Maize Leaf Disease Detection using Deep Learning Models and a DenXNet Ensemble Model
محورهای موضوعی : Image Processing
Meghna Gupta
1
,
Sarika Jain
2
,
Manoj Kumar
3
1 - Amity Institute of Information Technology, Amity University Noida, Uttar Pradesh, India
2 - Amity Institute of Information Technology, Amity University Noida, Uttar Pradesh, India
3 - Faculty of Engineering & Information Sciences, University of Wollongong, Dubai, United Arab Emirates
کلید واژه: Deep Learning, DenseNet169, DenseNet201, Xception, Mobilenet, Ensemble Model,
چکیده مقاله :
Maize(Corn) is considered an important crop worldwide for global production after wheat and rice. It provides food, ethanol, carbohydrates, vitamins, and other resources, making it essential to human civilization. However, it does face numerous difficulties, including pest infestations, deteriorating soil, scarce water supplies, and climate change, resulting in various yield losses. This research introduces an efficient deep learning framework for the accurate identification of maize leaf disease. Four convolutional neural network architectures, DenXNet- MobileNet, Xception, DenseNet169, and DenseNet201- were trained and evaluated using both original and augmented datasets. To ensure fairness and eliminate data leakage, the original data is divided into train, validation, and test sets, and then augmented, whereas a stratified five-fold cross-validation strategy was applied to non-augmented data. A comprehensive ablation study was conducted to compare model performance with and without augmentation and across different ensemble configurations. The study explored soft ensemble modelling using combinations of two and four base models. Among all configurations, the four-model ensemble, DenXNet, achieved the highest accuracy of 98.46% and consistency across folds, outperforming individual and partial ensembles. The proposed method demonstrates improved precision, reduced over fitting, and strong adaptability for real-world agricultural disease detection tasks.
Maize(Corn) is considered an important crop worldwide for global production after wheat and rice. It provides food, ethanol, carbohydrates, vitamins, and other resources, making it essential to human civilization. However, it does face numerous difficulties, including pest infestations, deteriorating soil, scarce water supplies, and climate change, resulting in various yield losses. This research introduces an efficient deep learning framework for the accurate identification of maize leaf disease. Four convolutional neural network architectures, DenXNet- MobileNet, Xception, DenseNet169, and DenseNet201- were trained and evaluated using both original and augmented datasets. To ensure fairness and eliminate data leakage, the original data is divided into train, validation, and test sets, and then augmented, whereas a stratified five-fold cross-validation strategy was applied to non-augmented data. A comprehensive ablation study was conducted to compare model performance with and without augmentation and across different ensemble configurations. The study explored soft ensemble modelling using combinations of two and four base models. Among all configurations, the four-model ensemble, DenXNet, achieved the highest accuracy of 98.46% and consistency across folds, outperforming individual and partial ensembles. The proposed method demonstrates improved precision, reduced over fitting, and strong adaptability for real-world agricultural disease detection tasks.
[1] A. H. Ali, A. Youssef, M. Abdelal, and M. A. Raja, “An ensemble of deep learning architectures for accurate plant disease classification,” Ecol. Inform., vol. 81, 102618, 2024, doi: 10.1016/j.ecoinf.2024.102618.
[2] S. Vallabhajosyula, V. Sistla, and V. K. K. Kolli, “A novel hierarchical framework for plant leaf disease detection using residual vision transformer,” Heliyon, vol. 10, no. 9, 2024, doi: 10.1016/j.heliyon.2024.e29912.
[3] R. Lumbantoruan, N. Rajagukguk, A. U. Lubis, M. Claudia, and H. Simanjuntak, “Two-step convolutional neural network classification of plant disease,” IAES Int. J. Artif. Intell., vol. 14, no. 1, pp. 584–591, 2025, doi: 10.11591/ijai.v14.i1.pp584-591.
[4] L. Miao et al., “A high-precision automatic diagnosis method of maize developmental stage based on ensemble deep learning with IoT devices,” Comput. Electron. Agric., vol. 227, 109608, 2024, doi: 10.1016/j.compag.2024.109608.
