SlideShare a Scribd company logo
The International Journal Of Engineering And Science (IJES)
||Volume|| 2 ||Issue|| 10 ||Pages|| 39-42 ||2013||
ISSN (e): 2319 – 1813 ISSN (p): 2319 – 1805

Pest Detection on Leaves Using Poission’s Thresholding
Techniques
Sitaram Longani1, Prof.V.V. Dixit2
1

M.E. (Communication Network) Student, Sinhgad College of engineering, Pune- 41.
Department of Electronics and Telecommunication, Sinhgad College of engineering, Pune- 41.

2

--------------------------------------------------------ABSTRACT-------------------------------------------------Different diseases and bioagressor are affecting the crops, due to which the plants cannot survive for a
long duration. Mainly the bioagressor which is been frequently seen on the leaves of the plant is the whitefly.
Our main aim is to count the number of whitefly on the leaves. Different techniques are used such as poission’s
minimum error thresholding, learning, layer labelling, to count the number of pest on the leaves. The automatic
counting of pests on the leaf helps in deciding the amount of pesticides to be sprayed on the leaf. This system is
useful not only to count the number of pest on its mature stage but also it can count the number of stages at its
middle stage and starting stage. We have compared our result with the manual method and its has been seen
that automatic counting gives the greater accuracy.

Keywords - whitefly, Digital image, Image segmentation, leaf, Thresholding technique
----------------------------------------------------------------------------------------------------------------------------- ---------Date of Submission: 11th, October, 2013
Date of Acceptance: 30th, October, 2013
----------------------------------------------------------------------------------------------------------------------------- ----------

I.

INTRODUCTION

Our India is an agriculture country, most of the people in india are farmer and the other depends on the agriculture.
Most of the scientists are doing research to increase the cultivity of crops. But one problem still exist which is a major
concern of the cultivation of crop and that is crop diseases. Due to these problems, the cultivation decreases and hence all the
farmers and in turn the country suffers the lack of cultivation of crop. Different types of pesticides are there in market which
are used to avoid the damage to fruit and vegetable, but the amount of pesticides to be used is not known due to which the
cost as well as the environmental pollution gets affected. Different methods are used to find the disease on the leaves; Cerco
Spora-leaf Spot is again one type of disease in which it affects older leaves of mature plants. The spots are round or irregular
in shape yellowish brown, with purple, dark brown or blackish borders and white centers affected leaves become pale in
colour and finally fall off [1]. Uptill now the naked eye observation was used to calculate the number of pest on the leaves
but the results were subjective and it was not possible to get the accurate results. Grid counting method was used to calculate
the severity of the disease leaf, which improved the accuracy but this method has cumbersome operation process and time
consuming [2]. To measure severity of Rust disease on Soybean, disease spot have segmented by Sobel operator to find out
spot edge and plant disease severity has measured by calculating the quotient of disease spot area and leaf area [3]. To
identify on line of pest damage in pip fruit in orchards they used a wavelet based image processing technique and neural
network [4]. Different number of disease are affecting the cotton leaves and the color of the leaves are also changed, also
there are different shapes of the holes on the leaves. So calculating the major and minor axis of the holes is the major task.
They extracted the feature using the self organizing feature map together with a back-propagation neural network to
recognize the color of image and by using these techniques they used to analyzed the image [1]. To detect and calculate
automatically the number of pest they propose cognitive vision system that combines image processing, learning and
knowledge based techniques. For automatic detection they used the digital remote sensor, then the object was identified. The
main challenge was to identify the object for which the different techniques were used [5]. To calculate the severity of attack
of herbivorous on the leaves the video digitizer is used. A Tekmatic system Video Van Gogh digitizer card was equipped
with an IBM PC or compatible microcomputer and the card can the card can be interfaced with standard video camera for
rapidly measuring the percentage of leaf area lost (LAL) to herbivorous insects [10]. Disease infection on fruits is also
important to maintain the quality of the fruit, to increase the final yield. Many researches have been conducted for the same
as - classification of grape fruit peel disease have been done using color texture feature sets through a discriminate function
with 2.3 % standard deviation [7]. A strong demand now exists in many countries for non-chemical control methods for
pests or diseases, and this issue have not been studied enough [9].

www.theijes.com

The IJES

Page 39
Pest Detection on Leaves Using Poission’s Thresholding Techniques
II.

Methodology

Fig. 1: block diagram


Image Acquisition:A leaf containing the bioagressor i.e the pests is taken from the environment and its image is stored in
computer in JPEG format. The pest leaf is kept on the white background and is zoomed so that the picture taken
contains the leaf part and the white background.

Fig. 2: Image captured

Fig. 3: Gray image

Poisson’s Minimum Error Thresholding:For the initial binarization, we first compute the image into gray and then normalized image histogram,
denoted h(i), where i denotes the intensity of a pixel in the range {0, Imax}[8]. Here we use Poisson-distribution
based on minimum error thresholding algorithm. The normalized image histogram for the mixture of Poisson
distributions is written as[8]
h(i ) = P0 × p(i│0) + P1 × p(i│1) …(1)
where P0 and P1 are the a priori probabilities of the background and foreground regions[8].
p(i|j), j = 0, 1 are Poisson distributions with means μj [8].

www.theijes.com

The IJES

Page 40
Pest Detection on Leaves Using Poission’s Thresholding Techniques
For a threshold t, the Poisson mixture parameters are given by[8]
t

t

P0(t) = ∑ h(i)

µ0(t) = 1/P0(t) ∑ i × h(i)

IMAX
P1(t) = ∑ h(i)

