ISSN (Online) 2321 – 2004

ISSN (Print) 2321 – 5526

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN ELECTRICAL, ELECTRONICS, INSTRUMENTATION AND CONTROL ENGINEERING
And
National Conference on Advanced Innovation in Engineering and Technology (NCAIET-2015)

Alva’s Institute of Engineering and Technology, Moodbidri

Vol. 3, Special Issue 1, April 2015

Early Detection and Classification of Pests Using

Image Processing
Sreelakshmi M1, Padmanayana2
2nd Year M.Tech, Srinivas Institute of Technology, India1
Associate Professor, Srinivas Institute of Technology, India2

Abstract: Early pest detection is a major challenge in agriculture field. The easiest way, to control the pest infection is
the use of pesticides. But the excessisive use of pesticides are harmful to plants, animals as well as human beings.
Integrated pest management combines biological and physical methods to prevent pest infection. The techniques of
machine vision and digital image Processing are extensively applied to agricultural science and it have great
perspective especially in the plant protection field, which ultimately leads to crops management. This paper deals with
a new type of early detection of pests system. Images of the leaves affected by pests are acquired by using a digital
camera. The leaves with pest images are processed for getting a gray colored image and then using feature extraction,
image classification techniques to detect pests on leaves. The images are acquired by using a digital camera . The
images are then transferred to a PC and represented in MATLAB software. The RGB image is then converted into gray
scale image and the feature extraction techniques are applied on that image. The Support Vector Machine classifier is
used to classify the pest types.

Index Terms: Early pest detection, feature extraction, image processing, pests, SVM (Support Vector Machine).

I. INTRODUCTION
India is an agricultural country. 70 percent of the people their features and drawbacks.
mainly depends upon agriculture. So increasing the
productivity of crops is an important matter now. Most of A. Detection of Pests Using Video Analysis
the scientists are doing their researches on this field. By This work combines image processing techniques as well
using their new techniques and practical implementations as knowledge based technique[1] .It will detect only
this is very easy. But one of the most important problem whiteflies. The resulst of this system are more reliable and
now exists is „pest infection‟ on plants. This paper mainly accurate than that of the manual methods. This is actually
focuses on greenhouse crops. There are different crops a multidisciplinary cognitive vision system that combines
cultivated under greenhouse. for example, vegetables like different types of techniques like computer vision ,
cucumber, potato, tomato etc and flower plants like rose, artificial intelligence, image processing etc. In this work,
jasmine etc. The most common pests which will affect on they chose rose plant as the testing crop and white fly as
this green house crops are whiteflies a, aphids and thrips. the pest for testing. The early stage of detection was quite
One way to control the pest infection is by using the difficult. So they chose adult flies. But some problems
pesticides. Pesticides will suppress particular species of were there in detection of adult also. The adult may fly
pests. Pesticides are detrimental for the environment and away during the image capturing time. So they chose to
produce considerable damage to eco systems. scan the leaves of rose when flies were not active. The
future scope of the work is to detect whiteflies in its early
The excessicive use of pesticides will pollute air, water, stage.
and soil. Carried by the wind pesticides suspensions
contaminate other areas. In this paper, we focus on early B. Method which use Sticky Traps.
pest detection. This implies to regular observation the The goal of Detection of insects by a video camera
plants. Images are acquired using cameras. Then the network[2] is to detect the pest infection on leaves by
acquired image has to be processed to interpret the image using a video analysis. The traditional methods will take
contents by image processing methods. The focus of this more time to detect and count the pests. Because of this
paper is on the interpretation of image for pest detection. reason they have developed an automatic system based on
video analysis. They used 5 wireless cameras in
II. LITERATURE SURVEY greenhouse. They chose rose as a crop for testing . sticky
In this section we will discuss some methods which are traps are used in this work. Sticky traps are nothing but a
presently used for the early detection of pests in sticky material which is having some colours to attract the
greenhouse crops along with their advantages and pests. For the detection of insects, they used video
disadvantages. The methods are explained below with segmentation algorithms with learning and adaptation

