ROBUST CLASSIFICATION OF DISEASES IN RUBBER LEAF BASED

ON DECISION TREE ALGORITHM

NAYANA
M.Tech(DECS) Student, Dept. of Electronics and Communication Engineering
VCET Puttur D.K, Karnataka, India 574203

DR. SHIVAPRAKASH KOLIWAD

Professor, Research coordinator, Dept. of Puttur and Communication Engineering,
VCET Puttur D.K, Karnataka, India 574203

PROF.SRIKRISHTNA SHASTRI C
Associative Professor, Dept. of Electronics and Communication Engineering
VCET Puttur D.K, Karnataka, India 574203

PROF. JAYANTH J
Research Scholar VCET Puttur D.K., India574203

ABSTRACT- In agricultural research, detection of disease in Rubber leaf plays a dominant role in
deciding the Latex from the Rubber tree. A healthy Rubber tree yields more Latex when it is not
encountered by the disease; there exists four different diseases which reduces the Latex. Early
detection and a proper counter measure will enhance the quality and quantity of Latex since most
of the diseases are seen on the leaves themselves. Hence, monitoring the healthiness of leaf
continuously is a challenging task. The features of the leaves changes when they are affected by
the diseases. Based on the percentage of disease incidence, symptoms of disease attack and the
season during which, a particular disease is identified all play a major role. The changes in the
features of the leaves are used to classify the type of disease. To implement the work Image
processing concepts are used. In this paper identification of disease is done based on Decision tree
algorithm. The proposed work will help the small and big farmers to grow Rubber tree more
efficiently and take control measures at appropriate time to increase the yield.

KEYWORDSDecision tree, Latex, Types of Disease, Natural Rubber, Classification, Rubber

leaf diseases, Image Acquisition.

INTRODUCTION

India is an agricultural country; wherein about 70% of the population depends on agriculture.
Farmers have wide range of diversity to select suitable fruit and vegetable crops. However, the
cultivation of these crops for optimum yield and quality produce are highly technical. The
management of perennial fruit crops requires close monitoring especially for the management of
diseases that can affect production significantly in the post-harvest life. In case of plant, the
disease is defined as any impairment of normal physiological function of plants, producing
characteristic symptoms. A symptom is a phenomenon accompanying something and is regarded
as evidence of its existence. Disease is caused by pathogen which is any agent causing disease [6].
Rubber trees are one of the earths greatest natural resource.
Natural rubber also called as India rubber or caoutchouc, as initially produced, consists of
polymers of the organic compound isoprene, with minor impurities of other organic compounds
plus water. Forms of polyisoprene used as natural rubbers are classified as elastomers. Currently
rubber is harvested mainly in the form of latex from trees. The latex is sticky, milky colloid drawn
off by making incisions into the bark and the fluid is collected in vessels in a process called
tapping. The latex then is refined into rubber ready for commercial processing. Natural rubbers
are extensively used as the products either alone or in combination with other materials. Rubber is
used in a variety of applications ranging from latex gloves, textile manufacturing, valves in
machinery and in automobiles to shoes.

In this market environment today, going green is the thing. Rubber production industry is
recognized as a green industry. After 30 years of rubber tapping a rubber tree efficiency to produce
rubber drops, then tree is chopped down and the wood from the tree is used as bio-fuel, furniture
wood, or as light manufacturing wood. Every time when tree is chopped down a new tree takes its
place. The greatest problem now faced by the growers is rubber tree diseases. It is essential to
identify the appropriate disease and take necessary control measures for the same before tree dies
off. Hence the work aims to identify the diseases using the features of rubber leaves from their
image.

LITERATURE SURVEY

To understand problem faced in the implementation of work, an exhaustive literature survey is

necessary. The survey provides input for carrying out the work. It also helps to overcome the
problems while implementing the work.

Smita Naikwadi, Niket Amoda considered the management of disease in leaves or stems of the
plant. Precise quantification of these visually observed diseases, pests, traits has not been studied
because of the complexity of visual patterns. As such, there is an increasing demand for more
specific and sophisticated image pattern understanding. In biological science, sometimes
thousands of images are generated in a single experiment. These images are required for further
studies like classifying lesion, scoring quantitative traits, calculating area eaten by insects, etc.
Almost all of these tasks are processed manually or with distinct software packages. It is not only
tremendous amount of work but also suffers from two major issues: i) excessive processing time
ii)subjective classification rising from different individuals. Hence to conduct high throughput
experiments, plant biologist needs efficient computer software to automatically extract and analyze
significant content.