IMAX
µ1(t) = 1/P1(t) ∑ i × h(i) …(2)

t=0

i=t+1

t=0

i=t+1

The optimal threshold t* is chosen to minimize an error criterion, as follows:[8]
t* = arg min {µ - p0(t) (ln p0(t) + µ0(t) ln µ0(t)) – p1(t) (ln
p1(t) + µ1(t) ln µ1(t))}
where μ is the mean intensity of the complete image. The result of thresholding IN (x, y) using t* is refined by
incorporating spatial continuity constraints.[8]

Fig. 4: poission’s threshold image


Layer Labelling:-

Layer labelling is used to label the connected components, the MATLAB has the direct instruction for labelling the
object. L = bwlabeln(BW) is the instruction which returns a label matrix, L, containing labels for the connected components
in BW. The input image BW can have any dimension; L is the same size as BW. The elements of L are integer values greater
than or equal to 0. The pixels labeled 0 are the background. The pixels labeled 1 make up one object; the pixels labeled 2
make up a second object; and so on. Here the layer labelling is used to first label the background and the leaf part then
labeled the pest on the leaves.



Training:Training sets are created and they can be evaluated, deleted, renamed and merged with signature from
other files training sets evaluation and editing permit complex classification with training that are derived from
more than one training method (supervised and/or unsupervised ). The training set parameters includes
following attributes in additional to standard attribute training sets.





The number of bands in input image (as processed in program).
The minimum and maximum data file value in each band for each sample or cluster.
The mean data file value for each band for each sample or cluster.
The number of pixel in the sample or cluster [11].

The training is done to get the RGB component of the input image. The number of select point is set to
acquire the data set so that it can be used to match the data set acquired from processing the image.


Pixel intensity matching:-

The pixel intensity used at the training data set is matched with the
data set of the image which is processed. The Euclidean distance is used to match the image with the query image. The
Euclidean is the ordinary distance between two points that one would measure with a ruler and is given by Pythagorean
formula. Suppose there are two points p and q of the line segment then the Euclidean distance between two point is (
) in
Cartesian coordinates if p = (p1, p2,….,pn) and q = (q1, q2,…, qn) are two points in Euclidean n-space, then the distance from p
to q, or from q to p is given by:

d(p,q) = d(q,p) =
hence the equation used to calculate the Euclidean distance between the training image and the image used for processing,
the minimum distance achieved between the set of training image and processed image gives the disease part on the leaf.

www.theijes.com

The IJES

Page 41
Pest Detection on Leaves Using Poission’s Thresholding Techniques
III.
RESULTS
We have tested our system over the database which consist of 148 samples of images in which some of
the images were infected with the disease and other images were having the pest on it. The images were
captured when the leaves were infested with the whiteflies, which was found manily on the bottom of leaves. the
main aim is to count the number of pest on the leaves. On training the numerical values of the pest were learned
on the subset of 30 images for pests and 79 images for disease leaves. The image contain the pest on the leaf in
which atleast one pest is been detected on the leaf.
Table I: Result table for detecting atleast one pest.
Types of leaves
1(79)
2(67)
Whole set(148)

FNR%
0.0
7.46
3.42

FPR%
2.53
1.49
2.09

Table II: Result table for detecting number of correct pest.
Types of leaves
1(79)
2(67)
Whole set(148)

FNR%
0.0
25.3
11.8

FPR%
2.53
1.49
2.09

To make use of our result table, we have separated it into two classes c1 and c2 , where the first class c1 has the 79
images which does not has a whitefly on the leaves but there are some disease on the leaves and the second class c2 consist
of whitefly on its leaves. The FPR i.e., false positive rate means the images for which the number of detected whiteflies is
greater than the actual whiteflies on the leaf (rate of over detection) and the FNR i.e., false negative rate means the images
for which the number of detected whiteflies is less than the actual whiteflies on the leaf (rate of under detection) [5] Table 1
and Table 2 summarizes the detection results. The figures represent the mean values of FNR and FPR for class C1, C2, and
for the whole image test set. Table 1 shows the result of detecting atleast one pest on the leaves i.e. the FNR and FPR
calculated was to detect atleast one pest from the number of pest on the leaves. Table 2 shows the result of detecting the
number of correct pest i.e. to detect the actual number of pest available on the leaves. The FNR are roughly similar for the
two configurations. The two overlapping whitefly have been segmented into one region though there were two whitefly on
the leaf, hence the system count one whitefly instead of two whitefly.

IV.

CONCLUSION

Hence using different techniques such as poission’s minimum error thresholding which was used for segmentation,
pixel labelling, the third mode rejection and extraction of ROI and so on. Certain training for the color model is performed
which is used in the final part in classification, which uses linear Euclidean classifier for the purpose. There are some
disadvantage i.e., different other bioaggressor are not extracted from the leaves and secondly if the pests are overlapped it is
difficult to count automatically. This system will be helpful to get the accurate result and the time requirement for counting
the pest will also get reduced.

REFERENCES
[1]
[2]
[3]
[4]
[5]

[6]
[7]
[8]

[9]
[10]
[11]

