IMAGE PROCESSING-DRIVEN DEEP LEARNING MODEL FOR PLANT DISEASE DETECTION TO ENHANCE IRRIGATION EFFICIENCY IN SMART AGRICULTURE

Abstract

In the era of smart agriculture, efficient irrigation management is crucial for optimizing crop yield and resource use. Traditional methods of plant disease detection often rely on manual inspection, which is time-consuming and prone to errors. Smart agriculture leverages technology to improve agricultural practices. Accurate and timely plant disease detection is vital for effective irrigation management and overall crop health. Current methods are limited by their manual nature and inability to process large volumes of data quickly. Manual plant disease detection is labor-intensive and may not provide timely information, leading to inefficient irrigation practices. This inefficiency can result in reduced crop yield and wasted resources. LeNet integrates advanced image processing techniques with a deep learning architecture tailored for plant disease detection. The model utilizes convolutional neural networks (CNNs) to analyze plant leaf images, identifying disease patterns with high precision. LeNet incorporates preprocessing steps such as image normalization and augmentation to enhance model robustness. The network is trained on a comprehensive dataset of plant disease images, employing transfer learning to leverage pre-trained weights for improved accuracy. Evaluation of LeNet on a test dataset comprising 10,000 images demonstrated an impressive accuracy of 92.5%, with a precision of 90.3% and recall of 94.1%. The model significantly outperforms traditional methods, reducing disease detection time by 60% and enhancing irrigation efficiency by 30%. The reduction in water usage and increased crop yield were observed in practical trials.