From the ancient years, humans and other social species directly & indirectly dependent on Plants. Plants play an enormous role in human life by providing them food for living, wood for houses and other resources to live life.So, human should take care of plants and agricultural crops. But apart from the human, various natural factors are there that are responsible for destroying the growth of plants like unavailability of accurate plant resources, deficiency of sunlight, weather conditions, lack of expert knowledge for the accurate use of pesticides. The major factor responsible for this destruction of plant growth is diseases. Early detection and accurate identification of diseases can control the spread of infection.In the earlier days, it was not easy to identify the plant diseases but with the advancements of digital technology, it becomes easy to identify plant disease with image processing techniques. In this paper, an exploration is made on the exiting approaches of plant leaf disease detection using image processing approach. Also a discussion is made on the major disease types like fungal, bacterial and viral diseases. Different authors have presented the different approaches for the identification of leaf diseases for the different plant types.

1. IJEMT Volume 4, Issue 4 ( OCT-DEC, 2016) ISSN: 2320-7043 2016
International Journal of Engineering & Management Technology [http://www.ijemt.net]
An Exploration on the Identification of Plant Leaf Diseases
using Image Processing Approach
Vishal Mani Tiwari&Tarun Gupta
Computer Science, RadhaGovind Group of Institutions, Meerut, India
tiwarikivisha53@gmail.com
Abstract— From the ancient years, humans and other
social species directly & indirectly dependent on Plants.
Plants play an enormous role in human life by providing
them food for living, wood for houses and other resources
to live life.So, human should take care of plants and
agricultural crops. But apart from the human, various
natural factors are there that are responsible for
destroying the growth of plants like unavailability of
accurate plant resources, deficiency of sunlight, weather
conditions, lack of expert knowledge for the accurate use
of pesticides. The major factor responsible for this
destruction of plant growth is diseases. Early detection
and accurate identification of diseases can control the
spread of infection.In the earlier days, it was not easy to
identify the plant diseases but with the advancements of
digital technology, it becomes easy to identify plant disease
with image processing techniques. In this paper, an
exploration is made on the exiting approaches of plant leaf
disease detection using image processing approach. Also a
discussion is made on the major disease types like fungal,
bacterial and viral diseases. Different authors have
presented the different approaches for the identification of
leaf diseases for the different plant types.
Keywords— Plant Leaf Diseases,Image Processing,
Agriculture crops, Disease Symptoms
I. INTRODUCTION
India is an agricultural country where in about seventy
percentage of the population is dependent on productivity of
agricultural crops/plants [1]. Farmers have wide range of
diversity to select suitable Fruit and Vegetable crops. But due
to increasing disease types in plants/agricultural crops, risk of
crops quality and growth is also increasing. Diseases are the
natural factor that can cause some serious effects on plants
which ultimately reduces productivity, quality and quantity of
products [2]. Manual detection of plant diseases just increases
the human efforts as it is not easy to check each individual
plant. Also the manual detection is not appropriate method.
However, the cultivation of these crops for optimum yield and
quality product is highly technical. It can be improved with
the aid of technological support. To evaluate the seriousness
of plant diseases, it is essential to develop advanced, speedy
and accurate disease detection technologies.The main part of
plant to examine the plant diseases is leaf. The detection and
classification of leaf diseases accurately is the key to prevent
the agriculture loss [3]. Different plant leaf bears different
diseases. There are a list of methods and classifiers to detect
plant leaf diseases. The considered methods for plant leaf
disease are explained as existing work in section IV.Here, the
analysis is made on the plant leaf disease detection using
image processing approach. The basic steps of image
processing [4] are image acquisition, pre-processing (Image
Contrast Enhancement), image segmentation, feature
extraction, leaf disease detection & classification. These steps
are described as below:
• Image Acquisition: Image acquisition involves the
steps to obtain the plant leaf and capture the high
quality images to create the required database. The
efficiency of the concept depends upon the quality of
database image. So, images should be considered of
high quality with RGB color.
• Image Pre-processing: Image preprocessing involves
the steps of image contrast enhancement. Here, the
captured image is enhanced to remove the noise from
image, and then RGB color image is converted into
HSV plane image.
