International Journal of Recent Technology and Engineering (IJRTE)

ISSN: 2277-3878, Volume-8, Issue-1, May 2019

Plant Health Monitoring System Through Image

Processing and Defects Overcoming Through
Embedded System
K.Anitha, G.Keerthiga, A. Hema Malini

ABSTRACT: Agriculture is the back bone of the world Economy,

75% of countries depends on agriculture. Farmers have different II. LITERATURE SURVEY
type of multiformity for selecting various suitable crops and
Multiple numbers of methods are used by researchers and
finding the relevant pesticides for plant. Affected plants drive to
analysed the dieses of the plants. Raghottam Ramesh
the heavy decrement in both the quality and quantity of
proposed a method “Plant Leaf Disease Management
agricultural profits. Monitoring the condition of the plant plays
System” to detect all possible lemon leaf diseases. The
an important role in successful cultivation of crops in farming. concept of this project is to identify the disease of the plant
In ancient days, the observation and analysis process of plant leaves and obtain solution to that disease. Image processing
growth and diseases detection were done through manually by techniques are used to identify and arrange the plant leaf
the expertise person. But it needs tremendous amount of manual diseases. With the help of these methods, the plant diseases
work and also requires huge processing time. With the help of can be indentified in the beginning stage itself. The
modern technology image processing methods can be involved in techniques used for identification are K-Means cluster,
the plant disease detection. In large number of cases affected GLCM, and Neural Network Classifiers.
symptoms were detected on the leaves, stem and fruits of the These methods are helped to detect the growth and heath
plant. In this paper we are proposing an algorithm for detecting level of the leaves. Vijai Singh proposed an algorithm based
the dieses and depending upon the types of the diseases, the on image segmentation “Detection of unhealthy region of
respective medicine can be given to the crops through an plant leaves using Image Processing and Genetic
automated prototype. Algorithm” used for automatic identification and
classification of plant leaf disease. Image segmentation, is a
Key words: cultivation, soil analysis, growth, health and disease significant method for disease identification in plants and
it’s done by using genetic algorithm.
I. INTRODUCTION
III. FRAMEWORK
Monitoring the farm of plants requires a lot of attention
regarding seeding, plant growth and maintaining the soil A) Image acquisition:
moisture etc. This requires a lot of human effects. Especially It is a digital encoding process of a visual object. Images
due to the time of plant growth tracking the health of the play an important role in day today life of a human. Based
plants is the most important thing. Plant disease on our requirements the images can be obtained by using
management is the most essential work in farming. The different kind of device like cameras and sensors, and then it
research about the plant disease refers to the studies of can be processed by various techniques like sampling and
visually observable patterns on the plants. quantisation for digital encoded representation
Plant disease types are varied based on so many factors like B) Image segmentation:
climatic changes, ground soil and insects disturbance. In Segmentation is the method of splitting the pictures in terms
today’s agriculture indentifying the plant disease nature is of various parts based on different type’s image analysis
the very hard and challenging task. Generally plant dieses techniques, like edge and texture regional thresholding. The
identification was done manually. segmentation process of the plant is carried out by splitting
Human visual system can detect the external disturbances of the colour pixel of the plant and compared the affected part
the plant but most of the diseases are caused by virus and of the plant with encoded image based on the size and leaf
bacteria. This can be identified by image processing. colour texture. Depends on the outcome of the analysis the
dieses range will be identified.
C) Image analysis:

Images of the plant and roots can be analysis by various

techniques. Image analysis requires extraction of particular
features that aid in the identification of the object. The
Images obtained might be of different forms and of various
dimensions, hence the images are pre processed and brought
to same dimension, removes noise, background and reduces
Revised Manuscript Received on May 18, 2019 unwanted distortions.
Ms. K.Anitha, Faculty of Electronics and Communication
Engineering, Saveetha Engineering College, Chennai, India
Ms. G.Keerthiga, Faculty of Electronics and Communication
Engineering, Saveetha Engineering College, Chennai, India
Ms. A. Hema Malini, Faculty of Electronics and Communication
Engineering, Saveetha Engineering College, Chennai, India

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number A3394058119/19©BEIESP 406 & Sciences Publication
Plant Health Monitoring System through Image Processing and Defects Overcoming Through Embedded
System

