Plant Leaf Disease Detection Using Deep Learning

Abstract

Agriculture is the backbone of food security and a primary source of income for many nations. However, plant diseases caused by fungi, bacteria, and viruses lead to significant crop losses, making early detection and timely treatment essential. In this project, we propose a leaf disease detection system that utilizes computer vision and deep learning (CNNs) to analyze plant leaf images and accurately identify diseases. Once detected, the system provides detailed disease information, recommended pesticides, and preventive measures. A unique feature of this system is its voice-enabled advisory service, where the AI automatically generates speech and calls the farmer in their local language to explain the disease status and suggest remedies. This approach ensures accessibility for farmers with limited literacy, while enabling quick, effective, and informed decision-making. By combining deep learning accuracy with AIpowered voice interaction, the system aims to reduce crop loss and enhance agricultural productivity.

Introduction

Agriculture is a vital sector for global food security and economic development, but crop productivity is heavily affected by plant diseases caused by fungi, bacteria, viruses, and environmental stress. Early detection is essential, yet traditional visual inspection methods are often inaccurate, time-consuming, and dependent on expert availability, especially in rural areas. To address this, the study proposes an AI-based plant leaf disease detection system using deep learning, particularly Convolutional Neural Networks (CNNs), which can automatically extract image features and classify diseases without manual feature engineering.

The system’s main motivation is the limitations of existing approaches, such as low accuracy, poor generalization to real-world field conditions, and inability to handle multiple disease types effectively. To overcome these issues, the proposed work introduces a dual-pipeline framework combining CNN-based image classification and YOLO-based object detection, along with additional features such as disease recommendations, multilingual voice-based advisory support, and weather-aware alerts using real-time API integration. The system is designed for practical agricultural use through containerized deployment using tools like Docker and Flask.

The dataset is built from sources like PlantVillage and Kaggle, expanded to over 12,000 images across 28 crop and disease classes. Since real-world agricultural images vary widely in lighting, background, and orientation, preprocessing steps such as resizing, normalization, augmentation, and noise handling are applied to improve model robustness. YOLO is used for detecting diseased regions, while classification is handled using lightweight models such as MobileNetV3 to support edge deployment.

Despite strong potential, real-world deployment faces challenges including environmental variability, poor generalization from lab datasets to field conditions, and hardware limitations in rural areas. Overall, the system aims to provide an accurate, scalable, and user-friendly solution for early plant disease detection and farmer decision support.

Conclusion

The Plant Leaf Disease Detection system has strong future potential. The system accurately detects plant leaf diseases using deep learning, providing fast and reliable classification [cite: 626-627]. By integrating MobileNetV3 for classification, YOLO for localization, OpenWeather for environmental context, and gTTS for audio accessibility, it serves as a costeffective and efficient solution for smart agriculture. With modern technologies such as mobile computing, IoT, cloud platforms, and advanced AI models, the system can become a powerful smart agriculture solution for farmers and researchers globally.

References

[1] S. P. Mohanty, D. P. Hughes, and M. Salathe´, “Using Deep Learning for Image-Based Plant Disease Detection,” Frontiers in Plant Science, vol. 7, p. 1419, 2016. [2] K. P. Ferentinos, “Deep Learning Models for Plant Disease Detection and Diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018. [3] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification,” Computational Intelligence and Neuroscience, 2016. [4] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A Comparative Study of Fine-Tuning Deep Learning Models for Plant Disease Identification,” Computers and Electronics in Agriculture, vol. 161, pp. 272–279, 2019. [5] A. Picon et al., “Deep Convolutional Neural Networks for Mobile Capture Device-Based Crop Disease Classification,” Computers and Electronics in Agriculture, vol. 161, pp. 280–290, 2019. [6] A. Kamilaris and F. X. Prenafeta-Boldu´, “Plant Diseases and Pests Detection Based on Deep Learning: A Review,” Plant Methods, vol. 17, no. 1, p. 22, 2021. [7] J. G. A. Barbedo, “Factors Influencing the Use of Deep Learning for Plant Disease Recognition,” Biosystems Engineering, vol. 172, pp. 84–91, 2018. [8] M. Brahimi, K. Boukhalfa, and A. Moussaoui, “Deep Learning for Tomato Diseases: Classification and Symptoms Visualization,” Applied Artificial Intelligence, vol. 31, no. 4, pp. 299–315, 2017. [9] P. P. Sharma et al., “Plant Leaf Disease Detection Using Transfer Learning and Convolutional Neural Networks,” International Journal of Advanced Science and Technology, vol. 29, no. 5, pp. 2020. [10] S. Ramesh, “Plant Disease Detection Using Machine Learning and Deep Learning Algorithms: A Review,” Archives of Computational Methods in Engineering, 2021. [11] Y. Lu, S. Yi, N. Zeng, Y. Liu, and Y. Zhang, “Identification of Rice Diseases Using Deep Convolutional Neural Networks,” Neurocomputing, vol. 267, pp. 378–384, 2017. [12] R. Mohanty et al., “Using Deep Learning for Plant Disease Detection: Advances and Challenges,” Artificial Intelligence in Agriculture, vol. 4, pp. 2020. [13] H. Durmus, E. O. Gunes, and M. Kirci, “Disease Detection on the Leaves of Tomato Plants by Using Deep Learning,” 6th International Conference on Agro-Geoinformatics, 2017.

Copyright

Copyright © 2026 Kandula Kasturi , Chintirala Sravanthi , Pondugala Sumanth Babu, Raavi Paleeswara Reddy , Mr. P. Yugandhar Reddy. 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.