Improving the efficiency of Plant-Leaf Disease detection using Convolutional Neural Network optimizer-Adam Algorithm

Abstract

Crop diseases should be diagnosed and treated as early as possible in order to improve yield. With the growing demand for food, safe and diverse food to support a prosperous population and improve living standards, the management of plant diseases faces growing challenges. It has emerged the major problem in recent times. With the help of different technological implementations, many preventive measures are taken as detection and classification based on algorithms such as support vector machines and linear discriminant analysis, detection using image processing, recognition using pesticides etc. Since Convolutional neural networks (CNNs) have shown to be effective in the field of machine learning, (CNN) Adam optimization model is being used in this paper to detect and determine illnesses in plants based on their leaves The performance of the models was evaluated using various factors such as batch size, dropout, and the number of epochs. The accuracy of implemented model is 96.77% which is higher than the accuracy achieved from other models like SVM (Support Vector Machine) and basic CNN.