Fig 3: Plant Health monitor

clc;clear all;
Fig1. Flow chart close all;
workspace;
IV. PROPOSED SYSTEM [Path,U_C]=imgetfile;
In this project we are focusing to identifying the plant dieses IMA=imread(Path);
and trying to produce the solution for the infected area of the IMA = imresize(IMA,[500 500]);
plant through some medicine supplements. The Affected figure('name','Test Image','numbertitle','off');
crops are identified through image processing. Depending imshow(IMA);impixelinfo
upon the severity, the medicine amount is given to the crops. Ibright = Igreen + g;
Everything here is automated through a microcontroller, no Ibright = Ibright + (Imorph);
role to be played by human. For identifying the dieses we figure('name','Morphed
collected some plant data bases and by comparing the image','numbertitle','off');imshow(Ibright);impixelinfo;
infected plant with the various data bases we can identify for i=1:size(Ibright,1)
the dieses and we can monitor the process of the growth for j=1:size(Ibright,2)
level of the plants if Igreen(i,j)=0.98
Ib(i,j)=1;
else
Ib(i,j)=0;
End
g = graycomatrix(G);
stats = graycoprops(g,'Contrast Correlation Energy
Homogeneity');
Contrast = stats.Contrast;
Correlation = stats.Correlation;
Homogeneity = stats.Homogeneity;
Mean = mean2(G);
Standard_Deviation = std2(G);
Entropy = entropy(G);
RMS = mean2(rms(G));
%Skewness = skewness(img)
Variance = mean2(var(double(G)));
a = sum(double(G(:)));
Fig.2 Block Diagram Smoothness = 1-(1/(1+a));

V. EXPERIMENTAL SET UP AND PROTOCOL

VI. SIMULATION RESULTS
For identifying the dieses so many image processing
techniques also used and by using Adriano software we can
analyse the level of the infection of the plant and from that
we can decide what kind of medicine we can provide to
clear the infection.
The dieses can be identified based on measurement of soil
moisture, leaf analysis, ph level, and plant root based
analysis. The infected parts can be identified based on RGB
colour coordination and size of the images.

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number A3394058119/19©BEIESP 407 & Sciences Publication
 International Journal of Recent Technology and Engineering (IJRTE)
ISSN: 2277-3878, Volume-8, Issue-1, May 2019

1. Reference images

Image.4.Highly infected grass field output image

Image.1 Rice field green grass VII. CONCLUSION

The main focus of this project is to identify the dieses of the
plant and provide some necessary help to make the
unhealthy plant in to healthy one. An image processing
algorithm was developed to identify the dieses and a
prototype was created with full automated techniques to
provide the medical supplements to the affected plant .This
will helps the farmers to identify and rectify the dieses in the
initial stage itself and it will improves the cultivation with
healthy plants

REFERENCES
1. Sanjeev S Sannakki, Vijay S Rajpurohit, V B Nargund, Pallavi
Kulkarni,“Diagnosis and Classification of Grape Leaf Diseases using
NeuralNetworks”,IEEE proceedings of 4ICCCNT, 2013
2. S. Arivazhagan, R. NewlinShebiah, S. Ananthi, S. Vishnu Varthini,
“Detectionof unhealthy region of plant leaves and classification of
plant leaf diseases usingtexture features”, CIGR Journal ,Vol. 15,
No.1, 2013.
3. Arti N. Rathod, BhaveshTanawal, Vatsal Shah, “Image Processing
Image.2 Infected grass images
Techniquesfor Detection of Leaf Disease”, Vol 3, Issue 11, 2013.
4. Jayamala K. PatilBharti, “Advances in image processing for detection
of plantdiseases”, Journal of Advanced Bioinformatics Applications
2. Output images and Research, Vol 2,Issue 2, pp 135-141, 2011.
5. Camargoa, J.S. Smith, “An image-processing based algorithm to
automaticallyidentify plant disease visual symptoms”, Biosyst Eng.,
Vol 102:9–21, 2009.
6. SindhujaSankarana, AshishMishraa, Reza Ehsania, Cristina Davisb,
“A reviewof advanced techniques for detecting plant diseases”,
Computers and Electronicsin Agriculture, Vol 72, pp. 1–13, 2010.
7. Niketamoda, Bharat jadhav, Smeetanaikwadi, “Detection and
classification ofplantdiseases by image processing”, International
Journal of Innovative Science,Engineering & Technology, Vol. 1
Issue 2, 2014.
8. P.Revathi, M.Hemalatha, “Classification of Cotton Leaf Spot
DiseasesUsing Image Processing Edge Detection Techniques” IEEE
proceedings ofINCOSET, pp 169-173, 2012.
9. Raghottam Ramesh. Kulkarni, Dr. A. V. Sutagundar “Plant Leaf
Disease Management System” Proceedings of the IEEE 2017
International Conference on Computing Methodologies and
Communication(ICCMC)
10. Revathi, M. Hemalatha, “Cotton Leaf Spot Diseases Detection
UtilizingFeature Selection with Skew Divergence Method”,
International Journal ofScientific Engineering and Technology (ISSN:
2277-1581), Vol. (3), IssueNo.1, pg.no. 22-30, 1 Jan 2014.

Image.3.Normal grass field output image

Published By:
Blue Eyes Intelligence Engineering
Retrieval Number A3394058119/19©BEIESP 408 & Sciences Publication