Mr. V. A. Gulhane & Dr. A. A. Gurjar.” Detection of Diseases on Cotton Leaves and Its Possible Diagnosis, “International Journal
of Image Processing (IJIP), Volume (5) : Issue (5) : 2011
Sanjay B. Patil, Dr. Shrikant K. Bodhe,” LEAF DISEASE SEVERITY MEASUREMENT USING IMAGE
PROCESSING,”International Journal of Engineering and Technology Vol.3 (5), 2011, 297-301
Shen Weizhong, Wu Yachun [at.el], “Grading method of leaf spot disease based on image processing,’’ IEEE, 2008, pp.491494.
Brendon J. Woodford, Nikola K. Kasabov and C. Howard Wearing,” Fruit Image Analysis using Wavelets.
Paul Boissard, Vincent Martin, Sabine Moisan,” A cognitive vision approach to early pest detection in greenhouse crops”, UR880
Unit´e de recherches int´egr´ees, F-06903 Sophia Antipolis, France b INRIA, ORION Team, BP93, F-06902 Sophia Antipolis,
France Accepted 20 November 2007
Kridsakron Auynirndronkool, Varinthon Jarnkoon,”Analysis of economic crop reflectance by field spectral signature, case study
sugarcane”, Journal of plant physiol, 2008, pp.1-9.
Dae Gwan Kim, Thomas F. Burks,”Classification of grape fruit peel diseases using color texture feature analysis”, IJABE, 2009,
pp.41-50.
Yousef Al-Kofahi, Wiem Lassoued, William Lee, and Badrinath Roysam, Senior Member, “Improved Automatic Detection and
Segmentation of Cell Nuclei in Histopathology Images”, IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL.
57, NO. 4, APRIL 2010.
Hanafi, A., 2003. Integrated production and protection today and in the future in greenhouse crops in the Mediterranean region.
Acta Horticulturae (ISHS) 614, 755–765.
William W. Hargrove, D. A. Crossley, “Video Digitiser for the rapid measurement of leaf area lost due to Herbivorous insecct”
Journal of Entomological Society of America, 1998,pp.591-598.
www.forest.mtu.edu

www.theijes.com

The IJES

Page 42

More Related Content

What's hot

Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
Tarun Kumar
 
Kapil dikshit ppt
Kapil dikshit pptKapil dikshit ppt
Kapil dikshit ppt
kapil dikshit
 
R-PI BASED DETECTION OF LUNG CANCER USING MRI IMAGE
R-PI BASED DETECTION OF LUNG CANCER USING MRI IMAGER-PI BASED DETECTION OF LUNG CANCER USING MRI IMAGE
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
Tarun Kumar
 
IRJET- Detection and Classification of Leaf Diseases
IRJET-  	  Detection and Classification of Leaf DiseasesIRJET-  	  Detection and Classification of Leaf Diseases
IRJET- Detection and Classification of Leaf Diseases
IRJET Journal
 
Segmentation of unhealthy region of plant leaf using image processing techniques
Segmentation of unhealthy region of plant leaf using image processing techniquesSegmentation of unhealthy region of plant leaf using image processing techniques
Segmentation of unhealthy region of plant leaf using image processing techniques
eSAT Journals
 
Wheat leaf disease detection using image processing
Wheat leaf disease detection using image processingWheat leaf disease detection using image processing
Wheat leaf disease detection using image processing
IJLT EMAS
 
EDGE DETECTION IN DIGITAL IMAGE USING MORPHOLOGY OPERATION
EDGE DETECTION IN DIGITAL IMAGE USING MORPHOLOGY OPERATIONEDGE DETECTION IN DIGITAL IMAGE USING MORPHOLOGY OPERATION
EDGE DETECTION IN DIGITAL IMAGE USING MORPHOLOGY OPERATION
IJEEE
 
Disease Detection in Plant Leaves using K-Means Clustering and Neural Network
Disease Detection in Plant Leaves using K-Means Clustering and Neural NetworkDisease Detection in Plant Leaves using K-Means Clustering and Neural Network
Disease Detection in Plant Leaves using K-Means Clustering and Neural Network
ijtsrd
 
Comparative Study on Machine Learning Algorithms for Network Intrusion Detect...
Comparative Study on Machine Learning Algorithms for Network Intrusion Detect...Comparative Study on Machine Learning Algorithms for Network Intrusion Detect...
Comparative Study on Machine Learning Algorithms for Network Intrusion Detect...
ijtsrd
 
IRJET- Plant Leaf Disease Detection using Image Processing
IRJET- Plant Leaf Disease Detection using Image ProcessingIRJET- Plant Leaf Disease Detection using Image Processing
IRJET- Plant Leaf Disease Detection using Image Processing
IRJET Journal
 
Crop Leaf Disease Diagnosis using Convolutional Neural Network
Crop Leaf Disease Diagnosis using Convolutional Neural NetworkCrop Leaf Disease Diagnosis using Convolutional Neural Network
Crop Leaf Disease Diagnosis using Convolutional Neural Network
ijtsrd
 
COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING ALGORITHMS FOR PLANT DISEA...
COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING ALGORITHMS FOR PLANT DISEA...COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING ALGORITHMS FOR PLANT DISEA...
COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING ALGORITHMS FOR PLANT DISEA...
International Research Journal of Modernization in Engineering Technology and Science
 
IRJET- An Expert System for Plant Disease Diagnosis by using Neural Network
IRJET- An Expert System for Plant Disease Diagnosis by using Neural NetworkIRJET- An Expert System for Plant Disease Diagnosis by using Neural Network
IRJET- An Expert System for Plant Disease Diagnosis by using Neural Network
IRJET Journal
 
IRJET- Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence Ma...
IRJET- Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence Ma...IRJET- Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence Ma...
IRJET- Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence Ma...
IRJET Journal
 
A Novel Approach for Tomato Diseases Classification Based on Deep Convolution...
A Novel Approach for Tomato Diseases Classification Based on Deep Convolution...A Novel Approach for Tomato Diseases Classification Based on Deep Convolution...
A Novel Approach for Tomato Diseases Classification Based on Deep Convolution...
Mohammad Shakirul islam
 
Comparative Analysis: Effective Information Retrieval Using Different Learnin...
Comparative Analysis: Effective Information Retrieval Using Different Learnin...Comparative Analysis: Effective Information Retrieval Using Different Learnin...
Comparative Analysis: Effective Information Retrieval Using Different Learnin...
RSIS International
 
IRJET- Detection of Plant Leaf Diseases using Machine Learning
IRJET- Detection of Plant Leaf Diseases using Machine LearningIRJET- Detection of Plant Leaf Diseases using Machine Learning
IRJET- Detection of Plant Leaf Diseases using Machine Learning
IRJET Journal
 

What's hot (19)

Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
Plant Leaf Disease Analysis using Image Processing Technique with Modified SV...
 
