Page 228 - Handbook of Deep Learning in Biomedical Engineering Techniques and Applications

8

A review on plant diseases

recognition through deep

learning

R. Indrakumari, T. Poongodi, Supriya Khaitan,
Shrddha Sagar, B. Balamurugan
School of Computing Science and Technology, Galgotias University, Greater
Noida, Uttar Pradesh

1. Introduction

Farming is the basic source of food, fuel, and raw materials,
which is the backbone of the national economic development.
The exponential growth in the global population is making
farming to struggle to fill the necessity. The security of the food
remains challenging due to the crop diseases, pests, toxic patho-
gens, decline pollinators, climate change, irrigation problems,
and so on. Crop diseases lessen the food production and quality.
Food security for the earth population requires minimal crop
damage by a well-timed diagnosis of diseases. Some developing
countries are having poor knowledge about pest control and
management, which leads to food insecurity. Many advanced
technologies are available to fortify farming sustainability, to
minimize postharvest processing, and to increase the productiv-
ity. Laboratory-based techniques such as mass spectrometry, gas
chromatography, hyperspectral techniques, thermography, and
gas reaction are available for the disease diagnosis, but these
are time-consuming with more cost. In recent technological
advancements such as the Internet of things, artificial intelli-
gence, machine learning, and deep learning, it is now possible
to give an impactful solution to this problem. Among these areas,
deep learning is considered as the most accurate technology.
Advanced-level deep learning architecture is implemented along
with advanced visualization techniques to classify and find the

Handbook of Deep Learning in Biomedical Engineering. https://doi.org/10.1016/B978-0-12-823014-5.00009-0
Copyright © 2021 Elsevier Inc. All rights reserved. 219