Copyright to IJIREEICE DOI 10.17148/IJIREEICE 239

 ISSN (Online) 2321 – 2004
ISSN (Print) 2321 – 5526

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN ELECTRICAL, ELECTRONICS, INSTRUMENTATION AND CONTROL ENGINEERING
And
National Conference on Advanced Innovation in Engineering and Technology (NCAIET-2015)

Alva’s Institute of Engineering and Technology, Moodbidri

Vol. 3, Special Issue 1, April 2015

techniques. The adaptive system can be used in any of the image. Different types of filters are available. Low
weather conditions. The future scope of this system is to pass filters are smoothening filters, it will pass only low
detect new types of pests in early stage. frequency signals and eliminate all the high frequency
III. PROPOSED METHOD signals. High pass filters are sharpening filters, and it will
For this study, whiteflies and aphids are chosen because eliminate all the low frequency signals and pass only high
this pest requires early detection and treatment to prevent frequency signals. Band pass filters will pass the signals
durable infection. Samples are collected by using the pan which is having a specific range of frequencies. In our
tilt camera with zoom in greenhouse as shown in system we are using smoothening filter. The purpose of
Fig.1.The acquired Images are given to the local machine smoothing is to reduce noise and improve the visual
and the image processing techniques will takes place. quality of the image. Spatial filters are applied to both
static and dynamic images, whereas temporal images are
applied only to dynamic images. The simplest
smoothening filter is average filter. It consists of a 3X3
matrix of 1 and it is divided by 9.

3) Feature Extraction
Feature extraction is the most important part of this
project. Some properties of the images are considered
Fig. 1. Proposed System architecture here. The different types of properties includes region
properties, gray covariance matrix properties etc. The
properties standard deviation, entropy, contrast etc are
A. Methodology extracted from the image and are used to train the dataset
1) Image capturing for the SVM classification. Support Vector Machines
The first step of every image processing application is (SVM's) are a relatively new learning method used for
image acquisition or image capturing. The images of binary classification. The basic idea is to find a hyper
leaves are captured by using the camera and it will store it plane which separates the d-dimensional data perfectly
in some formats like .PNG, .JPG, .JPEG etc. into its two classes. The different types of properties of an
image is listed in the table below.
2) Image pre-processing
Image preprocessing is used to create an enhanced and TABLE I: PROPERTIES OF AN IMAGE
please full version of the captured image. The image Returns the mean value of
preprocessing steps used in the system are: 1) Conversion Mean the elements along different
of RGB image to gray image 2) Resizing of the image 3) parameters of an array
Filtering of the image.
Computes the standard
Standard Deviation deviation of the values in
a) Conversion of RGB to Gray Image
matrix.
In RGB color model, each color appears in its primary
Returns a measure of
spectral components of red, green, and blue. The color of a
Contrast intensity contrast between
pixel is made up of three components; red, green, and blue
pixels.
(RGB). The disadvantages of RGB models are, it requires
large space to store and it will take more time to process. Returns the sum of squired
Energy
So there is a need for converting the RGB model to Gray elements in the glcm.
model . Scalar specifying the number
Filled Area
of pixels in filled area
b) Resizing of the Image
Resizing is an important step in image preprocessing. The
acquired image is resized according to the requirement of 4. Detection and Classification
the system. Resizing of the image: Resizing is nothing but, In this module the affected and unaffected images are
changing the dimensions of an image. compared by using the dataset provide in the SVM. If it is
an affected image again it is compared by using the second
The captured image is resized using some resizing dataset provided in the SVM.
methods according to the requirement of the system. There From this comparison the type of pest can be detected
are different methods for the resizing of images. Blinear,
Bicubic and Nearest neighborhood interpolation are the
common resizing methods. Here in our system, we are
using bicubic method.
c) Filtering of the image
Filtering is nothing but, eliminating the unwanted portion

Copyright to IJIREEICE DOI 10.17148/IJIREEICE 240

 ISSN (Online) 2321 – 2004
ISSN (Print) 2321 – 5526

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN ELECTRICAL, ELECTRONICS, INSTRUMENTATION AND CONTROL ENGINEERING
And
National Conference on Advanced Innovation in Engineering and Technology (NCAIET-2015)

