Professional Documents
Culture Documents
Identification of Disease in Potato Leaves Using Convolutional Neural Network (CNN) Algorithm
Identification of Disease in Potato Leaves Using Convolutional Neural Network (CNN) Algorithm
Abstract— Potato crops have many benefits for human enfermedad de las hojas de patata, a saber,
life, one of the most useful benefits of potatoes for
humans is the carbohydrate content in them and el tizón temprano causado por el hongo
carbohydrates are the main food for humans. The Alternia solani, y luego la enfermedad del
development of potato crop agriculture is very tizón tardío causada por el microbio
important for the sustainability of human life. There
are several obstacles in developing potato farming, phytopthora infestans de bary. Esta
including a disease that attacks potato leaves which if enfermedad tiene sus respectivos síntomas
left untreated will result in poor production or even
crop failure in the future. One of the obstacles in the
por lo que los agricultores pueden tomar
development of potato plants is the disease on potato precauciones si ven síntomas en las hojas
leaves, namely early blight caused by the fungus de papa, pero en este paso preventivo solo
Alternia solani, then late bligt disease caused by
Microbe phytopthora infestans de bary. This disease has lo pueden hacer expertos que tengan
its respective symptoms so that farmers can take conocimientos en el campo de las
precautions if they see symptoms on potato leaves, but
in this preventive step can only be done by experts who
enfermedades en las plantas de papa
have knowledge in the field of diseases in potato plants mientras que el agricultor promedio no
while the average farmer does not have sufficient tiene los suficientes conocimiento. Por lo
knowledge. So, the identification process becomes less
accurate and takes a long time. Technology in the field
tanto, el proceso de identificación se vuelve
of informatics in the form of digital image processing menos preciso y lleva mucho tiempo. La
can be used to solve problems in disease identification tecnología en el campo de la informática en
in potato leaves, so this research will propose the right
method for detecting disease in potato leaves. The forma de procesamiento digital de
identification process in this study uses three types of imágenes se puede utilizar para resolver
data in the form of healthy leaves, early blight, and late
blight. The method used to identify is deep learning
problemas en la identificación de
using the Convolutional Neural Network (CNN) enfermedades en hojas de papa, por lo que
architecture. The result of this research is that the esta investigación propondrá el método
70:30 data division produces better accuracy than the
80:20 data division. The accuracy obtained is 97% on
adecuado para detectar enfermedades en
training data and 92% on validation data using 20 hojas de papa. El proceso de identificación
batch sizes at 10 epochs. en este estudio utiliza tres tipos de datos en
Keywords—Potato diseases, late blight, early blight, forma de hojas sanas, tizón temprano y
identification, CNN tizón tardío. El método utilizado para
identificar es el aprendizaje profundo
Resumen— Los cultivos de papa tienen
utilizando la arquitectura de red neuronal
muchos beneficios para la vida humana, uno
convolucional (CNN). El resultado de esta
de los beneficios más útiles de las papas
investigación es que la división de datos
para los humanos es el contenido de
70:30 produce una mayor precisión que la
carbohidratos en ellos y los carbohidratos
división de datos 80:20. La precisión
son el alimento principal para los humanos.
obtenida es del 97 % en datos de
El desarrollo de la agricultura del cultivo de
entrenamiento y del 92 % en datos de
papa es muy importante para la
validación utilizando 20 tamaños de lote en
sustentabilidad de la vida humana. Existen
10 épocas.
varios obstáculos para desarrollar el cultivo
de la papa, incluida una enfermedad que I. INTRODUCTION
ataca las hojas de la papa y que, si no se Potato plants have many benefits for human life.
trata, dará como resultado una producción The main human need is carbohydrates and potatoes
are one of the foods that contain carbohydrates. But
deficiente o incluso la pérdida de la cosecha in the development of potato crops there are
en el futuro. Uno de los obstáculos en el obstacles that must be faced by farmers, this obstacle
desarrollo de las plantas de patata es la is in the form of potato leaf disease. If not treated
Authorized licensed use limited to: Carleton University. Downloaded on June 15,2021 at 12:07:06 UTC from IEEE Xplore. Restrictions apply.
2020 3rd International Conference on Information and Communications Technology (ICOIACT)
The most common A potato leaf disease called early blight has early
symptoms characterized by circular spots on the
middle of the leaves and it could also be on the edges
of the leaves as shown in Fig. 1 (a). Then these spots
will widen and the color of the leaves turns brown, the
fungus Alternia solani is the cause of this leaf disease.
Furthermore, Microbe Phytopthora infestans de Bary
is the main cause of potato leaf disease called late
blight, plant leaves affected by this disease can cause
plant damage. The Fig. 1 (b) shows a leaf with late
blight, marked by the appearance of black lesions on
the leaves and will continue to propagate [4].
(a) (b)
Fig. 1. Potato disease (a) early blight (b) late blight
This identification can help agricultural managers
to provide effective and efficient handling of plants
that are not healthy or abnormal. With the
development of technology today there have been
many digital image studies in agriculture both to
identify diseases or identify good agricultural
production. One of these digital image studies is to
identify leaf rot in potato plants.
This study aims to create a system that can help
farmers or agricultural managers in identifying
diseases in potato leaves by using data on potato leaf
images. The identification of leaves in potato plants is
divided into three parts, namely potato plants with
healthy leaves, late blight, and early blight. So in this
study will identify this using the Convolutional Neural
Network (CNN) architecture which is one of the Deep
Learning methods. The data used in the form of
Authorized licensed use limited to: Carleton University. Downloaded on June 15,2021 at 12:07:06 UTC from IEEE Xplore. Restrictions apply.
2020 3rd International Conference on Information and Communications Technology (ICOIACT)
Authorized licensed use limited to: Carleton University. Downloaded on June 15,2021 at 12:07:06 UTC from IEEE Xplore. Restrictions apply.
2020 3rd International Conference on Information and Communications Technology (ICOIACT)
Authorized licensed use limited to: Carleton University. Downloaded on June 15,2021 at 12:07:06 UTC from IEEE Xplore. Restrictions apply.
2020 3rd International Conference on Information and Communications Technology (ICOIACT)
Dataset Collection
Preprocessing Data
Classification
Evaluation
73
Authorized licensed use limited to: Carleton University. Downloaded on June 15,2021 at 12:07:06 UTC from IEEE Xplore. Restrictions apply.
2020 3rd International Conference on Information and Communications Technology (ICOIACT)
74
Authorized licensed use limited to: Carleton University. Downloaded on June 15,2021 at 12:07:06 UTC from IEEE Xplore. Restrictions apply.
2020 3rd International Conference on Information and Communications Technology (ICOIACT)
75
Authorized licensed use limited to: Carleton University. Downloaded on June 15,2021 at 12:07:06 UTC from IEEE Xplore. Restrictions apply.
2020 3rd International Conference on Information and Communications Technology (ICOIACT)
76
Authorized licensed use limited to: Carleton University. Downloaded on June 15,2021 at 12:07:06 UTC from IEEE Xplore. Restrictions apply.