Development of Intelligent Pesticide Sprinkling System Determined by the Infection Level of a Plant (IOT based)

Abstract

This paper presents the development of an IoT-based intelligent pesticide sprinkling system for rice crops using image processing and machine learning techniques. The system aims to overcome the limitations of traditional pesticide spraying methods, which often result in excessive chemical usage, environmental pollution, and health risks to farmers. A camera module (ESP32-CAM) captures real-time images of rice leaves, which are processed using OpenCV and analyzed through a Convolutional Neural Network (CNN) model trained using TensorFlow. The model identifies common rice diseases such as bacterial leaf blight, brown spot, and leaf smut, and determines the infection severity. Based on the detection results, the ESP32 microcontroller activates a relay module that controls a DC pump to spray pesticides only on infected areas. The system also features an IoT-based dashboard for real-time monitoring, visualization, and remote operation. Experimental results demonstrate effective disease classification, with clear visualization using Grad-CAM and probability graphs. The proposed system reduces pesticide usage, minimizes human exposure to harmful chemicals, and enhances crop productivity. It provides a low-cost, efficient, and scalable solution for precision agriculture and smart farming applications.

Introduction

Diabetic Retinopathy (DR) is a diabetes-related eye disease that damages the retina’s blood vessels due to long-term high blood sugar, leading to vision impairment or blindness if not detected early. Traditional diagnosis relies on manual retinal examination, which is slow, subjective, and often inaccessible in rural areas. To overcome these limitations, AI-based systems—especially Convolutional Neural Networks (CNNs)—are being used for automated DR detection using retinal fundus images.

The detection pipeline includes image acquisition, preprocessing (noise removal, enhancement, normalization), segmentation of retinal structures, feature extraction, and classification into disease stages using machine learning or deep learning models. CNNs are particularly effective because they automatically learn complex features from images. The system is trained using labeled datasets and evaluated using metrics like accuracy, sensitivity, specificity, and AUC before deployment in clinical or mobile applications.

Research in this area shows a shift from traditional image processing to deep learning, transfer learning, and large-scale screening systems. Modern studies focus on improving accuracy, handling dataset imbalance, enabling lesion detection, and developing lightweight models for real-world deployment. However, challenges remain in generalization across datasets and clinical interpretability.

The methodology involves using datasets like Kaggle, Messidor, and DRIVE, applying preprocessing and augmentation, training deep learning models (such as CNNs, ResNet, VGG, EfficientNet), and deploying systems for real-time screening and decision support. Technologies used include Python, OpenCV, TensorFlow, PyTorch, GPUs, cloud platforms, and visualization tools.

Overall, the system aims to enable early, accurate, and scalable DR detection to support healthcare professionals and reduce preventable blindness through AI-assisted diagnosis.

Conclusion

The proposed IoT-based intelligent pesticide sprinkling system successfully demonstrates an effective approach for real-time rice leaf disease detection and automated pesticide application. By integrating image processing, deep learning, and IoT technologies, the system addresses the major limitations of traditional farming methods, such as excessive pesticide usage, delayed disease detection, and health risks to farmers. The use of a CNN model enables accurate identification of diseases like bacterial leaf blight, brown spot, and leaf smut, while the ESP32 microcontroller ensures seamless communication and control of the spraying mechanism. The system’s ability to activate the relay-controlled DC pump based on infection severity ensures precise and targeted pesticide application, significantly reducing chemical wastage and environmental impact. The AgroAI dashboard enhances usability by providing real-time monitoring, visualization, and control features. Experimental results confirm that the system performs efficiently with acceptable accuracy and response time, making it suitable for practical agricultural use. Overall, this project contributes to the advancement of precision agriculture by offering a low-cost, reliable, and scalable solution. It promotes sustainable farming practices and supports farmers in improving crop yield, reducing costs, and ensuring better crop health management.

