DEPARTMENT OF ELECRTONICS AND

COMMUNICATION ENGINEERING

CHARACTERIZATION OF PLANT DISEASE

PREDUCTION USING CONVOLUTIONAL NEURAL
NETWORK
CHARACTERIZATION OF PLANT DISEASE PREDICTION
USING CONVOLUTIONAL NEURAL NETWORK

 Project Guide Project Team

 Ms M.MEENAA KUMARI A.SUNEEL(U17EC369)

 ASSISTANT PROFESSOR K.SOMA SEKHAR(U17EC357)
 ECE ,BIHER M.HUSSAIN BASHA(U17EC358)
Abstract
 Due to various seasonal condition crops get affected by various kind of diseases .
 The plant disease detection can be done by observing spot of the leaf of the affected
plant.
 The method we are adopting to detect the plant leaf disease using image
processing,using convolution neural network.
 The django base web application, we used traine convolution neural network to identify
disease present in leaf it consist of 41 classes of different healthy and diseased plant
leaves.
 In this paper we are introducing the artificial intelligence based on plant leaf detection .
 In this approach we have follow several steps i.e, image collection ,image processing
,segmentation and classification .
 The result turned back to the user via python programming .
Introduction
 Traditionally identification of plant disease has relied on human annotation by visual
 
inspection and the agriculture production cost can be significantly increased.
 Plant disease has long been on of the major threats to food security because it dramatically
reduces the crop yield and quantity of the crop.
 Hence in order to solve this problem we have developed the artificial intelligence based
solution and the speed are the to main factor that will decide success of the automatic plant
leaf disease detection and classification model.
 The model is mainly divided into four steps or phases in first one we collectin
 These are all images will be color images ,in second step noise from the image is removed
then we will create a color transformation structure of the image .
 In third step we segment image using clustering techniques also available .
 In final step deep learning and machine learning algorithms that logistic regression ,KNN,
SVM, and CNN are trained to compare and bases of accuracy and the algorithm that performs
best training as well as testing is take in a count .
Literature survey
 Paper by Saradhambal.G, Dhivya.R, Latha.S, R. Rajesh give
solution to the plant disease with image classification.

 In their approach they collect 75 images of different diseased

plant leaves such as Bacterial Blight and more.
 There were total of 5 classes that include 4 disease classes
and one normal healthy leaf class. Removal of noise is done
with some image preprocessing and then conversion into lab
color model was done.
 They segmented the image with clustering and Otsu’s method.
After that some feature extraction is done on the basis of
which class is determined.
 They have not discussed the accuracy that they have achieved
as well as dataset was small .
Literature survey
 Paper named “Plant Leaf Disease Detection and Classification
Based on CNN with LVQ Algorithm” clarifies that they have
used CNN model for the leaf disease classification.
 In their methodology they have used a dataset of 500
images divided into 400 training and remaining 100 testing.
 Total classes for classification were 5 including one healthy
class as well. Images size used was quite well that is
512*512.
 Three matrixes for R, G, B channels were used as input to
CNN model and the output was feed into neural network
known as LVQ (Learning Vector Quantization).
 Their proposed model was only for tomato related diseases
Literature survey
 Plant Disease Classification Using Image Segmentation and
SVM Techniques” by K. Elangovan, S. Nalini uses the SVM for
the classification purpose.
 In their methodology image was converted into another color
space.
 After that image was cropped and with image preprocessing
techniques noise was removed and smoothening was done
and converted into grey scale images.
 Segmentation was also performed and then features were
extracted. They considered color, morphology and texture as
features and they were used for classification.
 They also doe not mention about the accuracy of their
suggested model
Existing system
 In developing countries, farming land can be
much larger and farmers cannot observe each
and every plant, every day. Farmers are unaware
of non-native diseases. Consultation of experts
for this might be time consuming & costly.
 Also unnecessary use of pesticides might be
dangerous for natural resources such as water,
soil, air, food chain etc. as well as it is expected
that there need to be less contamination of food
products with pesticides
Disadvantages
 Farmers cannot afford so much money for
persons who visit the crop for disease
prediction.
 Speed and accuracy of getting result is

delayed.
 As the cultivational fields are quite large and

have very large number of plants in that,

hence it becomes very difficult for the human
eye to properly detect and classify each and
every plant.
Proposed System
 We proposed a model to detect and classify
the infected plant leaves consists of 4 phases.
The phases are
 Dataset Collection
 Image Preprocessing
 Segmentation
 Selection of Classifier
Advantages
 Farmer can predict the diseases so that can
use the right cultivation and fertilizers
method. So that they can improve the product
quality and crop yield prediction.
 Based on our proposed system we achieved

the best model for prediction of diseases in

variety of crops.
System requirements
Software requirements
 Python programming language
 Visual studio code editor
 Django framework for web application

Hardware requirements
 Hard disk: 1Tb
 Ram : 4GB
 Processor: intel13
 GPU : 2GB
Block diagram
Project explanation
 In this project we collected data's of various
crops.
 The data’s undergoes different process to

identify the defects in it.