[5] W. H. Zeng, H. Li, G. Hu, and D. Liang, “Identification of maize leaf diseases by using the SKPSNet-50 convolutional neural network model,” Sustain. Comput. Informatics Syst., vol. 35, 100695, 2022, doi: 10.1016/j.suscom.2022.100695.
[6] I. Attri, L. K. Awasthi, T. P. Sharma, and P. Rathee, “A review of deep learning techniques used in agriculture,” Ecol. Inform., vol. 77, 102217, 2023, doi: 10.1016/j.ecoinf.2023.102217.
[7] M. Yang, A. Sekhari Seklouli, L. Ren, Y. He, X. Yu, and Y. Ouzrout, “A new mobile diagnosis system for estimation of crop disease severity using deep transfer learning,” Crop Prot., vol. 184, 106776, 2024, doi: 10.1016/j.cropro.2024.106776.
[8] S, Jenifer, M J, Carmel Mary Belinda. Convolutional Neural Networks for Medical Image Segmentation and Classification: A Review. Journal of Information Systems and Telecommunication (JIST) 2023;11(44):347-358.10.61186/jist.37936.11.44.347.
[9] O. Erenstein, M. Jaleta, K. Sonder, K. Mottaleb, and B. M. Prasanna, “Global maize production, consumption and trade: trends and R&D implications,” Food Secur., vol. 14, no. 5, pp. 1295–1319, 2022, doi: 10.1007/s12571-022-01288-7.
[10] T. Phattaraworamet, S. Sangsuriyun, P. Kutchomsri, and S. Chokphoemphun, “Image classification of lotus in Nong Han Chaloem Phrakiat Lotus Park using convolutional neural networks,” Artif. Intell. Agric., vol. 11, pp. 23–33, 2024, doi: 10.1016/j.aiia.2023.12.003.
[11] M. A. Jabed and M. A. Azmi Murad, “Crop yield prediction in agriculture: A comprehensive review of machine learning and deep learning approaches, with insights for future research and sustainability,” Heliyon, vol. 10, no. 24, 2024, doi: 10.1016/j.heliyon.2024.e40836.
[12] A. Pal and V. Kumar, “AgriDet: Plant Leaf Disease severity classification using agriculture detection framework,” Eng. Appl. Artif. Intell., vol. 119, 105754, 2023, doi: 10.1016/j.engappai.2022.105754.
[13] X. Sun and J. Wei, “Identification of maize disease based on transfer learning,” J. Phys. Conf. Ser., vol. 1437, no. 1, 2020, doi: 10.1088/1742-6596/1437/1/012080.
[14] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification,” Comput. Intell. Neurosci., 2016, doi: 10.1155/2016/3289801.
[15] X. Lv, X. Zhang, H. Gao, T. He, Z. Lv, and L. Zhangzhong, “When crops meet machine vision: A review and development framework for a low-cost nondestructive online monitoring technology in agricultural production,” Agric. Commun., vol. 2, no. 1, 100029, 2024, doi: 10.1016/j.agrcom.2024.100029.
[16] P. Chaudhary, A. K. Chaudhari, A. Cheeran, and S. Godara, “Color Transform Based Approach for Disease Spot Detection on Plant Leaf,” Int. J. Comput. Sci. Telecommun., vol. 3, no. 6, pp. 65–71, 2012, [17] S. B. Patil and S. K. Bodhe, “Leaf disease severity measurement using image processing,” Int. J. Eng. Technol., vol. 3, no. 5, pp. 297–301, 2011.
[18] M. U. Ahmad, S. Ashiq, G. Badshah, A. H. Khan, and M. Hussain, “Feature Extraction of Plant Leaf Using Deep Learning,” Complexity, 2022, doi: 10.1155/2022/6976112.
[19] E. Alehegn, “Maize Leaf Diseases Recognition and Classification Based on Imaging and Machine Learning Techniques,” Int. J. Innov. Res. Comput. Commun. Eng., vol. 5, no. 12, pp. 1–11, 2017.
[20] S. Mishra, R. Sachan, and D. Rajpal, “Deep Convolutional Neural Network based Detection System for Real-time Corn Plant Disease Recognition,” Procedia Comput. Sci., vol. 167, pp. 2003–2010, 2020, doi: 10.1016/j.procs.2020.03.236.