References

[1] O. Debnath, S. Das, and R. Sen, “IoT-based intelligent farming using CNN for early brown spot detection,” Sustainable Computing: Informatics and Systems, vol. 35, pp. 100–110, 2022. [2] K. Kiratiratanapruk, S. Sinthupinyo, and C. Chaiyasith, “Automatic detection of rice disease using image tiling and convolutional neural networks,” Computer Vision Research, vol. 12, no. 3, pp. 145–156, 2022. [3] P. K. Rajani and M. Reddy, “Rice leaf disease detection using convolutional neural networks,” International Journal of Innovative Research in Computer Technology, vol. 11, no. 2, pp. 55–60, 2023. [4] P. Seelwal, A. Kumar, and S. Verma, “Hybrid deep learning approaches for rice disease recognition,” Frontiers in Computer Science, vol. 6, pp. 1–12, 2024. [5] K. Saddami and R. Patel, “Lightweight CNN models for rice leaf disease identification,” Computers and Electronics in Agriculture, vol. 215, pp. 107–115, 2024. [6] V. Pandiyaraju and R. Karthikeyan, “Channel attention hybrid CNN for paddy leaf disease detection,” IEEE Access, vol. 12, pp. 44567–44576, 2024. [7] P. Pai, S. Kulkarni, and R. Deshmukh, “Deep learning-based diagnosis of rice leaf diseases,” Scientific Reports, vol. 15, pp. 1–10, 2025. [8] K. Fang, Y. Liu, and J. Chen, “RLDD-YOLOv11n rice leaf disease detection model,” Agronomy, vol. 15, no. 6, pp. 1266–1278, 2025. [9] S. Sharma and V. Gupta, “CNN-based identification of rice leaf diseases,” International Journal of Scientific Research in Science and Technology, vol. 12, no. 1, pp. 210–216, 2025. [10] A. B. Ayyappan and M. Natarajan, “Rice plant disease detection using deep learning,” Journal of Plant Pathology Informatics, vol. 16, pp. 45–53, 2025. [11] R. Patel and S. Kumar, “Deep learning-based plant disease detection using image processing techniques,” Computers and Electronics in Agriculture, vol. 198, pp. 107012, 2022. [12] M. A. Hossain, M. R. Islam, and F. Ahmed, “IoT-enabled smart agriculture system for crop monitoring and disease detection,” IEEE Internet of Things Journal, vol. 9, no. 14, pp. 12145–12155, 2022. [13] L. Zhang, Y. Wang, and X. Li, “Real-time crop disease detection using lightweight CNN models for edge devices,” IEEE Access, vol. 10, pp. 87654–87665, 2022. [14] S. Verma and A. Singh, “Automated plant disease detection and classification using deep learning,” Procedia Computer Science, vol. 218, pp. 123–132, 2023. [15] J. Chen, H. Liu, and Q. Zhao, “YOLO-based real-time plant disease detection for precision agriculture,” Agricultural Systems, vol. 206, pp. 103560, 2023. [16] P. Gupta and R. Sharma, “IoT-based smart pesticide spraying system using image processing,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 5, pp. 455–462, 2023. [17] T. Nguyen and D. Tran, “Edge AI for crop disease detection using embedded systems,” IEEE Embedded Systems Letters, vol. 16, no. 2, pp. 45–48, 2024. [18] A. K. Mishra and S. Tiwari, “Precision agriculture using IoT and machine learning for crop health monitoring,” Sensors, vol. 24, no. 3, pp. 1456, 2024. [19] Y. Li, X. Zhou, and M. Sun, “Attention-based deep learning model for plant disease classification,” IEEE Transactions on Artificial Intelligence, vol. 5, no. 1, pp. 89–98, 2024. [20] H. Park and J. Kim, “Smart farming system integrating AI, IoT, and automation for sustainable agriculture,” IEEE Access, vol. 13, pp. 11234–11245, 2025.

Copyright

Copyright © 2026 Dr. Dilip Kapse, Vaishnavi Kothe, Payal Paunikar, Aditi Pande, Nidhi Dande, Runmai Falke. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.