Kapil dikshit ppt
Kapil dikshit pptKapil dikshit ppt
Kapil dikshit ppt
 
R-PI BASED DETECTION OF LUNG CANCER USING MRI IMAGE
R-PI BASED DETECTION OF LUNG CANCER USING MRI IMAGER-PI BASED DETECTION OF LUNG CANCER USING MRI IMAGE
R-PI BASED DETECTION OF LUNG CANCER USING MRI IMAGE
 
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...
 
IRJET- Detection and Classification of Leaf Diseases
IRJET-  	  Detection and Classification of Leaf DiseasesIRJET-  	  Detection and Classification of Leaf Diseases
IRJET- Detection and Classification of Leaf Diseases
 
Segmentation of unhealthy region of plant leaf using image processing techniques
Segmentation of unhealthy region of plant leaf using image processing techniquesSegmentation of unhealthy region of plant leaf using image processing techniques
Segmentation of unhealthy region of plant leaf using image processing techniques
 
Wheat leaf disease detection using image processing
Wheat leaf disease detection using image processingWheat leaf disease detection using image processing
Wheat leaf disease detection using image processing
 
EDGE DETECTION IN DIGITAL IMAGE USING MORPHOLOGY OPERATION
EDGE DETECTION IN DIGITAL IMAGE USING MORPHOLOGY OPERATIONEDGE DETECTION IN DIGITAL IMAGE USING MORPHOLOGY OPERATION
EDGE DETECTION IN DIGITAL IMAGE USING MORPHOLOGY OPERATION
 
Imageprocessing
ImageprocessingImageprocessing
Imageprocessing
 
Disease Detection in Plant Leaves using K-Means Clustering and Neural Network
Disease Detection in Plant Leaves using K-Means Clustering and Neural NetworkDisease Detection in Plant Leaves using K-Means Clustering and Neural Network
Disease Detection in Plant Leaves using K-Means Clustering and Neural Network
 
Comparative Study on Machine Learning Algorithms for Network Intrusion Detect...
Comparative Study on Machine Learning Algorithms for Network Intrusion Detect...Comparative Study on Machine Learning Algorithms for Network Intrusion Detect...
Comparative Study on Machine Learning Algorithms for Network Intrusion Detect...
 
IRJET- Plant Leaf Disease Detection using Image Processing
IRJET- Plant Leaf Disease Detection using Image ProcessingIRJET- Plant Leaf Disease Detection using Image Processing
IRJET- Plant Leaf Disease Detection using Image Processing
 
Crop Leaf Disease Diagnosis using Convolutional Neural Network
Crop Leaf Disease Diagnosis using Convolutional Neural NetworkCrop Leaf Disease Diagnosis using Convolutional Neural Network
Crop Leaf Disease Diagnosis using Convolutional Neural Network
 
COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING ALGORITHMS FOR PLANT DISEA...
COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING ALGORITHMS FOR PLANT DISEA...COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING ALGORITHMS FOR PLANT DISEA...
COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING ALGORITHMS FOR PLANT DISEA...
 
IRJET- An Expert System for Plant Disease Diagnosis by using Neural Network
IRJET- An Expert System for Plant Disease Diagnosis by using Neural NetworkIRJET- An Expert System for Plant Disease Diagnosis by using Neural Network
IRJET- An Expert System for Plant Disease Diagnosis by using Neural Network
 
IRJET- Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence Ma...
IRJET- Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence Ma...IRJET- Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence Ma...
IRJET- Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence Ma...
 
A Novel Approach for Tomato Diseases Classification Based on Deep Convolution...
A Novel Approach for Tomato Diseases Classification Based on Deep Convolution...A Novel Approach for Tomato Diseases Classification Based on Deep Convolution...
A Novel Approach for Tomato Diseases Classification Based on Deep Convolution...
 
Comparative Analysis: Effective Information Retrieval Using Different Learnin...
Comparative Analysis: Effective Information Retrieval Using Different Learnin...Comparative Analysis: Effective Information Retrieval Using Different Learnin...
Comparative Analysis: Effective Information Retrieval Using Different Learnin...
 
IRJET- Detection of Plant Leaf Diseases using Machine Learning
IRJET- Detection of Plant Leaf Diseases using Machine LearningIRJET- Detection of Plant Leaf Diseases using Machine Learning
IRJET- Detection of Plant Leaf Diseases using Machine Learning
 

Viewers also liked

H03310038042
H03310038042H03310038042
H03310038042
theijes
 
K030102074084
K030102074084K030102074084
K030102074084
theijes
 
D0315025029
D0315025029D0315025029
D0315025029
theijes
 
H030102052055
H030102052055H030102052055
H030102052055
theijes
 
B0315011015
B0315011015B0315011015
B0315011015
theijes
 
E0313023027
E0313023027E0313023027
E0313023027
theijes
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
theijes
 
I030101048052
I030101048052I030101048052
I030101048052
theijes
 
M030101073078
M030101073078M030101073078
M030101073078
theijes
 
A03130109
A03130109A03130109
A03130109
theijes
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
theijes
 
B030102008010
B030102008010B030102008010
B030102008010
theijes
 
K030101060065
K030101060065K030101060065
K030101060065
theijes
 
C0314018022
C0314018022C0314018022
C0314018022
theijes
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
theijes
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
theijes
 
E03310026031
E03310026031E03310026031
E03310026031
theijes
 
E030102031037
E030102031037E030102031037
E030102031037
theijes
 
G0314046051
G0314046051G0314046051
G0314046051
theijes
 

Viewers also liked (19)