[21] B. S. Anami, N. N. Malvade, and S. Palaiah, “Arti fi cial Intelligence in Agriculture Deep learning approach for recognition and classi fi cation of yield affecting paddy crop stresses using fi eld images,” Artif. Intell. Agric., vol. 4, pp. 12–20, 2020, doi: 10.1016/j.aiia.2020.03.001.
[22] M. Agarwal, S. K. Gupta, and K. K. Biswas, “Development of Efficient CNN model for Tomato crop disease identification,” Sustain. Comput. Informatics Syst., vol. 28, 100407, 2020, doi: 10.1016/j.suscom.2020.100407.
[23] K. P. Panigrahi, H. Das, A. K. Sahoo, and S. C. Moharana, “Maize Leaf Disease Detection and Classification Using Machine Learning Algorithms,” Adv. Intell. Syst. Comput., vol. 1119, pp. 659–669, 2020, doi: 10.1007/978-981-15-2414-1_66.
[24] S. Pudumalar and S. Muthuramalingam, “Hydra: An ensemble deep learning recognition model for plant diseases,” J. Eng. Res., 2024, doi: 0.1016/j.jer.2023.09.033.
[25] S. K. Subramanya and N. Bettahalli, “Enhanced detection of tomato leaf diseases using ensemble deep learning: INCVX-NET model,” IAES Int. J. Artif. Intell., vol. 13, no. 4, pp. 4757–4765, 2024, doi: 10.11591/ijai.v13.i4.pp4757-4765.
[26] J. Nakatumba-Nabende and S. Murindanyi, “Deep learning models for enhanced in-field maize leaf disease diagnosis,” Mach. Learn. with Appl., vol. 20, 100673, 2025, doi: 10.1016/j.mlwa.2025.100673.
[27] Maiti, Abdallah, Hanini, Mohamed, Abarda, Abdallah. Resolving Class Imbalance in Medical Classification: Technique Comparison and Performance Evaluation. Journal of Information Systems and Telecommunication (JIST) . 2025;13(51):177-188. .61882/jist.49725.13.51.177.
[28] S. Coulibaly, B. Kamsu-Foguem, D. Kamissoko, and D. Traore, “Deep neural networks with transfer learning in millet crop images,” Comput. Ind., vol. 108, pp. 115–120, 2019, doi: 10.1016/j.compind.2019.02.003.
[29] G. Wang, H. Yu, and Y. Sui, “Research on Maize Disease Recognition Method Based on Improved ResNet50,” Mob. Inf. Syst., 2021, doi: 10.1155/2021/9110866.
[30] M. M. Khalid and O. Karan, “Deep Learning for Plant Disease Detection,” Int. J. Math. Stat. Comput. Sci., vol. 2, pp. 75–84, 2023, doi: 10.59543/ijmscs.v2i.8343.
[31] A. Daza, C. F. Ponce Sánchez, G. Apaza-Perez, J. Pinto, and K. Zavaleta Ramos, “Stacking ensemble approach to diagnosing the disease of diabetes,” Informatics Med. Unlocked, vol. 44, 2024, doi: 10.1016/j.imu.2023.101427.
[32] M. Aqil et al., “Deep learning based stacking ensembles for tropical sorghum classification,” J. Agric. Food Res., vol. 21, 101931, 2025, doi: 10.1016/j.jafr.2025.101931.
[33] A. Ghasemieh, A. Lloyed, P. Bahrami, P. Vajar, and R. Kashef, “A novel machine learning model with Stacking Ensemble Learner for predicting emergency readmission of heart-disease patients,” Decis. Anal. J., vol. 7, 100242, 2023, doi: 10.1016/j.dajour.2023.100242.
[34] A. Asil, H. Alipour, S. Mojtahedzadeh, and H. Asil, “Ensemble learning of Ada-boosting Based on Deep Weighting for Classification of Hand-written Numbers in Persian (With the doctors’ (With the doctors’ prescription approach),” J. Inf. Syst. Telecommun., vol. 12, no. 2, pp. 162–169, 2024, doi: 10.61186/jist.41053.12.46.162.