• Image Segmentation: Image segmentation is applied
to simplify the illustration of image with segments so
that it can be easily analysed. Image segmentation is
performed to segment the disease affected and
unaffected portions of the leaf.
• Feature Extraction: After the segmentation, disease
portion from the image is extracted. This leaf diseases
area is treated as region of interest for the image
processing. Then, further features are extracted based
47

2. IJEMT Volume 4, Issue 4 ( OCT-DEC, 2016) ISSN: 2320-7043 2016
International Journal of Engineering & Management Technology [http://www.ijemt.net]
on the disease symptoms that are used to detect the
disease types.
• Leaf Disease Detection and classification: Then,
classifiers are used for the training and testing of the
dataset. These classifiers may be fuzzy logic based, k-
nearest neighbour, support vector machine, neural
network, etc. These methods are used to classify and
detect the diseased and healthy leaves.
The basic process of image processing used for plant leaf
disease analysis is shown in figure 1.
Figure 1: Basic concept of Image Processing
Plant diseases are analyzed with the symptoms available
on the leaf. There can be various methods to sense the disease
symptoms like Visible Spectroscopy, Light Reflectance,
Remote Sensing, Thermograph Techniques, Laser Sensing [5].
Visible spectroscopy techniques applied in soil testing
and characterization. There are various methods like NIR
reflectance spectroscopy, Raman spectroscopy, VIS, VV, etc.
which are applied in agriculture sector. Light reflect work on
law of reflection, and the result shows the reflection occurs off
a curved surface or off a flat surface. Light reflectance is
used for disease classification. Each disease has own
fundamental color properties and light reflectance works on
the bases of wave length and spectrum. Remote sensing
technology is used in agriculture for yield crop estimation. It
depends on the spatial resolution of the digital image and it is
affected in growing crops estimation. This method is more
robust because it's established the relation between yield
monitor data and remotely sensed images. Thermograph
techniques are depending upon the biomass of the fruit or
disease. This technique refers to identifying and classifying
between fruit and shrubs and trees. Laser sensors are used for
fruit recognitions technique. Image processing and laser based
application systems are used for navigating a tractor through
the alleyway of a citrus grove.
In this way, plant leaf diseases can be analysed with the
help of available symptoms. Rest of the paper is organized in
the following manner. Section II describes the different
disease types with symptoms. Section III explains the
literature review and Section IV concludes the paper.
II. DIFFERENT DISEASE TYPES AND SYMPTOMS
The major categories of plant leaf diseases are based on
viral, fungal and bacteria [6]. Here are some common
symptoms that should be kept in mind if plant growth seems
low.
A. Fungal disease symptoms
Plant leaf diseases, those caused by fungus are discussed
below and shown in Figure 2. e.g. Late blight caused by the
fungus. Initially it affects older leaves that look like, water-
soaked and spot of grey-green color. Further disease affect
increases, affects other leaves also and older spots becomes
darken.
Figure 2: Fungal Disease Symptoms
B. Bacterial disease symptoms
The disease is characterized by tiny pale green spots which
soon come into view as water- soaked. The lesions enlarge
and then appear as dry dead spots as shown in Figure 3.
Figure 3: Bacterial Disease Symptoms
C. Viral disease symptoms
Image Acquisition
Image Segmentation
Feature Extraction
Disease Detection & Classification
Image Pre-Processing
48

3. IJEMT Volume 4, Issue 4 ( OCT-DEC, 2016) ISSN: 2320-7043 2016
International Journal of Engineering & Management Technology [http://www.ijemt.net]
Among all plant leaf diseases, those caused by viruses are
the most difficult to diagnose. Viruses produce no telltale
signs that can be readily observed and often easily confused
with nutrient deficiencies and herbicide injury. Aphids,
leafhoppers, whiteflies and cucumber beetles insects are
common carriers of this disease, e.g. Mosaic Virus, Look for
yellow or green stripes or spots on foliage, as shown in Figure
4. Leaves might be wrinkled, curled and growth may be
stunted.
Figure 4: Viral Disease Symptoms
III.LITERATURE REVIEW
In this section, the existing work of plant leaf disease
detection is presented. Various authors have used the different
approaches to detect the leaf diseases for different types of
plants and crops etc. The review of these considered
approaches is summarised in table 1 with their key features.
