Page 166 - Handbook of Deep Learning in Biomedical Engineering Techniques and Applications

P. 166

Plant leaf disease classification

based on feature selection and

deep neural network

Tan Pham, Son Dao
International University, Vietnam National University - Ho Chi Minh City,
Ho Chi Minh City, Vietnam

1. Introduction
The plant diseases pose a major threat to losses of agricultural
production. However, their rapid identiﬁcation remains as a
difﬁculty in many parts of the world due to the lack of the neces-
sary infrastructure. The spread of transboundary plant pests and
diseases has increased dramatically in recent years. Globaliza-
tion, trade, and climate change, as well as reduced resilience in
production systems due to decades of agricultural intensiﬁcation,
have all played a part. Transboundary plant pests and diseases
can easily spread to several countries and reach epidemic
proportions. Outbreaks and upsurges can cause huge losses to
crops and pastures, threatening the livelihoods of vulnerable
farmers and the food and nutrition security of millions at a time.
Traditionally, farmers use their eyes to detect diseases and
make decisions based on their experiences, which is often not
accurate and sometimes bias since in the early stage, some
diseases appear to be the same. Also, their experiences need to
be passed down generations by generations. Therefore, there is
a need for an accurate diseases detection and classiﬁcation
system associated with a reliable database to help farmers, espe-
cially the young and inexperienced ones to protect their crops.
Advances in computer vision pave the way for this with the
state-of-the-art deep learning (DL) or machine learning algo-
rithms. There is also a need for an early diseases detection system
to protect the crop in time.
There are many previous researches conducted for this pur-
pose. Most of them make use of the so-called “Plant Village”

161 162 163 164 165 166 167 168 169 170 171