H03310038042
H03310038042H03310038042
H03310038042
 
K030102074084
K030102074084K030102074084
K030102074084
 
D0315025029
D0315025029D0315025029
D0315025029
 
H030102052055
H030102052055H030102052055
H030102052055
 
B0315011015
B0315011015B0315011015
B0315011015
 
E0313023027
E0313023027E0313023027
E0313023027
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
 
I030101048052
I030101048052I030101048052
I030101048052
 
M030101073078
M030101073078M030101073078
M030101073078
 
A03130109
A03130109A03130109
A03130109
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
 
B030102008010
B030102008010B030102008010
B030102008010
 
K030101060065
K030101060065K030101060065
K030101060065
 
C0314018022
C0314018022C0314018022
C0314018022
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
 
The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)The International Journal of Engineering and Science (The IJES)
The International Journal of Engineering and Science (The IJES)
 
E03310026031
E03310026031E03310026031
E03310026031
 
E030102031037
E030102031037E030102031037
E030102031037
 
G0314046051
G0314046051G0314046051
G0314046051
 

Similar to The International Journal of Engineering and Science (The IJES)

Foliage Measurement Using Image Processing Techniques
Foliage Measurement Using Image Processing TechniquesFoliage Measurement Using Image Processing Techniques
Foliage Measurement Using Image Processing Techniques
IJTET Journal
 
T2_219a.pdf
T2_219a.pdfT2_219a.pdf
T2_219a.pdf
NehaBhati30
 
Pine wilt disease spreading prevention system using semantic segmentation
Pine wilt disease spreading prevention system using semantic segmentation Pine wilt disease spreading prevention system using semantic segmentation
Pine wilt disease spreading prevention system using semantic segmentation
IJECEIAES
 
A Novel Machine Learning Based Approach for Detection and Classification of S...
A Novel Machine Learning Based Approach for Detection and Classification of S...A Novel Machine Learning Based Approach for Detection and Classification of S...
A Novel Machine Learning Based Approach for Detection and Classification of S...
IRJET Journal
 
IJSRED-V2I2P60
IJSRED-V2I2P60IJSRED-V2I2P60
IJSRED-V2I2P60
IJSRED
 
Pest Control in Agricultural Plantations Using Image Processing
Pest Control in Agricultural Plantations Using Image ProcessingPest Control in Agricultural Plantations Using Image Processing
Pest Control in Agricultural Plantations Using Image Processing
IOSR Journals
 
IRJET - Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence M...
IRJET - Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence M...IRJET - Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence M...
IRJET - Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence M...
IRJET Journal
 
IRJET- Crop Pest Detection and Classification by K-Means and EM Clustering
IRJET-  	  Crop Pest Detection and Classification by K-Means and EM ClusteringIRJET-  	  Crop Pest Detection and Classification by K-Means and EM Clustering
IRJET- Crop Pest Detection and Classification by K-Means and EM Clustering
IRJET Journal
 
IRJET- Plant Disease Identification System
IRJET- Plant Disease Identification SystemIRJET- Plant Disease Identification System
IRJET- Plant Disease Identification System
IRJET Journal
 
Vegetables detection from the glossary shop for the blind.
Vegetables detection from the glossary shop for the blind.Vegetables detection from the glossary shop for the blind.
Vegetables detection from the glossary shop for the blind.
IOSR Journals
 
Using deep learning algorithms to classify crop diseases
Using deep learning algorithms to classify crop diseasesUsing deep learning algorithms to classify crop diseases
Using deep learning algorithms to classify crop diseases
IJECEIAES
 
Plant Diseases Prediction Using Image Processing
Plant Diseases Prediction Using Image ProcessingPlant Diseases Prediction Using Image Processing
Plant Diseases Prediction Using Image Processing
IRJET Journal
 
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
IJERA Editor
 
Plant Monitoring using Image Processing, Raspberry PI & IOT
 	  Plant Monitoring using Image Processing, Raspberry PI & IOT 	  Plant Monitoring using Image Processing, Raspberry PI & IOT
Plant Monitoring using Image Processing, Raspberry PI & IOT
IRJET Journal
 
IRJET- Crop Leaf Disease Diagnosis using Convolutional Neural Network
IRJET- Crop Leaf Disease Diagnosis using Convolutional Neural NetworkIRJET- Crop Leaf Disease Diagnosis using Convolutional Neural Network
IRJET- Crop Leaf Disease Diagnosis using Convolutional Neural Network
IRJET Journal
 
EARLY BLIGHT AND LATE BLIGHT DISEASE DETECTION ON POTATO LEAVES USING CONVOLU...
EARLY BLIGHT AND LATE BLIGHT DISEASE DETECTION ON POTATO LEAVES USING CONVOLU...EARLY BLIGHT AND LATE BLIGHT DISEASE DETECTION ON POTATO LEAVES USING CONVOLU...
EARLY BLIGHT AND LATE BLIGHT DISEASE DETECTION ON POTATO LEAVES USING CONVOLU...
IRJET Journal
 
IRJET- Image Processing based Detection of Unhealthy Plant Leaves
IRJET- Image Processing based Detection of Unhealthy Plant LeavesIRJET- Image Processing based Detection of Unhealthy Plant Leaves
IRJET- Image Processing based Detection of Unhealthy Plant Leaves
IRJET Journal
 
IRJET- Leaf Disease Detection using Image Processing
IRJET- Leaf Disease Detection using Image ProcessingIRJET- Leaf Disease Detection using Image Processing
IRJET- Leaf Disease Detection using Image Processing
IRJET Journal
 
Paper id 71201958
Paper id 71201958Paper id 71201958
Paper id 71201958
IJRAT
 
Plant leaf detection through machine learning based image classification appr...
Plant leaf detection through machine learning based image classification appr...Plant leaf detection through machine learning based image classification appr...
Plant leaf detection through machine learning based image classification appr...
IAESIJAI
 

