IRJET-Android Based Plant Disease Identification System using Feature Extraction Technique

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 01 | Jan-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 861
Android Based Plant Disease Identification System Using Feature
Extraction Technique
Dixit Ekta Gajanan1, Gavit Gayatri Shankar2, Gode Vidya Keshav3
1,2,3 Student, Dept. of Computer Engineering, Gokhale Education Society's R. H. Sapat College of Engineering
Management Studies and Research,Nashik, Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Although professional agriculture engineers
are responsible for the recognition of plant diseases,
intelligent systems can be used for their diagnosis in early
stages. The expert systems that have been proposed in the
literature for this purpose, are often based on facts
described by the user or image processing of plant photos in
visible, infrared, light etc. The recognition of a disease can
often be based on symptoms like lesions or spots in various
parts of a plant. The color, area and the number of these
spots can determine to a great extent the disease that has
mortified a plant. Higher cost molecular analyses and tests
can follow if necessary. This application can easily be
extended for different plant diseases and different smart
phone platforms.
Key Words: Image processing, Intelligent system,
Molecular analyses, Plant diseases, Smart phone.
1. INTRODUCTION
The studies of fruit or plant can be determined by
observable patterns of specific plant and it is critical to
monitor health and detect disease within a plant. Through
proper management strategies such as pesticides,
fungicides and chemical applications one can facilitates
control of diseases which interns improve quality. There
are various techniques available such as spectroscopic and
imaging technology are applied to achieve superior plant
disease control and management. With smart farming
today’s farmer can use decision tools and automation
techniques which seamlessly integrate product, knowledge
and services for better productivity, grading and surplus
yield. The purpose of this paper is to monitor diseases on
fruits or plants or plants or plants and suggest better
solution for healthy yield and productivity and for this
SURF Pattern Matching concept is used. System uses two
image databases, one for training of already stored infected
area image and other for execution of query images. Three
fruits or plants namely grapes, apple and pomegranate
have been used for research in this paper.
As there is enormous economical loss in export business
due to degraded quality of fruit and it also has a harmful
impact on human health. Detection of Fruit Disease using
color, texture analysis, gives a great platform for
implementing a smart farming. The model when designed
and implemented can be considered for enriching India as
a smart country.
2. LITERATURE SURVEY
Image Processing for Smart Farming: Detection of Disease
and Fruit Grading, Authors (Monica Jhuria, Ashwani
Kumar, And Rushikesh Borse), 2013. As there is wide need
for agricultural industries improved yield of fruit is
important, there is need of automated technique which will
find disease on fruits or plants or plants or plants. For this
artificial neural network methodology is suggested which
can be helpful to categories fruit infection. K-Means
clustering is applied to find diseased area on the fruit but it
has disadvantage of sizable estimation load. It will
encourage agronomist to build better production and make
correct time to time judgment.
A Review of Image Processing For Pomegranate Disease
Detection, Authors (Manisha A. Bhange, Prof. H. A.
Hingoliwala), 2015. This process suggests a solution for the
recognition of pomegranate fruit disease and for that
disease after detection is proposed. In this process, web
based technique applied to help non experts in identifying
fruit diseases which is depends on the picture representing
the symptoms of the fruit. Farmers can take image of fruit
disease and upload it to the system. Then the farmer will
see the fruit is affected by bacterial blight or not.
A Cost Effective Tomato Maturity Grading System using
Image Processing for Farmers, Authors (Sudhir Rao
Rupangadi, Ranjani B.S., Prathik Nagaraj,Varsha G Bhat),
2014. In this system, it classifies ripeness of fruit based on
its color or texture. It involves current techniques mainly
manual inspection which leads to errorious classification,
which results in economic losses due to inferior produce in
the market chain. There are short comings that are several
methodologies but they require highly expensive setups
and complicated procedures, overall accuracy is achieved
up to 98%.
Adapted Approach for Fruit Disease Identification using
Images, Authors (Shiv Ram Dubey, Anandsingh Jalal). An
adaptive approach is experimentally validated. The
approach consist of steps and that are stated as; first step is
k-means clustering technique which is applied for defect
segmentation and second step involves some state of art
features that are extracted from segmented image and then
segmented image are classified into one of classes with the
help of multi-class support vector machine. It achieves
precision up to 93%.

