Essay: Agricultural Pest Detection and Classification

Abstract
In agriculture research of automatic pest detection
and disease detection is essential research topic as it may prove
benefits in monitoring large fields of Cotton crops and thus
automatically detect symptoms of disease as soon as they appear
on Cotton plant. The studies of plant disease refer to the studies
of visually observable patterns of a particular plant. Nowadays
crops faces many diseases such as damage of the insect/pest is
one of the major disease. A common practice for Cotton plant
scientists is to estimate the damage of plant (leaf, stem) because
of pest by an eye on a scale based on percentage of affected area.
It results in subjectivity and low throughput. This paper provides
a advances in various methods used to study plant diseases/traits
because of pest using image processing. The methods studied are
for increasing throughput and reducing subjectiveness arising
from human experts in detection of plant diseases.
I. INTRODUCTION
Computer vision techniques have great significance on the
automatic identification of the images of Cotton insect pests.
Those techniques not only can decrease the labour, but also
can improve the speed and precision of the identification
and diagnosis, when compared to manual method. In this
regard, recognition of paddy field insect pests is challenging
because the insect pests are highly articulated, they exhibit
a high degree of intra-pest variation in size and colour, and
some insect pests are difficult to distinguish visually, despite
prominent dorsal patterning. The manual classification of such
insect pests in paddy fields can be time consuming and requires
substantial technical expertise. The task becomes more
challenging when insect pests are to be recognised from still
images using an automated system. Images of one insect pest
may be taken from different viewpoints, cluttered background,
or may suffer transformation such as rotation, noise, etc. So
it is likely that two images of the same insect pest will be
different. To address these challenges, we have adopted the
gradient-based features in classifying images of Cotton crops
insect pests. The primary advantage of this approach is that it
is invariant to changes in pose and scale as long as the features
can be reliably detected. Furthermore, with an appropriate
choice of classifier, not all features need to be detected in
order to achieve high classification accuracy. Hence, even if
some features are occluded or fail to be detected, the method
can still succeed.
In this paper various techniques to identify the diseases and
pests using infected images of various symptoms and leaf spots
and pests on crops were studied. Images are captured by digital
camera mobile and processed using image growing, then the
Figure 1: Selected species of cotton insect pests.
part of the leaf sport has been used for the classification
purpose of the train and test. The technique evolved into
the system is both Image processing techniques and advance
computing techniques. Image analysis can be applied for the
following purposes:
1) To detect diseased leaf, stem, fruit and pests on Cotton
crops.
2) To detect quantity of affected area by disease and pests.
3) To find the boundaries of the affected area.
4) To determine the color of the affected area.
5) To determine size and shape of leaf and pests.
6) To identify the Object correctly.
The rest of this paper is organized as Section II provides
short review of agricultural pest detection and classification
techniques. Section III provides short summery of revived
classification techniques. In end of paper we conclude about
revived techniques.
II. REVIEW OF AGRICULTURAL PEST DETECTION AND
CLASSIFICATION TECHNIQUES
In this section different pest detection techniques implemented
by different researchers from all over the world are
summarised. P. Revathi et. al[7] detected Cotton leaf spot
diseases in [7] by using Homogenous Segmentation based
Edge Detection Techniques. This system is analyzed with
eight types of cotton leaf diseases they are Fusarium wilt,
Verticillium wilt,Root rot,Boll rot,Grey mildew ,Leaf blight
,Bacterial blight,Leaf curl.In these work symptoms of cotton
leaf spot images are captured by mobile and classification is
done by using neural network. In this work a homogeneity
operator can take the difference of the center pixel and a
pixel that is two or three pixels away. The main aim Research
2
work is to use Homogeneity-based edge detector segmentation,
which takes the result of any edge detector and divides it by the
average value of the area. This work has been implemented in
the real time software and produces best results. The software
is very fast and time intense, low cost, automatically identify
the diseases and pest recommendation to farmers through a
mobile phone.