Similar to The International Journal of Engineering and Science (The IJES) (20)

Foliage Measurement Using Image Processing Techniques
Foliage Measurement Using Image Processing TechniquesFoliage Measurement Using Image Processing Techniques
Foliage Measurement Using Image Processing Techniques
 
T2_219a.pdf
T2_219a.pdfT2_219a.pdf
T2_219a.pdf
 
Pine wilt disease spreading prevention system using semantic segmentation
Pine wilt disease spreading prevention system using semantic segmentation Pine wilt disease spreading prevention system using semantic segmentation
Pine wilt disease spreading prevention system using semantic segmentation
 
A Novel Machine Learning Based Approach for Detection and Classification of S...
A Novel Machine Learning Based Approach for Detection and Classification of S...A Novel Machine Learning Based Approach for Detection and Classification of S...
A Novel Machine Learning Based Approach for Detection and Classification of S...
 
IJSRED-V2I2P60
IJSRED-V2I2P60IJSRED-V2I2P60
IJSRED-V2I2P60
 
Pest Control in Agricultural Plantations Using Image Processing
Pest Control in Agricultural Plantations Using Image ProcessingPest Control in Agricultural Plantations Using Image Processing
Pest Control in Agricultural Plantations Using Image Processing
 
IRJET - Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence M...
IRJET - Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence M...IRJET - Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence M...
IRJET - Plant Leaf Disease Diagnosis from Color Imagery using Co-Occurrence M...
 
IRJET- Crop Pest Detection and Classification by K-Means and EM Clustering
IRJET-  	  Crop Pest Detection and Classification by K-Means and EM ClusteringIRJET-  	  Crop Pest Detection and Classification by K-Means and EM Clustering
IRJET- Crop Pest Detection and Classification by K-Means and EM Clustering
 
IRJET- Plant Disease Identification System
IRJET- Plant Disease Identification SystemIRJET- Plant Disease Identification System
IRJET- Plant Disease Identification System
 
Vegetables detection from the glossary shop for the blind.
Vegetables detection from the glossary shop for the blind.Vegetables detection from the glossary shop for the blind.
Vegetables detection from the glossary shop for the blind.
 
Using deep learning algorithms to classify crop diseases
Using deep learning algorithms to classify crop diseasesUsing deep learning algorithms to classify crop diseases
Using deep learning algorithms to classify crop diseases
 
Plant Diseases Prediction Using Image Processing
Plant Diseases Prediction Using Image ProcessingPlant Diseases Prediction Using Image Processing
Plant Diseases Prediction Using Image Processing
 
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
www.ijera.com 68 | P a g e Leaf Disease Detection Using Arm7 and Image Proces...
 
Plant Monitoring using Image Processing, Raspberry PI & IOT
 	  Plant Monitoring using Image Processing, Raspberry PI & IOT 	  Plant Monitoring using Image Processing, Raspberry PI & IOT
Plant Monitoring using Image Processing, Raspberry PI & IOT
 
IRJET- Crop Leaf Disease Diagnosis using Convolutional Neural Network
IRJET- Crop Leaf Disease Diagnosis using Convolutional Neural NetworkIRJET- Crop Leaf Disease Diagnosis using Convolutional Neural Network
IRJET- Crop Leaf Disease Diagnosis using Convolutional Neural Network
 
EARLY BLIGHT AND LATE BLIGHT DISEASE DETECTION ON POTATO LEAVES USING CONVOLU...
EARLY BLIGHT AND LATE BLIGHT DISEASE DETECTION ON POTATO LEAVES USING CONVOLU...EARLY BLIGHT AND LATE BLIGHT DISEASE DETECTION ON POTATO LEAVES USING CONVOLU...
EARLY BLIGHT AND LATE BLIGHT DISEASE DETECTION ON POTATO LEAVES USING CONVOLU...
 
IRJET- Image Processing based Detection of Unhealthy Plant Leaves
IRJET- Image Processing based Detection of Unhealthy Plant LeavesIRJET- Image Processing based Detection of Unhealthy Plant Leaves
IRJET- Image Processing based Detection of Unhealthy Plant Leaves
 
IRJET- Leaf Disease Detection using Image Processing
IRJET- Leaf Disease Detection using Image ProcessingIRJET- Leaf Disease Detection using Image Processing
IRJET- Leaf Disease Detection using Image Processing
 
Paper id 71201958
Paper id 71201958Paper id 71201958
Paper id 71201958
 
Plant leaf detection through machine learning based image classification appr...
Plant leaf detection through machine learning based image classification appr...Plant leaf detection through machine learning based image classification appr...
Plant leaf detection through machine learning based image classification appr...
 

Recently uploaded

Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Tobias Schneck
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Product School
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Product School
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
Alison B. Lowndes
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Product School
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
Elena Simperl
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Ramesh Iyer
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Thierry Lestable
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
DianaGray10
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 

Recently uploaded (20)

Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 

The International Journal of Engineering and Science (The IJES)

