AUTOMATED PLANT DISEASE DETECTION USING DEEP LEARNING

Abstract- Agricultural productivity is greatly affected by plant diseases, leading to significant economic losses worldwide. Early detection and proper diagnosis of plant diseases are critical for maintaining healthy crops and ensuring food security. Traditional disease detection methods rely on human expertise and manual inspection, which are labor-intensive and prone to errors. Automated plant disease detection using machine learning techniques provides a more efficient and accurate solution. This paper presents an approach that leverages image processing and deep learning algorithms to identify plant diseases from leaf images. The study compares the performance of VGG, Support Vector Machines (SVM), and Random Forest classifiers to determine the most effective model for disease classification. The proposed system utilizes advanced image preprocessing techniques, including noise removal and color normalization, to enhance model performance. The results indicate that the VGG model with transfer learning achieves superior accuracy compared to traditional machine learning models, making it an optimal choice for real-world applications. The proposed system provides real-time, cost-effective solutions for farmers, enabling them to detect diseases early and take preventive actions. Additionally, a mobile application is developed to allow farmers to capture and analyze plant images instantly, ensuring accessibility even in remote agricultural areas. By integrating artificial intelligence with precision agriculture, this research aims to minimize crop losses, enhance disease management, and contribute to sustainable farming practices. Future improvements include expanding the dataset, incorporating environmental parameters, and integrating real-time IoT-based monitoring for enhanced decision-making. Keywords— Plant Disease Detection, Machine Learning, Deep Learning, VGG, Image Processing, Agricultural Technology.