Implementing Deep Learning Architectures for Multi-Class Classification of Crop Images | IJCT Volume 13 – Issue 5 | IJCT-V13I5P68
International Journal of Computer Techniques
ISSN 2394-2231
Author
Narsaiah Battu, Dr. Arathi Chitla
Abstract
In order to identify illnesses, pests, and nutrient deficits in crop photos, this work develops and evaluates a deep learning model for multi-class categorization. The suggested approach, which makes use of convolutional neural networks (CNNs), performs well when managing the inherent variability in environmental factors, including lighting, weather, and crop health conditions. The method incorporates extensive data augmentation techniques, such as rotations, flips, and colour modifications, to boost accuracy and generalization while guaranteeing the model’s flexibility to a variety of agricultural contexts. Advanced optimization techniques, including early halting to avoid overfitting and model check-pointing to maintain the top-performing model throughout training, are incorporated into the training pipeline. A variety of datasets that are indicative of actual agricultural environments are used in the study to assess the architecture, and it achieves good precision and recall metrics across a number of crop classes. This study demonstrates how deep learning architectures have the potential to transform precision agriculture by making it possible to identify crop-related problems early on, which would increase productivity and promote sustainable farming methods.
Keywords
Convolutional Neural Networks (CNN), Multi-Classification, Crop Images
Conclusion
This study successfully addressed the problem of recognizing illnesses, pests, and nutrient deficits by implementing a deep learning model for multi-class classification of crop photos. The model’s use of convolutional neural networks (CNNs) allowed it to handle the variety present in agricultural datasets, such as variations in crop stages, lighting, and environmental variables, with strong performance. The model’s performance was further enhanced by the use of data augmentation approaches, early halting, and model checkpointing, which guaranteed the model’s responsiveness to actual agricultural situations. The findings demonstrate CNNs’ enormous promise in agricultural applications by showing how well and accurately they can automate and improve crop health monitoring procedures. This work lays a solid basis for future developments in precision agriculture, including the incorporation of real-time monitoring systems, the diversification of datasets, and the inclusion of other stressors like soil conditions or weather effects. Future studies could examine how effectively these models scale for more datasets and more diverse crop categories, as well as how they can be integrated with drone and Internet of Things technologies to provide real-time, field-level diagnoses. In an increasingly resource-constrained world, this work supports efforts to assure food security and promotes sustainable farming practices by expanding the possibilities of deep learning in agriculture.
References
[1] V. Sarvesh, S. Hemanth Raja, P. Jeevanantham, and S. P. Ramu, “EHiJackNet: A Quantized Hierarchical Deep Learning Framework for Efficient and Robust Jackfruit Disease Diagnosis on Edge Devices,” IEEE Access, vol. 14, pp. 79872–79900, 2026, doi: 10.1109/ACCESS.2026.3691996.
[2] S. Srinivasan, R. K. A, N. B. A, J. Tanwar, V. P. Singh, and U. Moorthy, “Multi-class classification of plant leaf diseases using a hybrid deep neural transformer system and explainable AI techniques,” Scientific Reports, vol. 16, Art. no. 18161, 2026, doi: 10.1038/s41598-026-48103-3.
[3] “AgriFusionNet: A Multi-Scale Attention-Based Framework for Fine-Grained Plant Disease and Severity Classification,” Procedia Computer Science, vol. 283, pp. 5090–5099, 2026, doi: 10.1016/j.procs.2026.06.562.
[4] E. Sert and S. Kiziloluk, “A hybrid deep learning approach combining neutrosophic set theory and multi-axis vision transformer for nutrient deficiency classification in plants,” Engineering Applications of Artificial Intelligence, vol. 162, Art. no. 112705, 2025, doi: 10.1016/j.engappai.2025.112705.
[5] S. Muthusamy and S. P. Ramu, “A Dynamic Attention-Guided Deep Learning Framework (D-PAN) With Reduced Complexity for Fine Grained Severity-Aware Classification of Micronutrient Deficiency and Disease Detection in Banana and Coffee Leaves,” IEEE Access, vol. 13, pp. 153474–153497, 2025, doi: 10.1109/ACCESS.2025.3599359.
[6] A. Prommakhot, J. Onshaunjit, W. Ooppakaew, G. Samseemoung, and J. Srinonchat, “Hybrid CNN and Transformer-Based Sequential Learning Techniques for Plant Disease Classification,” IEEE Access, vol. 13, pp. 122876–122887, 2025, doi: 10.1109/ACCESS.2025.3586285.
[7] M. Daga, D. Parikh, and S. P. Ramu, “DeepSeqCoco: A Robust Mobile Friendly Deep Learning Model for Detection of Diseases in Cocos nucifera,” IEEE Access, vol. 13, pp. 89367–89385, 2025, doi: 10.1109/ACCESS.2025.3571800.