Fruit Detection using Improved Multiple Features based
Algorithm, Authors (Hetal N. Patel, Dr.R.K.Jain, and Dr. M. V.
Joshi), 2011. It gives improved solution for locating the
fruits or plants or plants or plants on the plant based on
multiple features. Multiple feature extortion technique can
include steps like extraction of color and intensity feature,
extraction of orientation feature, extraction of edge feature,
extraction of area from feature maps. The process is
entirely automatic and it can work without user
involvement. To improve output it considers numerous
features.
Tomato quality evaluation with image processing: A
review, Authors(Abraham Gastlum- Barrios, Rafael A.
Brquez-Lpez, Enrique Rico-Garca, Manuel Toledano-Ayala
and Genaro M. Soto-Zaraza), 2011. All over the world there
is excessive requirement for tomato. Therefore grade
assessment of tomato is prime task using image processing
it can be acquire. Worldwide study of tomato production is
done to accomplish the target. It is useful to obtain tomato
quality, good color, pattern, size and composition. Instead
of manual testing we can achieve fast and accurate testing
in laboratories for tomato grading.
Fast and Accurate Detection and Classification of Plant
Diseases, Author (H. Al- Hiary, S. Bani-Ahmad, M. Reyalat,
M. Braik, and Z. ALRahamneh), 2011. Improved solution for
automated diagnosis and grading of plant leaves disorder
can be diagnose with help of K-Means Clustering
procedure. It uses SGDM Matrix for Hue Saturation. Also
Otsu method is applied for masking pixels based on certain
threshold values. It uses color concur technique for
extracting features of leaf but it is unable support huge
complicated network structure.
3. PROPOSED SYSTEM
The purpose of proposed system is to supervised the
diseases on fruit and suggest alternate solution for healthy
yield and good productivity. Labeling of border pixel can be
achieved by image segmentation this can be done by K-
Means clustering technique. Trained database of infected
image has been generated using Neural Network. Feature
vectors such as image color, morphology, texture and
structure of hole are applied for extracting features of each
image and for diagnosis of disease morphology gives
accurate result. SURF algorithm used as locator and
descriptor for extracting the features. Using extracted
features Scope of Interest can be calculated and extraction
can be followed as its first step after which refinement and
analysis is done.
Family of SURF Pattern Matching is used to evaluate or
appraisal functions that depends upon huge number of
inputs and they are generally unknown. They are systems
of interdependent ”neurons” and utilities from inputs for
computing and are having a potential of machine learning
along with pattern recognition in adaptive nature. This is
convenient technique which reduces human effort and
gives 90% accurate result. For starting this process,
initially non-uniform weights are fixed and then training
begins. Supervised and unsupervised are two
methodologies used for training. Supervised training
mechanism provides the network with the specific output
either by manually ”grading” the network’s performance or
by providing the desired outputs accomplished by the
inputs while Individual training can be achieved by
network that takes inputs without external help.
Supervised training approach is used by bulk of networks
whereas unsupervised training is applied to execute some
initial characteristics on inputs. Basically database server is
used for comparison of extracted image with trained
database which in turns diagnose and classify disease of
fruits or plants.
3.1 System Architecture
Fig-1 System Architecture
3.2 Methodology
a. Image acquisition: It is the initial condition for the work
flow series of image processing because as processing is
possible only with the help of an image. The image
obtained is entirely natural and is the consequence of any
hardware which was handled to produce it.
b. Image Segmentation - It is the method for segregation
of digital image into several segments. Objects and
bounding line of images are located by using image
segmentation. Pixels with similar label portion share
distinguishing features for allocating a label to each pixel in
an image. For this we are using K-Means Clustering
methodology.
c. Feature Extraction - Four feature vectors are
considered namely color, texture, morphology and
structure of hole of the fruits. Algorithm used for extracting
the features is as follow: SURF (Speed up Robust Feature)

algorithm is applied for extracting the features. SURF
algorithm used as local descriptor and blob detector.
S(x,y)=∑ ∑ ………….eq 1
Algorithm is mainly divided as -
1. Scope point Detector
2. Local surrounding descriptor
3. Matching.
d. Blob Analysis – It is intended at detecting scope of
interest surrounded by digital image that varies in
properties. Blob Analysis solution consists of the
successive stages:
1. Extraction: It is primary step of image
thresholding technique which inspects a region
corresponding to single object or objects.
2. Refinement: Extracted region contain various
kind of loud sound due to degraded quality of image.
Region transformation techniques are used in refinement
step.
3. Analysis: It is ultimate stage for refined region to
evaluate & compute the outcome. If the region shows
multiple objects then divide it into separate blobs for
inspection.
e. Pattern Matching - It is the procedure of examining
stated successions of tokens for the existence of the
elements of some pattern.
3.3 Algorithm
Input – Images of Various Fruits
Output – Detection of Fruit Disease
Step 1: Accept image using android phone from user:
(Color, Morphology, Texture, Structure of Hole)
Step 2: Extraction of Feature Vectors
E (n) = [C (n) + M (n) + T (n) +H (n)]
Here,
C = Color, M = Morphology, T = Texture, H = Structure of
Hole, E = Extraction of features, n = No. of images
Step 3: Calculating ROI:
Let E (n) be set of Extracted Images and
If<Fruit Detected> Then E (n)
Else Reject
Step 4: Pattern Matching
Let T be set Trained Database
If<E (n) = = T> Then Classification Detection
Else Go To Step (2)
Step 5: Stop.
3.4 Mathematical Model
Four feature vectors such as color, morphology, texture
and structure of hole are used as learning database images
for extracting the features.
a.Color: It is the most valuable properties used by human
for object discrimination. As RGB color space is affected
by light and angle of image which has been captured so
there is need for conversion into HSI color space.
Heu = { …………………………….…eq 2
Here,
Thita = [ ]
…………………………eq3
Saturation = 1- [ ]……………………..eq4
Intensity = ………………………………………..eq5
b.Morphology: Erosion concept is applied for acquiring
boundaries of all database images.
Erosion = { }…………..……………………….eq 6
Image Boundary= Original image - Eroded image……..eq7
Where,
X is erosion which indicates database images and Y as input
image which is set of each points Z such that Y converted
by Z and contained in X in morphology. Entire knowledge
about structure is symbolized with the help discrete cosine
conversion considering few co-efficient.
c. Texture: Visual patterns describe texture property,
each having similarity. Texture identification is done by
modeling textures as two-dimensional deviation of gray
level.
………………………..…eq8
Then
W =
√
∫ …………………………………………eq9
Where,
4. CONCLUSIONS
Proposed system suggests that the advanced approach is a
worth, which can distinctly support an accurate diagnosis
of fruit diseases in a minor computational effort. It also
dedicates future study on automatically estimating the
severity of the disease.
ACKNOWLEDGEMENT
The work procedure in this seminar would not have been
completed without the encouragement and support of
many people who gave the precious time and

encouragement throughout this period. I would like to
sincerely thank our seminar guide Prof. R. B. Mandlik for
his guidance and for the patience he showed during the
process of preparation of seminar from initial conception
to final implementation. I would also like to extend our
gratefulness to the Head of Computer Department Prof . D.
V. Patil. I would also thank to the teaching and non-
teaching staff who helped us from time to time with their
own experience and also I would like to express our
gratitude from core of our heart, principle Sir for being
supportive and always encouraging.
REFERENCES
[1] Monica Jhuria, Ashwini Kumar, Rushikesh Borse
Image Processing for Smart Farming: Detection of
Disease and fruit Grading Proceeding of the 2013 IEEE
second international Conference on image Processing.
[2] Sudhir Rao Rupanagudi, Ranjani B.S., Prathik Nagaraj
,Varsha G. Bhat A cost effective Tomato maturity
Grading system using image Processing for Farmers
2014 International Conference on Contemporary
Computing and Information.
[3] Shiv Ram Dubey, Anand Singh Jalal Adapted Approach
for Fruit Disease Identification using Images
[4] Manisha A. Bhange, Prof. H. A. Hingoliwala A Review of
Image Processing for Pomegranate Disease Detection.
International Journal of Computer Science and
Information Technologies, Vol. 6 (1), 2015, 92-94.
[5] Hetal N. Patel, Dr. M.V.Joshi, Fruit Detection using
Improved Multiple Features based Algorithm
International Journal of Computer Applications (0975
8887), Volume 13 No.2, January 2011.
[6] Abraham Gastlum-Barrios, Rafael A. Borquez-Lpez,
Enrique Rico-Garca Tomato Quality Evaluation with
Image processing: A review African Journal of
Agricultural Research Vol. 6(14), pp. 3333-3339, 18
July, 2011.
[7] H. Al-Hiary, S. Bani-Ahmad, M. Reyalat, M. Braik and Z.
ALRahamneh Fast and Accurate Detection and
Classification of Plant Diseases International Journal
of Computer Applications (0975 8887) Volume 17
No.1, March 2011.
[8] P.Vimala Devi and K.Vijayarekha Machine Vision
Application to Locates, Detect Defects and Remove
Noise: A Reviewvol.7—No.1—104-113— January
March — 2014
[9] Shiv Ram Dubey, A.S. Jalal Detection and Classification
of Apple Fruit Diseases using Complete Local Binary
Patterns
[10] Rashmi Pandey, Sapan Naik ,Roma Marfatia Image
Processing and Machine Learning for Automated Fruit
Grading System: A Technical Review International
Journal of Computer Applications (0975 8887)
Volume 81 No 16, November 2013 .
[11] Anshuka Srivastava, Swapnil Kumar Sharma
Development of a Robotic Navigator to Assist the
Farmer in Field Proceeding of the International Multi
Conference of Engineers and Computer Scientists
2010 Vol. (2) IMECS 2010 March 17-19 Hong Kong.
[12] Savita N. Ghaiwat, Parul Arora Detection and
Classification of Plant Leaf Diseases Using Image
processing Techniques: A Review International
Journal of Recent Advances in Engineering and
Technology (IJRAET)ISSN (Online): 2347 - 2812,
Volume-2, Issue - 3, 2014.
[13] Anand.H.Kulkarni, Ashwin Patil R. K. Applying image
processing technique to detect plant diseases
International Journal of Modern Engineering Research
(IJMER) Vol.2, Issue.5, Sep-Oct. 2012 pp-3661-3664.
[14] Pradnya Ravindra Narvekar, Mahesh Manik
Kumbhar2, S. N. Patil Grape Leaf Diseases Detection
and Analysis using SGDM Matrix Method(An ISO
3237:2007 certified organization ) Vol.2,Issue 3,
March 2014.

IRJET-Android Based Plant Disease Identification System using Feature Extraction Technique

Recommended

More Related Content

What's hot (20)

Similar to IRJET-Android Based Plant Disease Identification System using Feature Extraction Technique (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET-Android Based Plant Disease Identification System using Feature Extraction Technique