Authors :
Pradip Chougala; Dr. Rajashekharappa
Volume/Issue :
Volume 7 - 2022, Issue 10 - October
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3sRJCFN
DOI :
https://doi.org/10.5281/zenodo.7275321
Abstract :
Pest infestations have an impact on the nation's
agricultural output when they harm plants and crops.
Farmers or experts typically keep a close check on the
plants to spot any signs of disease. However, this
procedure is frequently time-consuming, expensive, and
unreliable. Results from automatic detection employing
image processing methods are quick and precise. This
study uses deep convolutional networks to establish a new
method for developing illness recognition models that is
supported by leaf image categorization. The field of
precision agriculture has a chance to grow and improve
the practise of precise plant protection as well as the
market for computer vision applications. A quick and
simple system implementation in practise is made possible
by a wholly original training methodology. The entire
process of putting this disease recognition model into
practise, from gathering photos to create a database to
having it reviewed by agricultural specialists and using a
deep learning framework to carry out the deep CNN
training, is comprehensively documented throughout the
research. With the help of a deep convolutional neural
network that has been trained and fine-tuned to
accurately match the database of plant leaves that was
compiled independently for various plant illnesses, the
technique paper presented here may represent a novel
way for identifying plant diseases. The innovation and
advancement of the developed model reside in its
simplicity; healthy leaves and backdrop images are
consistent with other classes, allowing the model to use
CNN to differentiate between ill and healthy leaves or
from the environment. On earth, food is produced by
plants. As a result, plant infections and diseases pose a
serious threat, and the most common method of diagnosis
is by looking for visible symptoms on the plant's body.
Diverse research projects intend to identify workable
methods for safeguarding plants as an alternative to the
customarily time-consuming practise. The development
of technology in recent years has led to the emergence of
several alternatives to laborious old procedures. Deep
learning methods are particularly effective at solving
picture classification issues.
Pest infestations have an impact on the nation's
agricultural output when they harm plants and crops.
Farmers or experts typically keep a close check on the
plants to spot any signs of disease. However, this
procedure is frequently time-consuming, expensive, and
unreliable. Results from automatic detection employing
image processing methods are quick and precise. This
study uses deep convolutional networks to establish a new
method for developing illness recognition models that is
supported by leaf image categorization. The field of
precision agriculture has a chance to grow and improve
the practise of precise plant protection as well as the
market for computer vision applications. A quick and
simple system implementation in practise is made possible
by a wholly original training methodology. The entire
process of putting this disease recognition model into
practise, from gathering photos to create a database to
having it reviewed by agricultural specialists and using a
deep learning framework to carry out the deep CNN
training, is comprehensively documented throughout the
research. With the help of a deep convolutional neural
network that has been trained and fine-tuned to
accurately match the database of plant leaves that was
compiled independently for various plant illnesses, the
technique paper presented here may represent a novel
way for identifying plant diseases. The innovation and
advancement of the developed model reside in its
simplicity; healthy leaves and backdrop images are
consistent with other classes, allowing the model to use
CNN to differentiate between ill and healthy leaves or
from the environment. On earth, food is produced by
plants. As a result, plant infections and diseases pose a
serious threat, and the most common method of diagnosis
is by looking for visible symptoms on the plant's body.
Diverse research projects intend to identify workable
methods for safeguarding plants as an alternative to the
customarily time-consuming practise. The development
of technology in recent years has led to the emergence of
several alternatives to laborious old procedures. Deep
learning methods are particularly effective at solving
picture classification issues.
