Open AccessTomato leaf disease diagnosis based on improved convolutional neural network
Author(s) -
G Suganeshwari
Publication year - 2022
Publication title -
international journal of health sciences (ijhs) (en línea)
Language(s) - English
Resource type - Journals
eISSN - 2550-6978
pISSN - 2550-696X
DOI - 10.53730/ijhs.v6ns2.6346
Subject(s) - convolutional neural network , crop , yield (engineering) , metric (unit) , agriculture , artificial intelligence , microbiology and biotechnology , agricultural engineering , computer science , agronomy , biology , business , engineering , marketing , ecology , materials science , metallurgy
Tomatoes are one of the world's most important and tasty crops. This is a high-value crop, and the nation grows a lot of them. Every year, pests and diseases cause more metric tonnes of tomato crop loss in India. Tomato leaf disease is a severe issue that costs farmers a lot of money and threatens the entire agricultural business. As a result, it is critical to precisely diagnose and characterise these diseases. A variety of diseases impede tomato production. Early diagnosis of these diseases will reduce the disease's impact on tomato plants and increase crop yield. Various novel ways of recognising and categorising certain ailments have been widely used. The purpose of this research is to help farmers identify diseases in their early stages. The improved Convolutional Neural Network (CNN) is used to appropriately define and categorise tomato diseases. Kaggle is used to undertake the dataset study, which includes 18160 images of tomato leaves affected with nine distinct diseases and a healthy leaf. The following is a breakdown of the complete procedure: The collected images are first pre-processed. Second, the improved CNN model is used for image feature extraction and classification.