Authors :
S. Kavitha; Dr. K. Sarojini
Volume/Issue :
Volume 7 - 2022, Issue 3 - March
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3kcqNZx
DOI :
https://doi.org/10.5281/zenodo.6486739
Abstract :
Plant Diseases are one of the leading reasons
of economic shortfalls in agricultural and farming
sectors worldwide. It is the most essential element since
it reduces crop quantity and quality significantly. Fruits
are one of the largest essential nutritional resources
from plants. Unfortunately, a variety of conditions
might impair both the content and outcome of fruits. As
a result, an autonomous Computer Vision (CV) -based
approach for reliable Fruit Disease Detection (FDD) is
necessary. CV is an Artificial Intelligence (AI) area that
allows software and algorithms to extract relevant data
from digital images. Over the past decades, advanced
AI techniques such as Machine Learning (ML) and
Deep Learning (DL) algorithms have been developed to
predict and classify FDs early from different imaging
modalities. The findings observed from these techniques
can help farmers with FDD and treatment. This paper
presents a detailed review of different ML and DL
algorithms developed to predict and classify FDs from
different fruit images. First, different FDD and
classification systems designed by many researchers
based on ML and DL algorithms are studied in brief.
Then, a detailed analysis is carried out in order to
identify the shortcomings of existing algorithms and to
provide a novel strategy for properly classifying fruit
pathogens.
Plant Diseases are one of the leading reasons
of economic shortfalls in agricultural and farming
sectors worldwide. It is the most essential element since
it reduces crop quantity and quality significantly. Fruits
are one of the largest essential nutritional resources
from plants. Unfortunately, a variety of conditions
might impair both the content and outcome of fruits. As
a result, an autonomous Computer Vision (CV) -based
approach for reliable Fruit Disease Detection (FDD) is
necessary. CV is an Artificial Intelligence (AI) area that
allows software and algorithms to extract relevant data
from digital images. Over the past decades, advanced
AI techniques such as Machine Learning (ML) and
Deep Learning (DL) algorithms have been developed to
predict and classify FDs early from different imaging
modalities. The findings observed from these techniques
can help farmers with FDD and treatment. This paper
presents a detailed review of different ML and DL
algorithms developed to predict and classify FDs from
different fruit images. First, different FDD and
classification systems designed by many researchers
based on ML and DL algorithms are studied in brief.
Then, a detailed analysis is carried out in order to
identify the shortcomings of existing algorithms and to
provide a novel strategy for properly classifying fruit
pathogens.