Sanjay B. Dhaygude, Mr. Nitin ,P. Kumbhar considerd a vision based detection algorithm. This
algorithm consists of four main steps. First, a color transformation structure for the input RGB
image is created, and this RGB is converted to HSI because RGB is for color generation and HSI
for color descriptor. Then green pixels are masked and removed using specific threshold value,
then the image is segmented and the useful segments are extracted. Finally the texture statistics is
computed from Spatial Gray Level Dependency Matrices. Then the presence of diseases on the
plant leaf is evaluated.

H. AI-Hiary, S. Bani-Ahmed, M. Reyalat, M. Braik and Z. AL Rahamneh discussed a method for

fast and accurate detection and classification of plant diseases. They have considered K-means

659
clustering, Otsu Segmentation and back propagation feed forward neural network for clustering
and classification of diseases that affect on plant leaves.

Hashim, H.; Haron.; M.A.; Osman, F.N; Al Junid, S.A.M explains the classification of five types
of rubber leaf diseases by using the spectrometer and data mining software such as Software
package for Statistical Analysis (SPSS). They conclude that these diseases can be discriminated
from each other using a Spectrometer for their analysis.

S.A Ali, Sulaiman, A Mustapha and N Mustapha used a new software tool for accurate findings of
diseases.They have used the concept of decision tree learning method. Before classification is
done the data is processed based on MLC, Bayseian Network and Decision tree. They found that
Decision tree method delivers better results than others and classification is done based on ranking
process.

TYPES OF DISEASES IN RUBBER LEAVES

The rubber tree may live for a hundred years or even more. But its economic life period in
plantations, on general considerations is, only around 7 years of immature phase and 25 years of
productive phase. But, if it is affected by diseases then production rate drastically reduces. Few
commonly found diseases are listed below:

Powdery Mildew (Oidium heveae)

Occurrence: Predominantly noticed on newly formed tender flush during the re-foliation period of
January to March. The disease is severe in Kanyakumari, Idukki and Wynad district of South India
and North Eastern States.

Figure. 1: Powdery mildew affected leaf

Symptoms: Tender leaves with ashy coating curl, crinkle, and edges roll inwards and fall, leaving
the petioles attached to the twigs like a broom-stick. After a few days, the petioles also fall. Die-
back of twigs follows

Corynespora Disease

Figure. 2: Corynespora affected leaf

660
Corynespora disease (caused by the fungus Corynespora cassiicola) is more severe during re-
foliation in the months from December to April. Though it affects leaves of all stages, young
leaves in the light green stage appear to be the most susceptible. Symptoms vary with the clones
and locality. Circular lesions of varying sizes with papery centre, brown margin and a yellow halo
is the common symptom. The leaf tissues surrounding infected veins turn yellow and later to
brown, and then the leaf falls off.

Bird's Eye Spot

Fig. 3: Birds eye spot affected leaf

Occurrence: A hot weather disease, serious and damaging in the nursery. Weaker plants and
plants growing under exposed situations are more susceptible.

Symptoms: Symptoms appear as small necrotic spots with dark/brown margins and pale centre.
Severe infection leads to premature defoliation and die back.

Control Measures: Shading the nursery plants reduces the disease incidence. Maintain seedlings in
vigorous condition through adequate balanced nutrition.

Colletotrichum

Figure. 4: Colletotrichum affected leaf

Causitive agent: Colletotrichum acutatum C. gloeosporioides Sacc.

Occurrence: Obsereved during April to December, In North East India. The disease is prevalent
throughout the year except. During winter.

Symptoms: Infects tender leaves, mostly at the leaf tip region. spots are small, brown in colour
and is sorrounded by an yellow hallo. Numerous spots coalesce and dry up leading to defoliation.
The infected leaves often crinkle and become distorted before shedding..

Control Measures: Spraying with Bordeaux mixture 1%, copper oxychloride 0.125% (Fytdan 2.5
g/l) mancozeb 0.2% (Dithane/ Indofil M 45 2.66 g/l) or carbendazim 0.05% (Bavastin 1 g/l) at 10 -
15 days intervals is effective.

