pp. 377-382, |
| [17] | Athar, Hussain., Balaji, Srikaanth., P. ”4. Deep Learning with Crested Porcupine Optimizer for Detection and Classification of Paddy Leaf Diseases for Sustainable Agriculture.” Journal of machine and computing, undefined (2024). |
| [18] | Hossain, S., Seyam, T. A., Chowdhury, A., Xamidov, M., Ghose, R., Pathak, A. (2025). Fine-tuning LLaMA 2 interference: a comparative study of language implementations for optimal efficiency. arXiv preprint arXiv: 2502.01651. |
| [19] | Wang, Z., Yang, W., & Li, Y. (2023). MobileViT: Lightweight Vision Transformers for Edge-Device Plant Disease Detection. Computers and Electronics in Agriculture, 205, 107591. |
| [20] | Zhang, X., Huang, J., & Li, H. (2023). Multi-Disease Classification in Wheat Leaves Using Swin Transformers. Sensors, 23(7), 3652. |
| [21] | Islam, R., Alam, T., & Khan, A. (2022). Edge-Intelligent Plant Disease Detection Using Quantized EfficientNet. IEEE Access, 10, 112845–112856. |
| [22] | Roy, S., Mandal, B., & Banerjee, A. (2022). A Comparative Study of CNN and Transformer Architectures for Crop Disease Detection. Computational Intelligence and Neuroscience, 2022, 9874935. |
| [23] | Seyam, T. A., Hossain, M. S., Ghose, R., Nurmamatov, M., Fayzullo, N., et al. (2025). Next-Generation K-Means Clustering: Mojo-Driven Performance for Big Data. International Journal of Intelligent Information Systems, 14(1), 7-19. |
| [24] | Ali, M., Nasim, U., & Rehman, M. (2023). Attention-Based Deep Learning for Multi-Class Fruit Leaf Disease Detection. Applied Sciences, 13(2), 1254. |
APA Style
Maria Moon, M. M. (2025). A Deep Learning Framework for Precise Detection and Classification of Wheat Leaf Diseases. Machine Learning Research, 10(1), 53-68. https://doi.org/10.11648/j.mlr.20251001.16
ACS Style
Maria Moon, M. M. A Deep Learning Framework for Precise Detection and Classification of Wheat Leaf Diseases. Mach. Learn. Res. 2025, 10(1), 53-68. doi: 10.11648/j.mlr.20251001.16
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.mlr.20251001.16,
author = {Mirza Maria Maria Moon},
title = {A Deep Learning Framework for Precise Detection and Classification of Wheat Leaf Diseases
},
journal = {Machine Learning Research},
volume = {10},
number = {1},
pages = {53-68},
doi = {10.11648/j.mlr.20251001.16},
url = {https://doi.org/10.11648/j.mlr.20251001.16},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mlr.20251001.16},
abstract = {Millions of people depend on wheat as a staple food, especially in agrarian nations like Bangladesh. It is a crop of global importance. Many foliar diseases, such as Septoria Tritici Blotch (STB), a fungal infection that causes tan lesions and yellow halos, pose a threat to its productivity. Manual inspection for traditional disease diagnosis is labor-intensive, prone to mistakes, and not scalable. Recent developments in deep learning and image processing provide a promising substitute for highly accurate automated plant disease detection. With an emphasis on Septoria, this study suggests a thorough deep-learning framework for the identification and categorization of wheat leaf diseases. The methodology entails gathering high-resolution images of wheat leaves from public and research institutions. The images are subjected to color-based and threshold segmentation to isolate infected regions following initial preprocessing, which includes noise reduction, enhancement, and standardization. After that, thirteen texture features that represent color and structural patterns are extracted using the Gray-Level Co-occurrence Matrix (GLCM) technique. Multiple classification models, such as Random Forest (RF), Support Vector Machine (SVM), k-nearest Neighbors (k-NN), and Naïve Bayes (NB), are then trained and assessed using these features. Python and the TensorFlow, Keras, and Mahotas libraries are used to implement the system. Confusion matrices are used to calculate performance metrics like accuracy, sensitivity, specificity, precision, and error rate. Based on experimental results, the Random Forest classifier performed better than the others, achieving 98.9% accuracy, 100% precision and specificity, and 98.1% sensitivity. This validates the suggested method's resilience in comparison to conventional classifiers. The results point to the possibility of implementing deep learning-based technology in actual agricultural environments, supporting sustainable farming, yield enhancement, and early disease detection.
},
year = {2025}
}
TY - JOUR T1 - A Deep Learning Framework for Precise Detection and Classification of Wheat Leaf Diseases AU - Mirza Maria Maria Moon Y1 - 2025/05/14 PY - 2025 N1 - https://doi.org/10.11648/j.mlr.20251001.16 DO - 10.11648/j.mlr.20251001.16 T2 - Machine Learning Research JF - Machine Learning Research JO - Machine Learning Research SP - 53 EP - 68 PB - Science Publishing Group SN - 2637-5680 UR - https://doi.org/10.11648/j.mlr.20251001.16 AB - Millions of people depend on wheat as a staple food, especially in agrarian nations like Bangladesh. It is a crop of global importance. Many foliar diseases, such as Septoria Tritici Blotch (STB), a fungal infection that causes tan lesions and yellow halos, pose a threat to its productivity. Manual inspection for traditional disease diagnosis is labor-intensive, prone to mistakes, and not scalable. Recent developments in deep learning and image processing provide a promising substitute for highly accurate automated plant disease detection. With an emphasis on Septoria, this study suggests a thorough deep-learning framework for the identification and categorization of wheat leaf diseases. The methodology entails gathering high-resolution images of wheat leaves from public and research institutions. The images are subjected to color-based and threshold segmentation to isolate infected regions following initial preprocessing, which includes noise reduction, enhancement, and standardization. After that, thirteen texture features that represent color and structural patterns are extracted using the Gray-Level Co-occurrence Matrix (GLCM) technique. Multiple classification models, such as Random Forest (RF), Support Vector Machine (SVM), k-nearest Neighbors (k-NN), and Naïve Bayes (NB), are then trained and assessed using these features. Python and the TensorFlow, Keras, and Mahotas libraries are used to implement the system. Confusion matrices are used to calculate performance metrics like accuracy, sensitivity, specificity, precision, and error rate. Based on experimental results, the Random Forest classifier performed better than the others, achieving 98.9% accuracy, 100% precision and specificity, and 98.1% sensitivity. This validates the suggested method's resilience in comparison to conventional classifiers. The results point to the possibility of implementing deep learning-based technology in actual agricultural environments, supporting sustainable farming, yield enhancement, and early disease detection. VL - 10 IS - 1 ER -
Department of Computer Science and Engineering, Sonargaon University, Dhaka, Bangladesh
Information