Sjadojevic et al. [7] have presented the concept of deep
convolution neural network (CNN) and fine tuning for the
identification of plant leaf diseases. Authors have considered
thirteen different types of dataset images with healthy leaf
images for the experimentation. Deep learning based Caffe
framework has been used along with the set of weights
learned on a very large dataset by authors. The core of
framework is developed in C++ and provides command line,
Python, and MATLAB interfaces. Authors have used the 10-
fold cross validation test for the accuracy assessment. The
overall results shows the accuracy of 96 % and precision value
lie between 91 % to 96 %.Fine-tuning has not shown
significant changes in the overall accuracy, but augmentation
process had greater influence to achieve respectable results.
Naik and Sivappagari [8] have presented the plant leaf
disease detection by incorporating the concepts of genetic
algorithm, neural network and support vector machine. Here,
support vector machine is used for the detection and
classification of leaf diseases. Genetic algorithm has been
used for the image segmentation. For the experimentation,
authors have used the dataset of guava, cotton, beans, moang
and lemon leaf images. Accuracy is evaluated for both of
SVM and neural network. Authors have evaluated the Neural
network based obtained accuracy shows efficient results as
compare to SVM.
Mohanty et al. [9] have used the concept of deep
convolutional neural network for the analysis of plant leaf
diseases. Authors have used the PlantVillage dataset having
38 classes based 54, 306 images for the experimentation. This
dataset consists of 14 crop species and 26 types of disease
affected plants. Deep learning based architecture of AlexNet
and GoogLeNet have been considered. Training mechanism of
transfer learning and training from scratch approaches have
been used. Testing is also performed with different ration
aspect of training and testing. Authors have shown the
accuracy of 99.35 % for the disease analysis. But there were
some limitations with the concept. Approach is limited to
applied dataset and presented approach is not able to detect
the leaf diseases if the leaf side changed apart from the front
area.
Bhog and Pawar [10] have incorporated the concept of
neural network for the classification of cotton leaf disease
analysis. For segmentation, K-means clustering has been used.
Different cotton leaf diseases are like Red spot, white spot,
Yellow spot, Alternaria and Cercospora on the Leaf. For
experimentation, MATLAB toolbox has been used. The
recognition accuracy for K-Mean Clustering method using
Euclidean distance is 89.56% and the execution time for K-
Mean Clustering method using Euclidean distance is 436.95
second.
Ramakrishnan et al. [11]has used back propagation
algorithm for the identification of groundnut leaf diseases.
Cercospora is the common groundnut disease. Its further stage
is cercosposiumpersonatum, then phaeoisariopsis and final
stage is alternaris. This classification with the proposed
concept shows efficient results.
Singh et al. [12] has presented the existing work for the
detection of unhealthy region of plant leaves. Authors have
described the framework for the detection and classification of
plat leaf diseases. Authors have also performed an important
step of image segmentation for leaf disease detection. For
segmentation, genetic algorithm is used by the authors and
segmented the healthy and unhealthy region of the plants. The
overall results are efficient for plant leaf diseases but authors
have also suggested to use Bayes classifier, ANN, Fuzzy
Logic etc. for the further improvement of concepts.
Dandawate and Kokare[13] have used support vector
machine concept for the detection and classification of
49

4. IJEMT Volume 4, Issue 4 ( OCT-DEC, 2016) ISSN: 2320-7043 2016
International Journal of Engineering & Management Technology [http://www.ijemt.net]
soybean plants as diseased or healthy species. Authors have
used the SIFT approach that automatically recognizes plant
species by their leaf shape. The proposed concept for soybean
plant diseases shows an average accuracy of 93.79%. For
experimentation, authors have prepared the data manually and
launch a mobile application for the farmers. The main
objective of the research is to build an autonomous decision
support system that can help for the plant leaf diseases
information over the mobile internet.
Sannakki et al. [14]has used feed forward back propagation
Neural Network based technique for the diagnosis and
classification of diseases in grape leaf. Author has used the
images of grape leaf with complex background for the
diagnosis as input. Further anisotropic diffusion is used to
remove the noise of the image which is further segmented
using k-means clustering. Finally results are observed using
neural network. Results are experimented on downy mildew
and powdery mildew images with simulation in MATLAB.