  • 1. The International Journal Of Engineering And Science (IJES) ||Volume|| 2 ||Issue|| 10 ||Pages|| 39-42 ||2013|| ISSN (e): 2319 – 1813 ISSN (p): 2319 – 1805 Pest Detection on Leaves Using Poission’s Thresholding Techniques Sitaram Longani1, Prof.V.V. Dixit2 1 M.E. (Communication Network) Student, Sinhgad College of engineering, Pune- 41. Department of Electronics and Telecommunication, Sinhgad College of engineering, Pune- 41. 2 --------------------------------------------------------ABSTRACT-------------------------------------------------Different diseases and bioagressor are affecting the crops, due to which the plants cannot survive for a long duration. Mainly the bioagressor which is been frequently seen on the leaves of the plant is the whitefly. Our main aim is to count the number of whitefly on the leaves. Different techniques are used such as poission’s minimum error thresholding, learning, layer labelling, to count the number of pest on the leaves. The automatic counting of pests on the leaf helps in deciding the amount of pesticides to be sprayed on the leaf. This system is useful not only to count the number of pest on its mature stage but also it can count the number of stages at its middle stage and starting stage. We have compared our result with the manual method and its has been seen that automatic counting gives the greater accuracy. Keywords - whitefly, Digital image, Image segmentation, leaf, Thresholding technique ----------------------------------------------------------------------------------------------------------------------------- ---------Date of Submission: 11th, October, 2013 Date of Acceptance: 30th, October, 2013 ----------------------------------------------------------------------------------------------------------------------------- ---------- I. INTRODUCTION Our India is an agriculture country, most of the people in india are farmer and the other depends on the agriculture. Most of the scientists are doing research to increase the cultivity of crops. But one problem still exist which is a major concern of the cultivation of crop and that is crop diseases. Due to these problems, the cultivation decreases and hence all the farmers and in turn the country suffers the lack of cultivation of crop. Different types of pesticides are there in market which are used to avoid the damage to fruit and vegetable, but the amount of pesticides to be used is not known due to which the cost as well as the environmental pollution gets affected. Different methods are used to find the disease on the leaves; Cerco Spora-leaf Spot is again one type of disease in which it affects older leaves of mature plants. The spots are round or irregular in shape yellowish brown, with purple, dark brown or blackish borders and white centers affected leaves become pale in colour and finally fall off [1]. Uptill now the naked eye observation was used to calculate the number of pest on the leaves but the results were subjective and it was not possible to get the accurate results. Grid counting method was used to calculate the severity of the disease leaf, which improved the accuracy but this method has cumbersome operation process and time consuming [2]. To measure severity of Rust disease on Soybean, disease spot have segmented by Sobel operator to find out spot edge and plant disease severity has measured by calculating the quotient of disease spot area and leaf area [3]. To identify on line of pest damage in pip fruit in orchards they used a wavelet based image processing technique and neural network [4]. Different number of disease are affecting the cotton leaves and the color of the leaves are also changed, also there are different shapes of the holes on the leaves. So calculating the major and minor axis of the holes is the major task. They extracted the feature using the self organizing feature map together with a back-propagation neural network to recognize the color of image and by using these techniques they used to analyzed the image [1]. To detect and calculate automatically the number of pest they propose cognitive vision system that combines image processing, learning and knowledge based techniques. For automatic detection they used the digital remote sensor, then the object was identified. The main challenge was to identify the object for which the different techniques were used [5]. To calculate the severity of attack of herbivorous on the leaves the video digitizer is used. A Tekmatic system Video Van Gogh digitizer card was equipped with an IBM PC or compatible microcomputer and the card can the card can be interfaced with standard video camera for rapidly measuring the percentage of leaf area lost (LAL) to herbivorous insects [10]. Disease infection on fruits is also important to maintain the quality of the fruit, to increase the final yield. Many researches have been conducted for the same as - classification of grape fruit peel disease have been done using color texture feature sets through a discriminate function with 2.3 % standard deviation [7]. A strong demand now exists in many countries for non-chemical control methods for pests or diseases, and this issue have not been studied enough [9]. www.theijes.com The IJES Page 39
  • 2. Pest Detection on Leaves Using Poission’s Thresholding Techniques II. Methodology Fig. 1: block diagram  Image Acquisition:A leaf containing the bioagressor i.e the pests is taken from the environment and its image is stored in computer in JPEG format. The pest leaf is kept on the white background and is zoomed so that the picture taken contains the leaf part and the white background. Fig. 2: Image captured Fig. 3: Gray image  Poisson’s Minimum Error Thresholding:For the initial binarization, we first compute the image into gray and then normalized image histogram, denoted h(i), where i denotes the intensity of a pixel in the range {0, Imax}[8]. Here we use Poisson-distribution based on minimum error thresholding algorithm. The normalized image histogram for the mixture of Poisson distributions is written as[8] h(i ) = P0 × p(i│0) + P1 × p(i│1) …(1) where P0 and P1 are the a priori probabilities of the background and foreground regions[8]. p(i|j), j = 0, 1 are Poisson distributions with means μj [8]. www.theijes.com The IJES Page 40
