Lychee Leaves Disease Detection

Abstract

The leaf maybe named most important part of a plant. If the leaf gets concerned by few disease it impacts the whole plant. To catch a excellent product, the quality of the leaf must be guaranteed. To ensure the quality of the leaf, early disease detection of the leaf is very effectual. Lychee is one of most profitable fruits in Bangladesh. Occurring in addition to 47,500 metric ton of Lychee is convinced in Bangladesh. The growth of the fruit is affected by several diseases. Most concerning this disease will show signs on the leaf of the plant. In this place paper, I have used two Convolutional Neural Network (CNN) architectures VGG16 and VGG19 that is a Deep Learning algorithm to classify Lychee leaf diseases. Further, a primary CNN model (3 convolution layers, 3 maxpooling layers, and 2 dense layers) is used to compare compare both structures. The aim concerning this paper search out find out that which architecture acts better to recognize Lychee leaf disease. Here, VGG16 gives 90% accuracy, VGG19 gives 88% accuracy and the fundamental CNN model gives 82% accuracy accompanying dataset containing 1655 leaf concepts. This thesis maybe used to discover early lychee leaf disease and prevent result misfortunes.