[8] D. J. Richter, I. Bappi, S. S. Kolekar, and K. Kim, “A Systematic Review of the Current State of Transfer Learning Accelerated CNN-Based Plant Leaf Disease Classification,” IEEE Access, vol. 13, pp. 116262–116303, 2025, doi: 10.1109/ACCESS.2025.3584404.
[9] A. Daalah, S. Aldousari, S. Alrashed, H. Alenezi, A. Alhajri, and A. Eleyan, “Plant Leaf Disease Classification Using Fine-Tuned Pre-Trained CNN Models,” in Proc. 6th Int. Conf. Bio-engineering for Smart Technologies (BioSMART), 2025, doi: 10.1109/BioSMART66413.2025.11046055.
[10] S. Makka, M. A. Sarvath, M. Shravya, and K. Meherkrishna, “Deep Learning-Driven System for Automated Identification of Plant Nutrient Deficiencies,” in Proc. 3rd Int. Conf. Communication, Security, and Artificial Intelligence (ICCSAI), 2025, doi: 10.1109/ICCSAI64074.2025.11064196.
[11] A. Srilatha and P. Pappula, “CNN-Based Plant Leaf Disease Identification and Classification for Sustainable Agriculture,” in Proc. 6th Int. Conf. Mobile Computing and Sustainable Informatics (ICMCSI), 2025, doi: 10.1109/ICMCSI64620.2025.10883522.
[12] “Deep Learning Approaches for Plant Disease Detection Using AI,” in Proc. 6th Int. Conf. Mobile Computing and Sustainable Informatics (ICMCSI), 2025, doi: 10.1109/ICMCSI64620.2025.10883358.
[13] M. S. Sirsat, D. Isla-Cernadas, E. Cernadas, and M. Fernández-Delgado, “Machine and deep learning for the prediction of nutrient deficiency in wheat leaf images,” Knowledge-Based Systems, vol. 317, Art. no. 113400, 2025, doi: 10.1016/j.knosys.2025.113400.
[14] R. Karthik, A. Ajay, A. S. Bisht, T. Illakiya, and K. Suganthi, “A Deep Learning Approach for Crop Disease and Pest Classification Using Swin Transformer and Dual-Attention Multi-Scale Fusion Network,” IEEE Access, vol. 12, pp. 152639–152655, 2024, doi: 10.1109/ACCESS.2024.3481675.
[15] S. Zhao, H. Wang, T. Liu, and S. Huang, “Integrating Multiscale Linear Attention and Focal Loss for Robust Pest Classification,” IEEE Access, vol. 12, pp. 146610–146619, 2024, doi: 10.1109/ACCESS.2024.3473536.
[16] M. Lubag, M. A. Lubreza, V. A. Dela Paz, R. Concepcion, and R. van de Zedde, “Potato Leaf Disease Classification Using Vision Transformer Networks,” in Proc. 16th IEEE Int. Conf. Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), 2024, Art. no. 11258664, doi: 10.1109/HNICEM64917.2024.11258664.
[17] M. F. Yustika, A. Candra, and A. I. Siregar, “Identification of Rice Pests using Digital Images and Convolutional Neural Network (CNN) Methods to Support Modern Agriculture,” in Proc. 5th Int. Conf. Computational Science & Information Management (ICoCSIM), pp. 116–121, 2024, doi: 10.1109/ICoCSIM65098.2024.00028.
[18] H. P. Chandu, G. Vyshnavi, K. D. Kotipalli, and P. Ramireddygari et al., “Machine and Deep Learning Approaches for Crop Disease Detection: An In-Depth Analysis,” in Proc. 9th IEEE Int. Conf. for Convergence in Technology (I2CT), 2024, doi: 10.1109/I2CT61223.2024.10543627.
[19] H. Peng, H. Xu, Z. Gao, Z. Zhou, X. Tian, Q. Deng, H. He, and C. Xian, “Crop pest image classification based on improved densely connected convolutional network,” Frontiers in Plant Science, vol. 14, Art. no. 1133060, 2023, doi: 10.3389/fpls.2023.1133060.
[20] S. S. Begum, A. Yannam, M. C. C. Chowdary, T. R. Devi, V. P. Nallamothu, Y. Jahnavi, and R. Vijayender, “Deep Learning-based Nutrient Deficiency symptoms in plant leaves using Digital Images,” in Proc. 2nd Int. Conf. Advances in Computational Intelligence and Communication (ICACIC), 2023, doi: 10.1109/ICACIC59454.2023.10435129
How to Cite This Paper
Narsaiah Battu, Dr. Arathi Chitla (2026). Implementing Deep Learning Architectures for Multi-Class Classification of Crop Images. International Journal of Computer Techniques, 13(5). ISSN: 2394-2231.