• data collection
Image processing

 In this step images are resized to smaller

pixel size in order to speed up the
computation.
 The noise is removed using some filter

technique like gaussain blur.

 After the images are present in RGB format

which is not appropriate for further work as

RGB format does not separate image
instantly.
Project explanation
 It is connected to another colour space that
is HSV which separates image instantly
segmentation

 In this step ,segmentation of image is done in

order to separate the leaves from the background.
 segmentation is performed using k-means

clustering with 2 cluster center.

 Segmentation process is dividing image in to

small segments to identify the disease.

 Image after k-means clustering
segmentation
Selection of Classifier
 This is the classification problem as we have
to classify the type of disease on the leaf of
the plant. So, we have plenty of machine
learning as well as deep learning algorithms
that we can apply on this dataset.
python
Python is an interpreted high-level
programming language for general-purpose programming.
In python, OpenCV is to be installed.
‘Open source computer vision library' initiated some enthusiast

coders in ‘ 1999' to incorporate Image

Processing into a wide variety of coding languages. It has C++, C

and Python interfaces running on Windows, Linux, Android, and

Mac.
 It is one of the Libraries used for the image processing in python.

On python web framework by using: leaf Identification algorithm it

detects and identifies the Leaf and diseases. By using Database it
sends the result back to the sender farmer
Python server connecting data from data base
Image captured from data base
OUTPUT
OUTPUT
Result
 Data base collected from different websites
 Captured image is uploaded to the python server
with the help of visual studio code
 Image undergoes various image processing
algorithum to determine the disease
 The determined disease is sent to the interface to
show the output
 Paddy accuracy

Table: accuracy of two diseases

Disease Name TR FR

Accuracy

Leaf blight 40 2 95

Leaf smut 40 3 92.5

Disease Name TR FR Accuracy(%)

Black root 20 3 85

Rust 25 2 92

Bar grapg result accuracy

 Tamato Accuracy
Table shows Accuracy of two diseases
Disease name TR FR Accuracy
Bacterial spot 20 1 95
Early blight 20 0 100

Bar graph result accuracy

Potato Accuracy
Table shows accuracy of two diseases

Disease name TR FR Accuracy

healthy 25 1 95
Late blight 20 0 100

Bar graph result accuracy

 Corn Accuracy
Table shows accuracy of two diseases

Disease name TR FR Accuracy

Common rust 20 1 95

Leaf blight 20 0 100

Bar graph Result Accuracy

Conclusion
 In this paper, gives accurate artificial intelligence
solution for detecting and classifying different plant
leaf disease is presented which makes use of
convolutional neural network for classification
purpose . The presented model used the dataset
that consists of more than 20,000 images with 41
total classes . The following model can be extended
by using even more large dataset with more
categories of diseases and the accuracy can also be
improved by tuning the hyper parameters . The
remedies for the classified disease can also be
included in the model.
References
 [1] “Plant Disease Detection And Its Solution Using image Classification” by
Saradhambal.G, Dhivya.R, Latha.S, R.Rajesh in International Journal of Pure
and Applied Mathematics Vol. 11 ,no.14, pp. 879- 884, 2018
 [2] “Plant Leaf Disease Detection an Classification Based on CNN with LVQ
Algorithm” by Melik Sardogan, Adem Tuncer, Yunus Ozen in 3r International
Conference on Computer Scienc and Engineering, 2018
 [3] “Plant Disease Classification Using Image Segmentation and SVM
Techniques” by K.Elangovan, S.Nalini in International Journal of
Computational Intelligence Research ISSN 0973-1873 Vol.13 ,no.7, pp.-
1821-1828, 2017
 [4] Rajneet Kaur , Manjeet Kaur “A Brief Review on Plant Disease Detection
using Image Processing” IJCSMC, Vol. 6, Issue 2, 2017
 [5] SandeshRaut, AmitFulsunge “Plant Disease Detection in Image Processing
Using MATLAB” IJIRSET Vol. 6, Issue 6 , 2017
 [6] Sonal P Patel, Mr. Arun Kumar Dewangan “A Comparative Study on Various
Plant Leaf Diseases Detection and Classification” (IJSRET), ISSN 2278-08882
Vol. 6 , Issue 3, March 2017
 THANK Q