  • 3. Pest Detection on Leaves Using Poission’s Thresholding Techniques For a threshold t, the Poisson mixture parameters are given by[8] t t P0(t) = ∑ h(i) µ0(t) = 1/P0(t) ∑ i × h(i) IMAX P1(t) = ∑ h(i) IMAX µ1(t) = 1/P1(t) ∑ i × h(i) …(2) t=0 i=t+1 t=0 i=t+1 The optimal threshold t* is chosen to minimize an error criterion, as follows:[8] t* = arg min {µ - p0(t) (ln p0(t) + µ0(t) ln µ0(t)) – p1(t) (ln p1(t) + µ1(t) ln µ1(t))} where μ is the mean intensity of the complete image. The result of thresholding IN (x, y) using t* is refined by incorporating spatial continuity constraints.[8] Fig. 4: poission’s threshold image  Layer Labelling:- Layer labelling is used to label the connected components, the MATLAB has the direct instruction for labelling the object. L = bwlabeln(BW) is the instruction which returns a label matrix, L, containing labels for the connected components in BW. The input image BW can have any dimension; L is the same size as BW. The elements of L are integer values greater than or equal to 0. The pixels labeled 0 are the background. The pixels labeled 1 make up one object; the pixels labeled 2 make up a second object; and so on. Here the layer labelling is used to first label the background and the leaf part then labeled the pest on the leaves.  Training:Training sets are created and they can be evaluated, deleted, renamed and merged with signature from other files training sets evaluation and editing permit complex classification with training that are derived from more than one training method (supervised and/or unsupervised ). The training set parameters includes following attributes in additional to standard attribute training sets.     The number of bands in input image (as processed in program). The minimum and maximum data file value in each band for each sample or cluster. The mean data file value for each band for each sample or cluster. The number of pixel in the sample or cluster [11]. The training is done to get the RGB component of the input image. The number of select point is set to acquire the data set so that it can be used to match the data set acquired from processing the image.  Pixel intensity matching:- The pixel intensity used at the training data set is matched with the data set of the image which is processed. The Euclidean distance is used to match the image with the query image. The Euclidean is the ordinary distance between two points that one would measure with a ruler and is given by Pythagorean formula. Suppose there are two points p and q of the line segment then the Euclidean distance between two point is ( ) in Cartesian coordinates if p = (p1, p2,….,pn) and q = (q1, q2,…, qn) are two points in Euclidean n-space, then the distance from p to q, or from q to p is given by: d(p,q) = d(q,p) = hence the equation used to calculate the Euclidean distance between the training image and the image used for processing, the minimum distance achieved between the set of training image and processed image gives the disease part on the leaf. www.theijes.com The IJES Page 41
  • 4. Pest Detection on Leaves Using Poission’s Thresholding Techniques III. RESULTS We have tested our system over the database which consist of 148 samples of images in which some of the images were infected with the disease and other images were having the pest on it. The images were captured when the leaves were infested with the whiteflies, which was found manily on the bottom of leaves. the main aim is to count the number of pest on the leaves. On training the numerical values of the pest were learned on the subset of 30 images for pests and 79 images for disease leaves. The image contain the pest on the leaf in which atleast one pest is been detected on the leaf. Table I: Result table for detecting atleast one pest. Types of leaves 1(79) 2(67) Whole set(148) FNR% 0.0 7.46 3.42 FPR% 2.53 1.49 2.09 Table II: Result table for detecting number of correct pest. Types of leaves 1(79) 2(67) Whole set(148) FNR% 0.0 25.3 11.8 FPR% 2.53 1.49 2.09 To make use of our result table, we have separated it into two classes c1 and c2 , where the first class c1 has the 79 images which does not has a whitefly on the leaves but there are some disease on the leaves and the second class c2 consist of whitefly on its leaves. The FPR i.e., false positive rate means the images for which the number of detected whiteflies is greater than the actual whiteflies on the leaf (rate of over detection) and the FNR i.e., false negative rate means the images for which the number of detected whiteflies is less than the actual whiteflies on the leaf (rate of under detection) [5] Table 1 and Table 2 summarizes the detection results. The figures represent the mean values of FNR and FPR for class C1, C2, and for the whole image test set. Table 1 shows the result of detecting atleast one pest on the leaves i.e. the FNR and FPR calculated was to detect atleast one pest from the number of pest on the leaves. Table 2 shows the result of detecting the number of correct pest i.e. to detect the actual number of pest available on the leaves. The FNR are roughly similar for the two configurations. The two overlapping whitefly have been segmented into one region though there were two whitefly on the leaf, hence the system count one whitefly instead of two whitefly. IV. CONCLUSION Hence using different techniques such as poission’s minimum error thresholding which was used for segmentation, pixel labelling, the third mode rejection and extraction of ROI and so on. Certain training for the color model is performed which is used in the final part in classification, which uses linear Euclidean classifier for the purpose. There are some disadvantage i.e., different other bioaggressor are not extracted from the leaves and secondly if the pests are overlapped it is difficult to count automatically. This system will be helpful to get the accurate result and the time requirement for counting the pest will also get reduced. REFERENCES [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] Mr. V. A. Gulhane & Dr. A. A. Gurjar.” Detection of Diseases on Cotton Leaves and Its Possible Diagnosis, “International Journal of Image Processing (IJIP), Volume (5) : Issue (5) : 2011 Sanjay B. Patil, Dr. Shrikant K. Bodhe,” LEAF DISEASE SEVERITY MEASUREMENT USING IMAGE PROCESSING,”International Journal of Engineering and Technology Vol.3 (5), 2011, 297-301 Shen Weizhong, Wu Yachun [at.el], “Grading method of leaf spot disease based on image processing,’’ IEEE, 2008, pp.491494. Brendon J. Woodford, Nikola K. Kasabov and C. Howard Wearing,” Fruit Image Analysis using Wavelets. Paul Boissard, Vincent Martin, Sabine Moisan,” A cognitive vision approach to early pest detection in greenhouse crops”, UR880 Unit´e de recherches int´egr´ees, F-06903 Sophia Antipolis, France b INRIA, ORION Team, BP93, F-06902 Sophia Antipolis, France Accepted 20 November 2007 Kridsakron Auynirndronkool, Varinthon Jarnkoon,”Analysis of economic crop reflectance by field spectral signature, case study sugarcane”, Journal of plant physiol, 2008, pp.1-9. Dae Gwan Kim, Thomas F. Burks,”Classification of grape fruit peel diseases using color texture feature analysis”, IJABE, 2009, pp.41-50. Yousef Al-Kofahi, Wiem Lassoued, William Lee, and Badrinath Roysam, Senior Member, “Improved Automatic Detection and Segmentation of Cell Nuclei in Histopathology Images”, IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 57, NO. 4, APRIL 2010. Hanafi, A., 2003. Integrated production and protection today and in the future in greenhouse crops in the Mediterranean region. Acta Horticulturae (ISHS) 614, 755–765. William W. Hargrove, D. A. Crossley, “Video Digitiser for the rapid measurement of leaf area lost due to Herbivorous insecct” Journal of Entomological Society of America, 1998,pp.591-598. www.forest.mtu.edu www.theijes.com The IJES Page 42