Corn Leaf Disease Detection Using Convolutional Neural Networking (CNN)

Abstract

Plant diseases compose a great threat to global food security. However, it remains challenging for the small-scale farmers and others to identify the disease and is often time consuming. It often requires the advice from expert panels on classifying the diseased plant and healthy plant. Profound learning strategies have as of late been utilized to recognize and analyze unhealthy plants and users can themselves identify the disease category the plant is suffering from. In this project,we develop an application interfacefor a start to finish profound learning model to distinguish sound and undesirable corn plant leaves while thinking about the quantity of boundaries of the model. The proposed model uses two pre-prepared convolutional brain organizations (CNNs), EfficientNetB0 and DenseNet121, to extricate profound elements from the corn plant pictures. The profound elements extricated from each CNN are then combined utilizing the connection procedure to create a more perplexing structure which is then prepared and approved from pictures in the datasets. In this paper, information expansion methods were utilized to add varieties to the pictures in the dataset used to prepare the model, expanding the assortment and number of the pictures and empowering the model to learn more complicated instances of the information.