1

RESEARCH PAPERS

Grape Leaf Disease Identification using Machine

Learning

Mr.G.Samrat Krishna Ch.Vinay Kumar Sk.Ameer Sohel

Assistant Professor
Department of Computer Science
samratkrishnagaddam@gmail.com
P.B.Siddhartha College of Arts &
Science,Vijayawada,Andhrapradesh
MCA Student MCA Student
vinaykumarchokkapu78@gmail.com sohelameer73148@gmail.com
P.B.Siddhartha College of Arts & P.B.Siddhartha College of Arts &
Science,Vijayawada,Andharapradesh Science,Vijayawada,Andhrapradesh

ABSTRACT : The Indian economy heavily relies on the agricultural productivity of the nation. Grapes are a highly profitable fruit in
India and can be cultivated in various climatic regions, including tropical, sub-tropical, and temperate zones. India's diverse geography,
encompassing different climates and soil types, underscores the significant socio-economic importance of grape cultivation. However,
grapevines are susceptible to diseases caused by viruses, bacteria, fungi, insects, rust, nematodes, and more. These diseases can adversely
affect crop yield and growth. Traditionally, farmers rely on their experience or consult experts for disease identification through visual
inspection, a process that is both inaccurate and time-consuming. Therefore, there is a pressing need in the agricultural and horticultural
sectors for early disease detection to enhance crop yields. Our proposed system aims to address this need by detecting and identifying
diseases in grape plant leaves.

INTRODUCTION

The Indian economy heavily relies on the agricultural productivity within the nation. Grapes hold significant commercial value in India
and can thrive in various climatic zones, including tropical, sub-tropical, and temperate regions. India's diverse geographical landscape
results in varying climates and soil types across the country, rendering grapevines a major crop propagated through vegetative means,
carrying substantial socioeconomic importance. However, the grape plant's susceptibility to diseases can lead to reduced yields and
hindered growth. These diseases, caused by viruses, bacteria, fungi, and transmitted by insects, rust, nematodes, and more, are traditionally
assessed by farmers based on their experience or with the assistance of experts through visual inspection. This manual observation process
is both time-consuming and prone to inaccuracies. Hence, there is a pressing need for early disease detection in agriculture and horticulture
to bolster crop yields. We have introduced a system designed to detect and identify diseases in grape plant leaves.

MOTIVATION

Prior endeavors have proposed web-enabled disease detection systems [8]. One such system introduced a segmentation method employing
a mean-based approach for threshold computation. Textual features were extracted, and classification was performed using Support Vector
Machines (SVM). In a comprehensive survey by Vijai et al. [12], various disease classification techniques for plant leaf diseases were
explored, accompanied by the use of genetic algorithms for image segmentation. Additionally, an integrated methodology combining
particle swarm optimization and SVM was presented for the detection and classification of plant leaf diseases [10].
Existing System

The existing system featured a segmentation technique that relied on a mean-based approach for threshold computation. Textual features
were extracted, and classification was carried out through SVM. Vijai et al.'s survey delved into diverse disease classification techniques
for plant leaf diseases and incorporated genetic algorithms for image segmentation. Furthermore, an integrated approach merging particle
swarm optimization and SVM was proposed for the detection and classification of plant leaf diseases.

IDENTIFY, RESEARCH AND COLLECT IDEA

To Identify the grape leaf disease first we can check the leaf of the grape branch and The spots of black rot are nearly round with
a dark brown middle and brown edges. The yellow-green disease spots gradually appear on the fronts of the grape leaves with downy
mildew, and white frosty mildew appears on the backs of the leaves. Leaf blight produces dark brown patches on the surface of grape
leaves .and Collect the few leaf and check it how they are.

Research On Grape Leaf Disease Identification https://pbsiddhartha.ac.in/

 2
RESEARCH PAPERS

WRITE DOWN YOUR STUDIES AND FINDINGS

We have evaluated the proposed system using 5675 grape leaves which have been downloaded from the plant village website and also
from web. We have used 80% of the images for training and others for testing.The global thresholding method used for segmenting leaf
disease part was found to be more suitable for training the model as it segments the precise diseased part of the leaves which leads to
improved classification results. Training accuracy obtained using different machine learning techniques are summarized in Table. From
the results it is evident that good training accuracy is achieved when the features are extracted from the diseased part of the images using
global thresholding and trained using SVM classifier with tuned parameters since SVM performs good when the data is highly non-linear.
The overall accuracy obtained is 93.035% for 1135 test images

Research On Grape Leaf Disease Identification https://pbsiddhartha.ac.in/

 3
RESEARCH PAPERS

Use of Simulation software

The System is developed with the Python, Machine Learning, Flask frameworks and some Machine Learning Algorithms i.e.,
Random forest Algorithm, K-Means Algorithm, and some detection Algorithms to detecting the spam the process of Algorithms working
process is given below
Random forest algorithm which is used to classification, in this paper we are going to identify the undisease firstly we have to
categorized the undisease after that we are going to identify the undisease.

REVIEW
Here comes the most crucial step for your research publication. Ensure the drafted journal is critically reviewed by your peers
or any subject matter experts. Always try to get maximum review comments even if you are well confident about your paper.

MATERIAL & METHODS

In order to develop accurate image classifiers to diagnose plant diseases, a large verified data set of images of diseased and
healthy plants is required. Until very recently, such a dataset did not exist, and even smaller datasets were not freely available. So,
researchers had to create datasets by themselves. In this study, the Plant Village dataset, as a freely-available dataset, was used. The
present study involved three types of plant diseases in addition to healthy leaves, which made four classes in total .

Research On Grape Leaf Disease Identification https://pbsiddhartha.ac.in/


RESEARCH PAPERS
RESULT
We can easily identify the Grape leaf disease by using this
source of the data. The Diseased leaves to come black dots on
that leaf then we can conform it is caused grape leaf disease.
Another leaves are safe remaining leaves are the undiseased
leaves. And also we have some techniques to identify the
disease by using machine learnings algorithms. We can upload
the leaf image. Then the machine learning algorithms can test
the image what we are trained they can perform on this time.
They can Show Accuracy result.
Support Vector Machine
Research On Grape Leaf Disease Identification
4
Logistic regression
Logistic regression is named for the function used at the core
of the method, the logistic function.
Where e is the base of the natural logarithms (Euler’s number
or the EXP() function in your spreadsheet) and value is the
actual numerical value that you want to transform. Below is a
plot of the numbers between -5 and 5 transformed into the range
0 and 1 using the logistic function.
https://pbsiddhartha.ac.in/

RESEARCH PAPERS
 Project Development Modules:
 Modules
 Upload data
 Reading Data
 The train_test_split()
 All Classifiers
 Model Comparison
 Predict
Upload Data:-Uploading refers to transmitting
data from one computer system to another
through means of a network. Common methods
of uploading include: uploading via web
browsers, FTP clients], and terminals
(SCP/SFTP). Uploading can be used in the
context of (potentially many) clients that send
files to a central server.
Reading Data:-is an action performed by
computers, to acquire data from a source and
place it into their volatile memory for processing.
Computers may read information from a variety
of sources.
The train_test_split():- method is used to split
our data into train and test sets. First, we need to
divide our data into features (X) and labels (y).
The dataframe gets divided into X_train, X_test,
y_train, and y_test. X_train and y_train sets are
used for training and fitting the model. You can
use train_test_split() to solve classification
problems the same way you do for regression
analysis. In machine learning, classification
problems involve training a model to apply labels
to, or classify, the input values and sort your
dataset into categories
All Classifiers:-
Naive Bayes:- Naïve Bayes classifiers. The
Naïve Bayes classifier is a supervised machine
learning algorithm, which is used for
classification tasks, like text classification
Decision Tree:- Decision trees are a rule-based
approach to classification and regression
problems. They use the values in each feature to
split the dataset to a point where all data points
that have the same class are grouped together
Logistic Regression:- Logistic regression is a
supervised learning classification algorithm used
1. Data Collection:Collect sufficient data samples
and legitimate software samples.
Research On Grape Leaf Disease Identification
5
to predict the probability of a target variable. The
nature of target or dependent variable is
dichotomous, which means there would be only
two possible classes.
K-Nearest Neighbor:- The k-nearest neighbors
algorithm, also known as KNN or k-NN, is a
non-parametric,
supervised learning classifier, which uses
proximity to make classifications or predictions
about the rouping of an individual data point.
Artificial Neural Networks/Deep Learning:-
An Artificial Neural Network (ANN) is a
machine learning model inspired by the human
brain's neural structure. It comprises
interconnected nodes (neurons) organized
into layers. Data flows through these nodes,
adjusting the weights of connections to learn
patterns and make predictions.
Support Vector Machine:- Classification
algorithms are particularly common in machine
learning because they map input data into
predefinedClassification algorithms are
particularly common in machine learning
because they map input data into predefined
categories, making the process easier for the user.
They analyze data automatically, simplify
operations, and obtain useful information.
categories, making the process easier
for the user. They analyze data automatically,
simplify operations, and obtain useful
information
Model Comparision:-Multiple model
comparison is also called Cross Model
Validation. Here the model refers to completely
different algorithms. The idea is to use multiple
models constructed from the same training
dataset and validated using the same verification
dataset to find out the performance of the
different models.
Predict:- the output of an algorithm that has been
trained on a historical dataset. The algorithm then
generates probable values for unknown variables
in each record of the new data. The Predict can
do the prediction of the data it shows the
predictable data.
2. Feature Extraction:For each image extract the
features ubsing image processing and save in ‘.csv’
extension
https://pbsiddhartha.ac.in/
 6
RESEARCH PAPERS
3. Train and Test Modelling: Split the data into
train and test data Train will be used for
trainging the model and Test data to check the
performace
4. Modelling: SVM Navie bayes, Random
FOrest,KNN,Ada boost, Decision tree, Ada boost
with randomforest . Combine the training using
machine learning algorithms and establish a
classification model.
5. Execution Steps:
1. Open anaconda Prompt
2. Conda activate tf
3. Goto Project Directory 7. Import the data and Preprocess
4. Python featureextract.py
5. Python final.py

