2. INTRODUCTION:
In India around 65% of the population is based on
agriculture.
Due to various seasonal conditions the crop get
infected by various kinds of disease.
Disease will firstly affect the leaf of the plant and then
infect the whole plant, since it is large number of leaf
in plants it is very difficult for the human eye to
identify the infected leaf.
3. OBJECTIVE:
The project presents plant disease detection using
image processing technique
For this approach, automatic classifier SVM will be
used for classification based on learning with some
training samples of that two category
The main objective is to identify the infected leaf by
compare and classify the feature in the database.
The main goal towards increasing the productivity of
crops in agriculture.
4. LITERATURE SURVEY:
S.NO JOURNAL AND
PUBLICATION YEAR
TITLE ALGORITHM USED OUTCOME
1 International journal of
cloud computing
[IEEE-2020]
Classification of plant
leaf diseases using
machine learning and
image pre-processing
techniques.
KNN and CNN Maximum accuracy of
98%
2
10th ICCCNT [IEEE-
2019]
Recognition of jute
diseases by leaf image
classification using CNN
CNN Provides an accuracy of
96%
3 1st International
Conference on Advances
in Science, Eng and
Robotics Technology
2019
Prediction of Potato
Disease from Leaves
using Deep Convolution
Neural Network towards
a Digital Agricultural
System
CNN and Deep learning Accuracy of 98.33%
4 International Journal of
Innovative Technology
and Exploring
Engineering (IJITEE)
Image processing and
classification a method
for plant disease
detecion
K means algorithm Accurateness of this
method is around 97%
5.
Springer-2018
Image processing based
rice plant leaves diseases
K means and support
vector machine(SVM)
This method provides
accuracy up to 98.63%
5. EXISTING SYSTEM:
•A very accurate artificial intelligence solution for detecting
and classifying different plant leaf disease is presented which
makes use of Convolution Neural Network for classification
purpose
CLASSIFIER ACCURACY (%)
KNN 54.5
SVM 53.4
CNN 98.0
6. • The infected leaf and disease leaf are identified
automatically by using SVM classification algorithm.
• Proposed system is divided into 3 steps
1.Dataset
2.Image Pre-processing
3.Selection of Classifier
PROPOSED SYSTEM:
8. RGB TO GRAYSCALE:
• A pixel color is an image is a combination of three colors Red,Green and
Blue(RGB).
• In this step images are resized to smaller pixel size in order to speed up the
computations.
9. EDGE DETECTION & FEATURE EXTRACTION:
• In edge detection, we find the boundaries or edges of
objects in an image
• Edge detection can be used to extract the structure of
objects in an image.
•From that result 3 features will be extracted,
1.Perimeter
2.Total area
3.Infected area
11. RESULT:
Healthy leaf:
The leaf is sufficiently healthy
Accuracy 70.086%
Infected leaf:
The leaf is infected
Accuracy: 70.068%
12. CONCLUSION & FUTURE WORK:
By using SVM algorithm, a very accurate solution for
detecting & classifying different a plant leaf diseases is
done.
In future, the proposed system extended to increase the
accuracy and the remedies for the classified disease can also
be included.
13. REFERENCES:
1. Al-Amin, Md.,TasfiaAnikaBushra, and NazmulHoq. Md. (2019) “Prediction of potato disease from leaves using deep convolution
neural network towards a digital agricultural system”, IEEE, 1st International Conference on Advances in Science, Engineering
and Robotics Technology
2. Anand. H.,Kulkarni, I. and AshwinPatil. R.K. (2012), “Applying image processing technique to detect plant
diseases”,International Journal of Modern Engineering Research (IJMER)
3. Gayathri Devi, T. and Neelamegam, P. (2019) “Image processing based rice plant leaves diseases
4. Kaur, S., Pandey, S. and Goel, S. (2018) “Plants Disease Identification and Classification Through Leaf Images: A
Survey”, Archives of Computational Methods in Engineering
5. Malini, S., and RathaJeyalakshmi, T. (2015) “Detection of Unhealthy Region of Plant Leaves Using Texture
Features”,International Journal of Computer Sciences and Engineering,
6. NeedaSamreen, Khan, I., Rajesh, and B.Pandhare, B. (2012) “A review on off-line leaf recognition using neural
network”,International Journal of Computer Science and Mobile Computing, Vol. 4, no. 1, pp. 478-482
7. PremRishi Kranth, M., HemaLalitha,LaharikaBasava,AnjaliMathur. (2018) “Plant Disease Prediction using Machine
Learning Algorithms”,International Journal of Computer Applications , Vol. 182, no. 25.
8. Pushkara Sharma,Pankaj Hans,Subhash Chand Gupta,”Classification of plant leaf disease using machine learning and
image preprocessing techniques”,IEEE 10th International Conference on Cloud Computing, Data Science &
Engineering (Confluence) 978-1-7281-2791-0/20/$31.00 #2020