Alva’s Institute of Engineering and Technology, Moodbidri

Vol. 3, Special Issue 1, April 2015

Fig. 2. Database for classification affected. Also further the affected category is divided into
IV. FLOWCHART two classes, aphids and whiteflies. For this classification
Flowchart for the proposed system is given in figure 3. we have used one more SVM classifier.
The images are acquired by using camera and it is filtered
by using bicubic filters to avoid unwanted noise portions. The different properties which decide that they are
This is actually the image preprocessing step. The next whiteflies or aphids are shown in table 3. The graph for
step is svm classification to detect the pest infection. If the different properties is shown in figure 5. Based on this the
image is affected, then again it is applied to the svm to SVM is trained and input image of affected leaf is given to
detect the type of pest. the second support vector machine which will generate the
output as 1 or 0 based on the parameters of the input
image. 1 is for aphids and 0 is for whiteflies.

TABLE II. DIFFERENT PARAMETERS

Fig. 3. Flowchart for the proposed method

V. RESULTS
The results obtained by performing the operations are
shown below. The different parameters which are
calculated for given data base are shown in table 2. The
graph of the different parameters is also shown in fig. 4
and from the analysis of that we have decided to choose
Standard deviation and contrast as deciding or
classification factors. The graph shown in fig. 6 shows that
the training to the SVM is done with 100% accuracy. We
have divided it into two categories affected and
unaffected. Here 1 represents unaffected and 0 represents

Copyright to IJIREEICE DOI 10.17148/IJIREEICE 241

 ISSN (Online) 2321 – 2004
ISSN (Print) 2321 – 5526

INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN ELECTRICAL, ELECTRONICS, INSTRUMENTATION AND CONTROL ENGINEERING
And
National Conference on Advanced Innovation in Engineering and Technology (NCAIET-2015)

Alva’s Institute of Engineering and Technology, Moodbidri

Vol. 3, Special Issue 1, April 2015

Fig. 4. Graph of different parameters [2]. Vincent Martin and Sabine Moisan, “Early Pest Detection in
Greenhouses”. INRIA Sophia Antipolis M´editerrann´ee, PULSAR
TABLE III. DIFFERENT PARAMETERS FOR team 2004 route des Lucioles, BP93
CLASSIFICATION [3]. Jayamala K. Patil1 , Raj Kumar, “Advances In Image Processing
For Detection Of Plant Diseases” Journal Of Advanced
Bioinformatics Applications and Research ISSN 0976-2604 Vol 2,
Issue 2, June-2011, pp 135-141
[4]. Ikhlef Bechar and Sabine Moisan, “On-line counting of pests in a
greenhouse using computer vision”. published in "VAIB 2010 -
Visual Observation and Analysis of Animal and Insect Behavior
(2010)"
[5]. Paul Boissarda, Vincent Martin, “A cognitive vision approach to
early pest detection in greenhouse crops”. computers and
electronics in agriculture 6 2 ( 2 0 0 8 ) 81–93
[6]. B.Cunha.“Application of Image Processing in Characterisation of
Plants.” IEEE Conference on Industrial Electronics.2003.

Fig. 5. Graph of different parameters

VI. CONCLUSION
Image processing technique plays an important role in the
detection of the pests. Our first objective is to detect
whiteflies, aphids and thrips on greenhouse crops. We
propose a novel approach for early detection of pests. To
detect objects we use pan tilt camera with zoom. So
without disturbing the pests we are able to take the image.
It illustrates the collaboration of complementary
disciplines and techniques, which led to an automated,
robust and versatile system. The prototype system proved
reliable for rapid detection of pests. It is rather simple to
use and exhibits the same performance level as a classical
manual approach. Our goal is to detect the pests as early as
possible and reduce the use of pesticides.

REFERENCES
[1]. [1]. Martin,V.Thonnat,. “A Learning Approach For Adaptive Image
Segmentation.” In Proceedings of IEEE Trans.Computers and
Electronics in Agriculture.2008

Copyright to IJIREEICE DOI 10.17148/IJIREEICE 242