Upload the data and read the basic data

information will be shown on the screen

Above screen will be opened. 8. Now click on “Train and Test model”. split
the data into train and test and traain will
6. Now click on “Upload data be used for training and to tets the
performace we are using test data

Research On Grape Leaf Disease Identification https://pbsiddhartha.ac.in/

 7
RESEARCH PAPERS

10. Accuracy Comparision for all the models

9. Now click on “Run Algorithms”.
Mentioned algorithms will be run on the data

11. Predict:

Research On Grape Leaf Disease Identification https://pbsiddhartha.ac.in/


RESEARCH PAPERS
Extension Bagging algorithm is performed
well compared other ml algortithms
Research On Grape Leaf Disease Identification
8
In this leaf disease prediction The Random
forest algorithm performs the highest
accuracy result of leaf disease. Random forest
is a commonly-used machine learning
algorithm trademarked by Leo Breiman and
Adele Cutler, which combines the output of
multiple decision trees to reach a single
result. Its ease of use and flexibility have
fueled its adoption, as it handles both
classification and regression problems
https://pbsiddhartha.ac.in/
 RESEARCH PAPER

CONCLUSION
In this project, we performed a review of techniques used for detecting spammers on Twitter. In addition,
we also presented a taxonomy of Twitter spam detection approaches and categorized them as fake content
detection, URL based spam detection, spam detection in trending topics, and fake user detection techniques. We
also compared the presented techniques based on several features, such as user features, content features, graph
features, structure features, and time features. Moreover, the techniques were also compared in terms of their
specified goals and datasets used. It is anticipated that the presented review will help researchers find the
information on state-of-the-art Twitter spam detection techniques in a consolidated form.

ACKNOWLEDGMENT
We are extremely thankful to our project guide G. Samrat Krishna Assistant Professor, Department of
Computer Science, PB Siddhartha College of Arts & Science, Krishna University, Machilipatnam for his timely
cooperation and valuable suggestions throughout the project. We are indebted to her for the opportunity given
to work under her guidance. We are extremely thankful to Dr. T. S. Ravi Kiran, Head of the Computer Science
Department and Dean Rajesh C. Jampala, PB Siddhartha College Of Arts &Science, Vijayawada for providing
good environment and better infrastructure facilities. My sincere thanks to all the teaching and non-teaching staff
of Department of Computer Applications for their support throughout my project work. Finally, I am very much
indebted to my family for their moral support and encouragement to achieve higher goals

REFERENCES

[1] Agrawal, G.H., Galande, S.G., Londhe, S.R.: Leaf disease detection and climatic parameter monitoring of plants using iot 4, 9927 –
9932 (2015)
[2] Al- hiary, H., Bani-ahmad, S., Reyalat, M., Braik, M., Alrahamneh, Z.: Fast and accurate detection and classification of plant
diseases. International Journal of Computer Applications 17(1) (2011)
[3] G.Prem Rishi Kranth, Hema Lalitha, Laharika Basava, Anjali Mathurh : Plant disease prediction using machine learning algorithms.
International Journal of Computer Applications 18(2) (2018)
[4] H.Sabrol, K.Satish: Tomato plant disease classification in digital images using classification tree. In: 2016 International Conference
on Communication and Signal Processing (ICCSP), pp. 1242–1246 (2016)
[5] Khot.S.T, Supriya, P., Gitanjali, M., Vidya, L.: Pomegranate disease detection using image processing techniques 5(1), 2248 –
2251 (2016) .

GRAPE LEAF DISEASE IDENTIFICATION BY USING MACHINE LEARNING

TECHNIQUES