Ajay A. et. al [5] presented Eigen feature regularization
and extraction technique by this detection of three diseases
can be done. This system is having more accuracy, than that
of the other feature detection techniques. With this method
about 90% of detection of Red spot i.e. fungal disease
on cotton leaves is detected. Dheeb Al Bashish and et. al
2010[6] proposed image processing based work is consists
of the following main steps, In the first step the acquired
images are segmented using the K-means techniques and then
secondly the segmented images are passed through a pretrained
neural network .The images of leaves taken from Al-
Ghor area in Jordan. Five diseases that are prevalent in cotton
leaves were selected for this research; they are: Early scorch,
Cottony mold, Ashen mold, late scorch, tiny whiteness. The
experimental result indicates that the neural network classifier
that is based on statistical classification support accurate and
automatic detection of leaf diseases with a precision of around
93%.
R. G. Mundada et. al[24] have proposed a system to
detect white flies, aphids and trips on the infected crops in
greenhouse. Images of the infected cotton leaf are captured by
a camera and pre-processed by converting these images from
RGB to gray scales and filtering in order to obtain an enhanced
image set of pests. properties such as region properties and
gray covariance matrix properties such as entropy, mean,
standard deviation, contrast, energy, correlation and eccentricity
were extracted from these images. The classification was
performed by the use of support vector machines. proposed
system is used for rapid detection of pests and exhibits the
same performance level as a classical manual approach. R.
K. Samanta et. al[25] presented system for tea insect pests
classification using correlation-based feature selection (CFS)
and incremental back propagation learning network (IBPLN).
The authors have created a database concentrating on eight
major insect pests from the records of different tea gardens
of North-Bengal districts of India. The database consists of
609 instances belonging to eight classes described by 11
attributes (signs and symptoms); all of which are nominal. The
classification was performed using artificial neural networks.
The classification results were compared with the original
feature set and reduced feature set. Their study demonstrates
that CFS can be used for reducing the feature vector and
CFS+IBPLN combination can be used for other classification
problems.
T. Jaware et. al[26] presented a Fast and accurate method
for detection and classification of plant diseases. The proposed
algorithm is tested on main five diseases on the plants; they
are: Early Scorch, Cottony mold, Ashen Mold, Late scorch,
tiny whiteness. Initially the RGB image is acquired then
a color transformation structure for the acquired RGB leaf
image is created. After that color values in RGB converted
to the space specified in the color transformation structure.
In the next step, the segmentation is done by using K-means
clustering technique. After that the mostly green pixels are
masked. Further the pixels with zero green, red and blue values
and the pixels on the boundaries of the infected object were
completely removed. Then the infected cluster was converted
into HIS format from RGB format. In the next step, for each
pixel map of the image for only HIS images the SGDM
matrices were generated. Finally the extracted feature was
recognized through a pre-trained neural network. The results
show that the proposed system can successfully detect and
classify the diseases with a precision between 83% and 94%.
Y. Tian et. al[27] presented a method to monitor four main
wheat plant diseases: Powdery Mildew, leaf rust Puccinia
triticina, leaf blight, Puccinia striiformis and three features
obtained are color feature, texture feature, and shape feature
which further used as training sets for three corresponding
classifiers. This system is mainly classified into three main
steps: data acquisition, feature extraction, and classifier design.
Multiple Classifier System (MCS) includes number of
classifiers which can provide higher classification accuracy.
T. Rumpf et. al[28] presented a system for the detection
and differentiation of sugar beet diseases based on Support
Vector Machines and spectral vegetation indices. They used
Cercospora leaf spot, leaf rust and powdery mildew diseased
leaves as study samples. The main aim was to identify these
diseases before their symptoms became visible. In this proposed
work nine spectral vegetation were used as features for
an automatic classification. The experimental result indicates
that the discrimination between healthy sugar beet leaves and
diseased leaves classification accuracy up to 97%.
