AN INTELLIGENT APPROACH TO DETECT PLANT DISEASE

Date
2019
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
Vegetable and crop diseases are serious threat to food security for most of the agriculturally based country., but the identification is still very difficult specially in early stages. So, the idea of - fast, accurate and early detection of vegetable and crop’s pests and infectious disease can be used to minimize the food and economical losses. Indication of plant of vegetable diseases can be identified from leaves, where the evidence of a disease or infection can be found, using Convolutional Neural Network (CNN) techniques. We proposed a CNN model inspired by VGG19 model trained on 24,162 images of corn, potato and tomato leaves, that could detect 15 district categories of diseases excluding the healthy leaves. At the end, an accuracy of 96.70% was obtained on test dataset with our CNN architecture. The idea of identifying the phase of an infection or disease is predicted by observing the prediction for result as healthy plant or vegetable when the final prediction was infected vegetable.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN