Histogram Approach For Detection of Maize Leaf Damage: Debabrata Samanta and Arya Ghosh

International Journal of Computer Science and Telecommunications [Volume 3, Issue 2, February 2012]
26
Histogram Approach for Detection of Maize Leaf

Damage
ISSN 2047-3338
Debabrata Samanta1 and Arya Ghosh2

1
Department of CSE, National Institute of Technology, Durgapur, West Bengal, India

Department of IT, Bengal Engineering and Science University, Shibpur, Howrah, West Bengal, India
[email protected], [email protected]
Abstract Turcicum Leaf Blight disease in Maize are the most

major diseases which appear as spots on the leaves. If not treated
on time, causes the rigorous loss. In this paper proposes a novel
methodology of an image processing methodology to address one
of the core issues of plant pathology i.e., disease identification
and its grading. At first, the captured images are processed for
enhancement. Then image segmentation is carried out to get
target regions (disease spots). Later, image features such as
shape, color and texture are extracted for the disease spots based
on histogram. These resultants features are then given as input
to disease classifier to appropriately identify and grade the
diseases. Finally, based on the phase of the disease, the treatment
consultative module can be prepared by on the lookout for
agricultural experts, so plateful the farmers.
Index Terms Turcicum Leaf Blight Disease, Texture,
Histogram Approach, Segmentation and Objective Function
I.
INTRODUCTION
HE one and only area that serves the food desires of the
intact human race is the Agriculture zone. It has played a
key responsibility in the development of human
civilization [11]. Plants exist all over the place; we live, as
well as places without us. Plant disease is one of the essential
causes that reduces quantity and degrades quality of the
agricultural merchandises. Plant diseases have turned into a
terrible as it can cause significant reduction in both quality
and quantity of agricultural products. Some researchers are
portentous to verdict the Maize leaves using different loom
suggesting the various implementation ways as illustrated and
discussed below. In the research of identifying and diagnosing
Maize disease using computer vision intellectively in the
agriculture, feature selection is a key question in pattern
recognition and affects the design and performance of the
classifier. Mainly the fuzzy feature selection approach fuzzy
curves (FC) and surfaces (FS) - is proposed to select features
of Maize disease leaves image. Sannakki S.S., et al. [1]
proposed method for segmentation to collect the color and
texture are extracted for the disease spots. Ahmed Rafea et al.,
[2] used for integrating image scrutiny techniques into
diagnostic expert scheme. R. Pydipati et al., T.F. Burks et al.,
[3] mainly used proper disease control measures must be
undertaken in citrus groves to minimize losses. Sanjeev S
Journal Homepage: www.ijcst.org
Sannakkil et al., [4] proposed for to automatically grade the

disease spread on plant leaves by employing Fuzzy Logic.
Viraj A. Gulhane et al., [5] used the features could be
extracted using self organizing feature map together with a
back-propagation neural network is used to recognize color of
image. Major maize diseases are Turcicum Leaf Blight,
Maydis Leaf Blight, Banded Leaf and Sheath Blight, Powdery
Mildew, Downy Mildew and Bacterial Stalk Rot. Out [6] of
these we are working with one of the major severe maize
disease that is Turcicum Leaf Blight. It appears in most maize
grown area in India and sometimes is causing total loss of the
crop.
II. PROPOSD METHODOLOGY
The proposed methodology aims to model a promising
disease grading system for plant leaves. For the
experimentation purpose, pomegranate leaves are considered.
The flow chart of the methodology is presented in the
annexure 1 in the appendix. The system is divided into the
following steps: (1) Image enhancement (2) Image Preprocessing (3) Color image segmentation (4) Histogram draw
(5) Disease grading by picks value.
The proposed system is an efficient module that identifies
various diseases of that plant and also determines the stage in
which the disease is. The system employs various image
processing and machine learning techniques.
A. Image Enhancement
The aim of image enhancement is to improve the
interpretability or perception of information in images for
human viewers, or to provide `better' input [7] for other
automated image processing techniques. Image enhancement
techniques can be divided into two broad categories:
i). Spatial domain methods, which operate directly on
pixels, and
ii). Frequency domain methods, which operate on the
Fourier transform of an image.
For the purpose of image enhancement, authors have visited
and captured images from several pomegranate farms in the
places of Nadia District e.g., Krishnanagar Block-1, Chapra
Block, Dhantola Block and Ranaghat Block, India and
Debabrata Samanta and Arya Ghosh

improve the interpretability or perception of information in
images for human viewers.
B. Image Pre-processing
Image processing is a structure of signal processing for
which the input is an image, such as a photograph or video
frame; the output of image processing may be either an image
or a set of characteristics or parameters related to the image
[8]. Preprocessing uses the techniques such as image resize
segmentation, filtering, cropping, contrast enhancement, angle
correction, morphological operations etc.
C. Color Image Segmentation
Image segmentation refers to the progression of partitioning
the digital image into its ingredient regions or objects so as to
change the representation of the image into something that is
more consequential and easier to analyze [9]. K-means
clustering technique has been used in the present work to
carry out segmentation. K-Means Clustering is a method of
cluster analysis which aims to partition n observations into k
mutually exclusive clusters in which each observation belongs
to the cluster with the nearest mean.
The objective function is:
r
27
Where G = grade value, P(x,y) = Image matrix function,

r=row value and c=Colum value,
P ( x, y ) =
p ( x , y ,1, 0)
(3)
r 1 c 1
P ( x, y ,1, 0)
x =0 y =0
Table I: Disease grading
Disease
Grade
Downy
Mildew
Powdery
Mildew
Normal
Negative
Training
Sample
Testing
Sample
Classifier
Accuracy
210
43
83.5%
210
48
95.2%
210
210
47
45
96.7%
93.56%
III. PROPOSED WORK FLOW DIAGRM
START
Z = | Gx y S j |2 (1)
Capturer Image
x =1 y =1
Where
| Gx y S j |2 is a chosen distance measure between a
data point
Image Preprocessing
Gx y and the cluster centre S j , is an indicator of
the distance of the n data points from their respective cluster

centers. The K-Means follows by:
i) Place K points into the space represented by the objects
that are being clustered. These points represent initial
group centroids [10].
ii) Assign each object to the group that has the closest
centroid.
iii) When all objects have been assigned, recalculate the
positions of the K centroids.
iv) Repeat Steps 2 and 3 until the centroids no longer move.
This produces a separation of the objects into groups
from which the metric to be minimized can be
calculated.
D. Histogram Draw
Generally, in image processing expressions area of a binary
image is the total number of on pixels in the image. The
original resized image is converted to binary image such that
the pixels corresponding to the leaf image are on. Then we
plot the histogram for calculate the change the pick value.
F. Disease Grading by Picks Value
A histogram based System is developed for disease grading
by referring to the disease scoring scale in Table I. The main
grading system depends on:
r 1 c 1
G = P( x, y ) log P( x, y ) (2)
x =0 y = 0
Segmentation
Pick value of
histogram
Disease grading
Stop
Fig. 1: Flow Diagram
IV. RESULT AND DISCUSSION

Now, Maize leaf images are used to test proposed algorithm
(Fig. 1). First we get the Original leaf (Fig. 2) and another
disease leaf (Fig. 3). Then we calculate the gray value of each
leaf (Fig. 4 & Fig. 5). Finally we segmented the each image
using K-Mean clustering, i.e., background removed image
(Fig. 6 & Fig. 7) .Now we get picks values from each
histogram (Fig. 8 & Fig. 9) and define the disease grading.
International Journal of Computer Science and Telecommunications [Volume 3, Issue 2, February 2012]
Fig. 2: Original disease

free leaf
Fig. 3: Original affected

leaf
Fig. 4: Gray Image
Fig. 5: Gray Image
Fig. 6: Background remove

Image
Fig. 8: Histogram
Fig. 7: Background remove

Image
Fig. 9: Histogram
V. CONCLUSION
In this paper, we proposed a novel histogram based
detection of leaf damage technique for Maize. Using the
histogram approach and color image segmentation technique
to exact intensity pattern to Turcicum Leaf Blight disease
accordingly it is then possible to analyze the different Maize
leaf diseases. Here there is more scope to reduce the various
errors which will be occurred during the simulation, that can
be minimize as the more no of input is provided accordingly.
The result from the preliminary study indicated that the
proposed strategy is effective to assess disease intensity by
the plant pathologist more precisely.
REFERENCES
[1] Sannakki S.S, Rajpurohit V.S, Nargund V.B, Arun Kumar R
and Yallur P.S., A HYBRID INTELLIGENT SYSTEM FOR
AUTOMATED POMEGRANATE DISEASE DETECTION
AND GRADING, International Journal of Machine
Intelligence ISSN: 09752927 & E-ISSN: 09759166, Volume
3, Issue 2, 2011, pp-36-44.
[2] Ahmed Rafea,Salwa El-Gamal,Reda Abd EI Whab ,Integrating
Diagnostic Expert System with Image Processing via Loosely
Coupled Technique , Journal of Agricultural Research Center .
[3] R. Pydipati, T.F. Burks, W.S. Lee, Identification of citrus
disease using color texture features and discriminate analysis,
Computers and Electronics in Agriculture 52, pp.4959 , 2006.
28
[4] Sanjeev S Sannakki1, Vijay S Rajpurohit, V B Nargund, Arun

Kumar R, Prema S Yallur , Leaf Disease Grading by Machine
Vision and Fuzzy Logic, Int. J. Comp. Tech. Appl., Vol 2 (5),
1709-1716, 2011.
[5] Viraj A. Gulhane, Dr. Ajay A. Gurjar, Detection of Diseases
on Cotton Leaves and Its Possible Diagnosis, International
Journal of Image Processing (IJIP), Volume (5): Issue (5), 2011.
[6] WA Allen and E G Rajotte, The changing role of extension
entomology, Annual Review of Entomology, vol.35, pp.379397, January1990, doi:10.1146/annurev.en.35.010190.002115.
[7] Tang S and Chepe R, Models for integrated pest control and
their biological implications, Math.Biosci, pp.115-125.
[8] Yan Li, Chunlei Xia and Jangmyung Lee, Vision-based pest
detection and automatic spray of greenhouse plant, IEEE
International Symposium on Industrial Electronics, July 5-8
2009.
[9] Paul Boissard, Vincent Martin and Sabine Moisan, Acognitive
vision approach to early pest detection in greenhouse crops,
Computers and Electronics in Agriculture, pp. 81-93, 2008.
[10] Jongman Cho,Junghyeon Choi,Mu Qiao,Chang-woo Ji,Hwangyoung Kim,Ki-baik Uhm and Tae-soo Chon, Automatic
identification of whiteflies, aphids and thrips in greenhouse
based on image analysis, International journal of Mathematics
and Computers in Simulation, vol.1, 2007.
[11] A. N. Pavlov and V. S. Anishchenko, Multifractal analysis of
complex signals, Methodological Notes, pp.819-834, 2007.
Debabrata Samanta is a member of the IAENG, Board member of the

Seventh Sense Research Group Journals (SSRGJ), member of Editorial Board
of IJSCE. He obtained his B.Sc. (Physics Honors) in the year 2007, from the
Vivekananda Collage, Takurpukur, under Calcutta University; Kolkata, India
.He obtained his MCA in the year 2010, from the Academy Of Technology,
under WBUT. He is working his PhD in Computer Science and Engg. from
the year 2010 from National Institute of Technology, Durgapur, India in the
area of Image Processing .He is presently working as a Lecturer of CSE in
Abacus Institute of Engg. And Management, West Bengal, India. His areas of
interest are Artificial Intelligence, Natural Language Processing and Image
Processing. He has published 20 papers in International Journals /
Conferences.
Arya Ghosh obtained his B.C.A.in the year 2003, from the JIS Collage of
Engineering, Kalyani, under Kalyani University, India. He obtained his MCA
in the year 2006, from the JIS Collage of Engineering, under WBUT. He is an
MTech student of IT of Bengal Engineering and Science University, Shibpur,
Howrah, India.

Histogram Approach For Detection of Maize Leaf Damage: Debabrata Samanta and Arya Ghosh

Uploaded by

Copyright:

Available Formats

Histogram Approach For Detection of Maize Leaf Damage: Debabrata Samanta and Arya Ghosh

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Histogram Approach For Detection of Maize Leaf Damage: Debabrata Samanta and Arya Ghosh

Uploaded by

Copyright:

Available Formats

International Journal of Computer Science and Telecommunications [Volume 3, Issue 2, February 2012]

Histogram Approach for Detection of Maize Leaf

Debabrata Samanta1 and Arya Ghosh2

Department of CSE, National Institute of Technology, Durgapur, West Bengal, India

Abstract Turcicum Leaf Blight disease in Maize are the most

Journal Homepage: www.ijcst.org

Sannakkil et al., [4] proposed for to automatically grade the

Debabrata Samanta and Arya Ghosh

Where G = grade value, P(x,y) = Image matrix function,

Table I: Disease grading

III. PROPOSED WORK FLOW DIAGRM

| Gx y S j |2 is a chosen distance measure between a

Gx y and the cluster centre S j , is an indicator of

the distance of the n data points from their respective cluster

IV. RESULT AND DISCUSSION

Fig. 2: Original disease

Fig. 3: Original affected

Fig. 4: Gray Image

Fig. 5: Gray Image

Fig. 6: Background remove

Fig. 7: Background remove

[4] Sanjeev S Sannakki1, Vijay S Rajpurohit, V B Nargund, Arun

Debabrata Samanta is a member of the IAENG, Board member of the

You might also like