Improving Agricultural Productivity with CNN-Based Plant Disease Recognition System

The world’s agricultural production is at risk due to the significant economic losses and concerns about food security that have resulted from an increase in plant maladies. Traditional methods of disease detection are labor-intensive and susceptible to human error. This research aims to enhance agricultural productivity by introducing a novel method of detecting plant diseases that is based on Convolutional Neural Networks (CNNs). The objective is to facilitate the rapid and precise diagnosis of illnesses using leaf images. The proposed method employs state-of-the-art convolutional neural network (CNN) designs that have been optimized for accuracy, speed, and minimal computational cost. Consequently, they are well-suited for real-time implementation in a variety of agricultural environments. The system’s capacity to accurately identify various plant diseases in various crop types is illustrated by the testing results, which indicate that it could be a valuable addition to contemporary farming. This convolutional neural network (CNN) technology enables early intervention, which significantly reduces crop losses and improves agricultural production, thereby offering a scalable solution to the global food security problem. The model performed accuracy of 92.5 %.