661
PROPOSED METHOD

A decision tree is a classifier in the form of tree structure. It is a graphical model describing
decisions and their possible outcomes. It is used as a model for sequential decision problems under
uncertainty. A decision tree describes decision to be made, the events that may occur, and the
outcomes associated with combinations of decisions and events. Decision tree consists of three
types of nodes:
Decision node
Leaf node
Terminal node
Decision node: It is usually represented by squares showing decisions that can be made. Lines
emanating from this node show all distinct options available at a node.
Leaf node: It is usually represented by circles showing chance outcomes. Chance outcomes are
events that can occur but are outside the ability of the decision maker to control.
Terminal node: It is usually represented by triangles or by lines having no further decision nodes
or chance nodes. Terminal nodes depict the final outcomes of the decision making process.

Basic Block diagram

Image acquisition: Image acquisition in image processing can be broadly defined as the action of
retrieving an image from a hardware-based source, such as camera. Performing image acquisition
in image processing is always the first step in the workflow sequence because, without an image,
no processing is possible.

Acquire the Feature Knowledge Base

ref. Image extraction

Acquire the Feature Comparison

i/p image extraction

Disease
Classification

Figure. 5: Block diagram of designed system

Feature extraction: In image processing, feature extraction is a special form of reduction. The
feature is defined as a function of one or more measurements, each of which specifies some
quantifiable property of an object. When the input data to an algorithm is too large to be processed
and it is suspected to be notoriously redundant then the input data will be transformed into a
reduced representation set of features

Knowledge base: This contains a set of images of pre-defined diseases of rubber leaves. The
photographs of rubber leaf images are saved in JPEG format for further processing.

662
Comparison: When a test image is received, their features are extracted too and compared with
those stored in the data base. When a match is found we confirm the disease. Accordingly the
output is displayed showing the details of the disease and solution for the same.

RESULT

A Red, Green and Blue component values for all leaves are computed and the average values
obtained for each disease are used to construct the Decision tree.

Table1. Average RGB values for each leaf

Name of the Red Green Blue
disease
Birds Eye Spot 113 96 74
Colletotrichum 128 109 98
Powdery Mildew 136 144 106
Corynespora 204 170 136

CONCLUSION

Nowadays, a large sum of financial resources is destined to prevent the diseases in rubber
plantation by producers. The costs with agricultural inputs are a main factor in the permanent
expenses of the production system. A monitoring system suitable for plant is necessary to achieve
a correct decision-making about diseases. The proposed method indicates that the Image
Processing technique plays an important role in the analysis.

REFERENCES

S.Jayaraman,S.Esakkirajan,T.Veerakumar, Digital image processing Tata Mc.Graw Hill

Education Private Limited.
Kishan Mehrotra, Chilukuri K.Mohan, Sanjay Ranka, Artificial Neural Network.
Rafael C. Gonzalex, Richard E. Woods, Steven L. Eddins, Digital Image Processing using
Matlab.
Smita Naikwadi, Niket Amoda, Advances in Image Processing for Detection of Plant Diseases.
Prof. Sanjay B. Dhaygude, Mr.Nitin P.Kumbhar, Agricultural Plant Leaf Disease Detection
using image processing. International Journal of Advanced Research in Electrical, Electronics
and Instrumentation Engineering Vol.2, Issue 1, January 2013
Jaymala K. Patil, Raj Kumar, Advances in Image Processing for Detection of Plant
Diseases.Journal of Advanced Bioinformatics Application and Research, Vol.2, Issue 2, June-
2011, Pp135-141.
H. Al-Hiary, S. Bani Ahmad. Fast and Accurate Detection and classification of plant diseases
IJCA (0975-8887), Volume 17-No.1 March 2011.
Hashim, H.; Haron, M.A.; Osman, F.N; Al Junid, S.A.M, Classification of Rubber Tree Leaf
Disease Using Spectrometer. 2010 IEEE Fourth Asia International Conference on
Mathematical/Analytical Modelling and Computer Simulation .
S. A Ali, N. Sulaiman, A. Mustapha and N. Mustapha, Improving Accuracy of Intention- Based
Response Classification using Decision tree. Information Technology Journal 8(6):923-928,
2009.

663
S. A Ali, N. Sulaiman, A. Mustapha and N. Mustapha, K-Means Clustering to Improve the
Accuracy of Decision tree Response Classification. Information Technology Journal
8(8):1256-1262, 2009.
Varsha Choudhary, Pranita Jain, Classification : A decision Tree For Uncertain Data Using
CDFApplicatons(IJERA)ISSN:2248-96 Vol. 3, Issue 1, January-February 2013.

664