S. Phadikar et. al[29] presented an automated classification
system based on the morphological changes caused by brown
spot and the leaf blast diseases of rice plant. To classify the
diseases Radial distribution of the hue from the centre to the
boundary of the spot images has been used as feature by
using Bayes and SVM Classifier. The feature extraction for
classification of rice leaf diseases is processed in the following
steps: firstly images acquired of diseased rice leaves from
fields. Secondly preprocessing the images to remove noise
from the damaged leaf and then enhanced the quality of
image by using the [mean filtering technique. Thirdly Otsus
segmentation algorithm was applied to extract the infected
portion of the image, and then radial hue distribution vectors
of the segmented regions computed which are used as feature
vectors. Here classification performed in two different phases
.In first phase uninfected and the diseased leaves are classified
based on the number of peaks in the Histogram.In the second
phase the leaf diseases are classified by Bayes classifier.
This system gives 68.1% and 79.5% accuracies for SVM and
Bayesclassifier based system respectively.
S. S. Sannakki et. al[30] in paper titled A Hybrid Intelligent
System for Automated Pomegranate Disease Detection and
Grading proposed a system not only identifies various diseases
of pomegranate plant but also determines the stage in which
the disease is. The methodology is divided into four steps:
1) The images acquisition where the images were captured
by using digital camera.
3
2) The image preprocessing creates enhanced image that is
more useful for human observer. Image preprocessing
uses number of techniques like image resize, filtering,
segmentation, morphological operations etc.
3) Once the image has been enhanced and segmented in
image postprocessing noises like stabs, empty holes
etc. are removed by applying morphological operations,
region filling. Further the features are extracted like color
, shape ,texture.
4) Once the features are extracted to which disease class the
query image in belongs different machine learning techniques
are used like Artificial neural networks, Decision
tree learning, genetic algorithms, Clustering, Bayesian
networks, Support Vector Machines, Fuzzy Logic etc.
P. Keskar et. al[31] presented a leaf disease detection and
diagnosis system for inspection of affected leaves and identifying
the type of disease. This system is comprised of four
stages: To improve the appearance of acquired images image
enhancement techniques are applied. The enhancement is done
in three steps: Transformation of HSI to color space in first
stage .In the next stage analyzing the histogram of intensity
channel to get the threshold. Finally intensity adjustment by
applying the threshold. . The second stage is segmentation
which includes adaption of fuzzy feature algorithm parameter
to fit the application in concern. The feature ex traction stage is
comprised of two steps spot isolation and spot extraction. For
identification of spot identification algorithm is used is called
component labeling. In feature extraction phase three features
are extracted namely color, size and shape of the spots. In
fourth stage classification is performed by Artificial Neural
Network.
A. Meunkaewjinda et. al[32] presented diagnosis system
for grape leaf diseases is proposed. The proposed system is
composed of three main parts: Firstly grape leaf color extraction
from complex background, secondly grape leaf disease
color extraction and finally grape leaf disease classification.
In this analysis back-propagation neural network with a selforganizing
feature map together is utilize to recognize colors
of grape leaf. Further MSOFM and GA deployed for grape
leaf disease segmentation and SVM for classification. Finally
filtration of resulting segmented image is done by Gabor
Wavelet and then SVM is again applied to classify the types
of grape leaf diseases. This system can classify the grape leaf
diseases into three classes: Scab disease, rust disease and no
disease. Even though there are some limitations of extracting
ambiguous color pixels from the background of the image.
The system demonstrates very promising performance for any
agricultural product analysis.
L. Liu et. al[33] a system for classifying the healthy and
diseased part of rice leaves using BP neural network as
classifier. In this study rice brown spot was select as a research
object. The images of rice leaves were acquired from the
northern part of Ningxia Hui autonomous region. Here the
color features of diseases and healthy region were served as
input values to BP neural network. The result shows that this
method is also suitable to identify the other diseases.
III. SUMMERY ON CLASSIFICATION TECHNIQUES
This section will discuss some of the popular classification
techniques with their advantages and disadvantages that are
used for plant leaf and pests classification. In plant pests
and leaf classification leaf is classified based on its different
morphological features. Some of the classification techniques
used are Neural Network, Genetic Algorithm, Support Vector
Machine and Principal Component Analysis, k-Nearest
Neighbor Classifier. Plant leaf disease classification has wide
application in Agriculture.
1) k-Nearest Neighbor: The main disadvantage of the KNN
algorithm is that it is a slow learner, i.e. it does not learn
anything from the training data and simply make use the
training data itself for classification. Another disadvantage
is this method is also rather slow if there are a large
number of training examples as the algorithm must have
to compute the distance and sort all the training data at
each prediction. Also it is not robust to noisy data in case
of large number of training examples. The most serious
disadvantage of nearest neighbor methods is that they are
very sensitive to the presence of irrelevant parameters.
2) Support Vector Machine: Main advantages of SVM
are Its prediction accuracy is high, Its working is robust
when training examples contain errors, Its simple
geometric interpretation and a sparse solution and
Like neural networks the computational complexity of
SVMs does not depend on the dimensionality of the
input space. Drawbacks are this classifier involves long
training time, In SVM it is difficult to understand the
learned function (weights) and the large number of
support vectors used from the training set to perform
classification task.
3) Artificial Neural Network (ANN): it is simplest single
layer networks whose weights and biases could be
trained to produce a correct target vector when presented
with the corresponding input vector and it can solve only
linear problems
4) Probabilistic Neural Networks: The main disadvantage
of PNN is it requires large storage space but PNNs
are much faster than multilayer perceptron networks,
PNNs are used in on-line applications where a real-time
classifier is required
5) Fuzzy Logic: As Fuzzy logic classifiers has very high
speed they are preferable in cases where there is limited
precision in the data values or when classification is
required in real time and Drawback of Fuzzy logic
as classifier is dimensionality because of this classifier
is inadequate for problems having a large number of
features. Also it gives poor performance while there is
a limited amount of knowledge that the designer can
incorporate in the system.
IV. CONCLUSION
This paper provides the survey of different techniques for
pests and leaf disease detection. Main aim of this work is
to study various pest detection techniques, characteristics of
pest and various diseases on cotton crops with the help of
4
image processing techniques likes image segmentation, feature
extraction, classification, with the help of these techniques
we will be identifying various agricultural pests on various
crops or specially cotton crops. which helps the farmer to
take correct action to increase production. For the detection of
pests speed and accuracy is important factor to be considered.
Hence there is working on development of automatic, efficient,
fast and accurate system which is use for detection pests
and disease on unhealthy cotton leaf. speed and accuracy are
the main factors keeping in mind and hence Work can be
extended for development of hybrid algorithms with neural
networks in order to increase the recognition rate of final
classification process. In future we can development of real
time implementation of this algorithm in farm for continuous
monitoring and detection of plant diseases. In real time system,
we can monitor and give exact solution to avoid various
diseases on cotton plant.
REFERENCES
[1] Ivan R. Kennedy, Francisco Sanchez-Bayo and Robert A. Caldwell, ‘Cotton
Pesticides In Perspective’, Australian Cotton Cooperative Research
Centre Environmental Protection: Pesticides,2nd Edition, A discussion
paper regarding research on pesticide management for the cotton industry.
[2] P. Revathi, M. Hemalatha, ‘Cotton Leaf Spot Diseases Detection Utilizing
Feature Selection with Skew Divergence Method’, International Journal
of Scientific Engineering and Technology, Volume 3, Issue 1, PP 22-30,1
Jan 2014.
[3] Qinghai He, Benxue Ma, Duanyang Qu, Qiang Zhang, Xinmin Hou
and Jing Zhao. ‘Cotton Pests and Diseases Detection based on Image
Processing’, TELKOMNIKA, Volume 11, Issue 6, pp. 3445-3450, June
2013.
[4] Mr. V. A. Gulhane and Dr. A. A. Gurjar ‘Detection of Diseases on
Cotton Leaves and Its Possible Diagnosis ‘, International Journal of
Image Processing (IJIP), Vol 5, Issue 5, pp 590-598, June-2011.
[5] Ajay A. Gurjar, Viraj A. Gulhane,’Disease Detection On Cotton Leaves
by Eigenfeature Regularization and Extraction Technique’, International
Journal of Electronics, Communication and Soft Computing Science and
Engineering(IJECSCSE), Volume 1, Issue 1, 2006.
[6] Vivek Chaudhari and C. Y. Patil,’Disease Detection of Cotton Leaves
Using Advanced Image Processing’, International Journal of Advanced
Computer Research, Volume 4, Number 2, Issue 15, June-2014.
[7] P.Revathi and M.Hemalatha,’Identification of Cotton Diseases Based
on Cross Information Gain Deep Forward Neural Network Classifier
with PSO Feature Selection’, International Journal of Engineering and
Technology (IJET), Vol 5, No 6, pp 4637-4642, Jan 2014.
[8] Alexandre A. Bernardes, Jonathan G. Rogeri, Roberta B. Oliveira, Norian
Marranghello and Aledir S. Pereira,’ Identification of Foliar Diseases in
Cotton Crop’, Universidade Estadual Paulista (UNESP).
[9] V. Premalatha, Dr. M. G. Sumithra, S. Deepak and P. Rajeswari,’
Implementation of Spatial FCM for Leaf Image Segmentation in
Pest Detection’, International Journal of Advanced Research in Computer
Science and Software Engineering, Volume 4, Issue 10, October 2014.
[10] Calvin Fauche, Mark Gaskel, Stven T. Koike, Jeff Mitchell and Richard
Smith’Insect pest management for organic crops’, University of California,
Division of Agricultural and Natural Resources.
[11] S. Phadikar, J. Sil, and A. K. Das,’ Classification of Rice Leaf Diseases
Based on Morphological Changes’, International Journal of Information
and Electronics Engineering, Vol. 2, No. 3, May 2012.
[12] Pranjali Vinayak Keskar, Shubhangi Nimba Masare, Manjusha Suresh
Kadam and Prof. Mrs. Seema U.Deoghare,’ Leaf Disease Detection and
Diagnosis’, International Journal of Emerging Trends in Electrical and
Electronics (IJETEE) Vol. 2, Issue. 2, April-2013.
[13] Zacharias N. Voulgaris,’Discernibility Concept in Classification Problems’,
University of London, may 2009.
[14] A. Meunkaewjinda, P. Kumsawat, K. Attakitmongcol and Sri
kaew,’Grape leaf disease detection from color imagery using hybrid
intelligent system’,proceedings of ECTI-CON, 2008.
[15] Libo Liu, Guomin Zhou,’Extraction of the Rice Leaf Disease Image
Based on BP Neural Network’, IEEE, 2009.
[16] Satish Madhogaria, Marek Schikora, Wolfgang Koch, Daniel
Cremers,’Pixel-Based Classification Method for Detecting Unhealthy
Regions in Leaf Images’, Informatik Informatik schafft Communities
41. Jahrestagung der Gesellschaft fr Informatik , vol. 4. issue 7, 2011
Berlin.
[17] Sannakki S.S., Rajpurohit V.S., Nargund V.B., Arun Kumar R.and Yallur
P.S.,’ A Hybrid Intelligent System for Automated Pomgranate Disease
detection and Grading’, International Journal of Machine Intelligence,
Volume 3, Issue 2,pp-36-44, 2011.
[18] Chen Jiajuan, Ji Shouwen, Li Juan, Zhao Xuedu. ‘Automatic Measurement
of Danger Degree of Cotton Insect Pests Using Computer Vision’,
Transactions of the Chinese Society of Agricultural Engineering, vol. 02,
pp. 157-160, 2001.
[19] R. G. Mundada and V. V. Gohokar, ‘ Detection and classification of
pests in greenhouse using image processing’, IOSR Journal of Electronics
and Communication Engineering, vol. 5, pp. 57-63, 2013.
[20] R. K. Samanta and I. Ghosh, ‘ Tea insect pests classification based on
artificial neural networks’, International Journal of Computer Engineering
Science (IJCES), vol. 2, issue. 6, 2012.
[21] D.D. Hardee, J.W. Van Duyn, M.B. Layton and R.D. Bagwell, ‘ Bt Cotton
Management of the Tobacco Budworm-Bollworm Complex’,United
States Department of Agriculture Agricultural Research Service, ARS154
January 2001.
[22] D.D. Hardee, J.W. Van Duyn, M.B. Layton and R.D. Bagwell, ‘Integrated
pest Management Practice for Cotton’,Ministry of Agriculture,
Department of Agriculture and Cooperation, Directorate of Plant Protection,
Quarantine and Storage, Government of India, 2003-04.
[23] Dr CD Mayee, Dr P Singh, Dr AB Dongre, Dr MRK Rao and Dr Sheo
Raj, ‘TRANSGENIC Bt COTTON’, Central Institute for Cotton Research
Nagpur, CICR Technical Bulletin No: 22,
[24] R. G. Mundada and V. V. Gohokar, ‘ Detection and classification of
pests in greenhouse using image processing, IOSR Journal of Electronics
and Communication Engineering, vol. 5, pp. 57-63, 2013.
[25] R. K. Samanta and I. Ghosh, ‘ Tea insect pests classification based on
artificial neural networks, International Journal of Computer Engineering
Science (IJCES), vol. 2, issue. 6, 2012.
[26] Tushar H Jaware, Ravindra D Badgujar and Prashant G Patil,’Crop
disease detection using image segmentation, Proceedings of Conference
on Advances in Communication and Computing (NCACC12), April 21,
2012.
[27] Yuan Tian, Chunjiang Zhao,Shenglian Lu,and Xinyu Guo,’SVM- based
Multiple Classifier System for Recognition of Wheat Leaf Diseases,
Proceedings of 2010 Conference on Dependable Computing (CDC2010)
vol. 20, no. 22, 2010 Yichang, China.
[28] T. Rumpf,A. K. Mahlein,U. Steiner,E. C. Oerke, H.W. Dehne,
L.Plumer,’Early detection and classification of plant diseases with Support
Vector Machines based on hyperspectral reflectance,Elsvier, 2010.
[29] S. Phadikar, J. Sil, and A. K. Das,’ Classification of Rice Leaf Diseases
Based on Morphological Changes, International Journal of Information
and Electronics Engineering, Vol. 2, No. 3, May 2012.
[30] Pranjali Vinayak Keskar, Shubhangi Nimba Masare, Manjusha Suresh
Kadam and Prof. Mrs. Seema U.Deoghare,’ Leaf Disease Detection and
Diagnosis, International Journal of Emerging Trends in Electrical and
Electronics (IJETEE) Vol. 2, Issue. 2, April-2013.
[31] Zacharias N. Voulgaris,’Discernibility Concept in Classification Problems,
University of London, may 2009.
[32] A. Meunkaewjinda, P. Kumsawat, K. Attakitmongcol and Sri
kaew,’Grape leaf disease detection from color imagery using hybrid
intelligent system,proceedings of ECTI-CON, 2008.
[33] Libo Liu, Guomin Zhou,’Extraction of the Rice Leaf Disease Image
Based on BP Neural Network, IEEE, 2009.in here…