Groundnut Leaf Disease Detection Using Deep Learning for Precision Agriculture

In this paper, a deep learning–based approach for automated groundnut leaf disease detection has been presented. The proposed system leverages the capabilities of Convolutional Neural Networks (CNNs) to accurately classify multiple groundnut leaf diseases using image-based analysis. By eliminating the need for manual feature extraction, the model effectively learns complex patterns such as texture variations, color changes, and lesion structures directly from raw images. The developed system is integrated into a Flask-based web application, providing a user-friendly interface for real-time disease prediction. Users can upload groundnut leaf images and instantly receive classification results along with confidence scores and visual interpretations. The inclusion of visualization techniques such as Grad-CAM enhances the transparency of the model by highlighting the regions responsible for the prediction, thereby increasing user trust and interpretability. Experimental evaluation demonstrates that the proposed model achieves high accuracy and performs reliably under varying environmental conditions, including differences in lighting, background, and leaf orientation. Compared to traditional machine learning approaches, the CNN-based system offers superior performance, scalability, and robustness. Additionally, the system reduces dependency on expert knowledge and enables faster decision-making, which is crucial for early disease detection and effective crop management. The practical significance of this work lies in its ability to assist farmers, agricultural researchers, and extension officers in identifying diseases at an early stage, thereby minimizing crop losses and improving productivity. By providing an automated and accessible diagnostic tool, the system contributes to the advancement of precision agriculture and sustainable farming practices. In conclusion, the integration of deep learning with web technologies presents a powerful and scalable solution for plant disease detection. The proposed system not only addresses the limitations of traditional methods but also establishes a foundation for future research in intelligent agricultural systems. With further enhancements such as mobile deployment, multi-crop support, and integration with IoT-based monitoring systems, this approach has the potential to significantly transform modern agricultural practices.

[1] A. Kaur, R. Sharma, S. Chattopadhyay, and A. Verma, “Automated multiclass classification of groundnut leaf diseases using fine-tuned Inception V3 model,” Proc. Int. Conf. Computer Vision in Agriculture, 2024. [2] Y. S. S. Sree, V. C. Reddy, D. Raveena, and J. Dolly, “Development of CNN model for detecting groundnut leaf diseases using MobileNet,” Proc. IEEE Conf. Smart Farming Technologies, 2024. [3] U. Naresh and T. B. Reddy, “Perception of groundnut leaf disease by neural network with progressive resizing,” IEEE Trans. Image Processing in Agriculture, vol. 11, no. 2, pp. 34–40, 2023. [4] A. Anbumozhi and S. A., “Leaf diseases identification and classification of self-collected dataset on groundnut crop using progressive CNN (PGCNN),” Int. J. AgriTech AI, vol. 7, pp. 98–104, 2023. [5] H. Kukadiya, D. Meva, N. Arora, and S. Srivastava, “Effective groundnut crop management by early prediction of leaf diseases through CNN,” Proc. DeepAgri Conf., pp. 88–94, 2023. [6] M. Aishwarya and P. Reddy, “Ensemble of CNN models for classification of groundnut plant leaf disease detection,” IEEE Access, vol. 11, pp. 78854–78862, 2023. [7] D. Sivaganesan, “Deep learning approaches for disease detection in groundnut crops using CNN models,” Int. J. Advanced Agricultural Intelligence, vol. 10, no. 4, pp. 210–215, 2023. [8] A. T. Madhavi, K. Rahimunnisa, and Karthik, “Impact analysis using transfer learning approaches for plant disease detection,” Computers in Agriculture, vol. 9, no. 1, pp. 32–38, 2023. [9] V. Ebenezer, E. B. Edwin, A. Anna, D. D. Thanka, and P. G. J. Lillipushp, “Classification and segmentation of leaf images based on deep learning for peanut plant disease,” J. Applied Deep Learning in AgriScience, vol. 5, no. 2, pp. 105–112, 2023. [10] K. Venkatesh and K. Naik, “Deep learning for macro-nutrient deficiency identification in groundnut plants,” Int. J. AI in Agriculture, vol. 6, no. 4, pp. 75–81, 2023.