Confusion matrix is considered with the true positive and false
positive parameters for the validation of results. The author
claimed to have the training accuracy of 100% if used hue
feature alone.
Akhtar et al. [15] have used the support vector machine
approach for the classification and detection of rose leaf
diseases as black spot and anthracnose. Authors have used the
threshold method for segmentation and Ostu’s algorithm was
used to define the threshold values. In this approach, features
of DWT, DCT and texture based eleven haralick features are
extracted which are further used with SVM approach and
shows efficient accuracy value.
TABLE I
SUMMARIZATION OF PLANT LEAF DISEASE DETECTION APPROACHES
Author and Year
Type of Plants and
Diseases
Classification
Technique
Key Features
Sjadojevic et al. (2016)
[7]
13 different type of
images
Deep Convolution
Neural Network (CNN)
and Fine Tuning
• Used Deep learning based CaffeNet
framework
• Fine-tuning has not shown significant
changes in the overall accuracy.
Naik and Sivappagari
(2016) [8]
Guava, Cotton, Beans,
Moang And Lemon Leaf
Images
Neural Network and
Support Vector Machine
• Neural network based obtained
accuracy shows efficient results as
compare to SVM
Mohanty et al. (2016) [9]
PlantVillage dataset
having 14 crop species
and 26 types of disease
Deep Convolutional
Neural Network
• Approach is limited to applied dataset
and presented approach is not able to
detect the leaf diseases if the leaf side
changed apart from the front area.
Bhog and Pawar (2016)
[10]
Cotton Leaf Disease Neural Network
• Accuracy for K-Mean Clustering
method using Euclidean distance is
89.56%.
Ramakrishnan et al.
(2015) [11]
Groundnut leaf diseases
Back Propagation Neural
Network
• Discussed the disease of Cercospora
and its various stages in groundnut leaf
Singh et al. (2015) [12] Different plant leafs Genetic algorithm
• The overall results of genetic algorithm
are efficient for detection of plant leaf
diseases but authors have also
suggested using Bayes classifier, ANN,
Fuzzy Logic etc. for the further
improvement of concepts.
Dandawate and Kokare Soybean plants Support Vector Machine • Soybean plant diseases show an
50

5. IJEMT Volume 4, Issue 4 ( OCT-DEC, 2016) ISSN: 2320-7043 2016
International Journal of Engineering & Management Technology [http://www.ijemt.net]
(2015) [13] average accuracy of 93.79%.
• Also a mobile based application
launched for soybean disease detection
Sannakki et al. (2013)
[14]
Grape diseases
Back Propagation Neural
Network
• Grape diseases viz. Powdery
Mildewand Downy Mildew are
identified.
• Accuracy is well Obtained.
Akhtar et al. (2013) [15] Rose leaf diseases Support Vector Machine
• Features of DWT, DCT and texture
based eleven haralick features are
extracted which are further used with
SVM approach and shows efficient
accuracy value.
IV.CONCLUSIONS
Human life is completely dependent upon nature and
plants. So, there should be special methods to save plants from
diseases. The decrease in crop production also affects the
economy of the country. There is the need of appropriate
research method that can automatically detect the plant leaf
disease. In this research paper, we have determined the
different approaches used by different authors for different
kind of plant diseases. The considered concept used for
classification are SVM, neural network, genetic algorithm,
discriminant function approach, back propagation neural
network etc. The detected diseases plant are grape, soybean,
citrus, grape, groundnut and some other available dataset with
their different disease types. From these classification and
detection method, there is need to develop some optimized
method as existing approaches are not fit for multiple leaf
disease types and if any of concept shows efficient results then
those results are with limitations.
REFERENCES
[1]. Arivazhagan, S., R. NewlinShebiah, S. Ananthi, and S.
Vishnu Varthini. "Detection of unhealthy region of
plant leaves and classification of plant leaf diseases
using texture features." Agricultural Engineering
International: CIGR Journal 15, no. 1 (2013): 211-217.
[2]. Kranz, J. "Measuring plant disease." In Experimental
techniques in plant disease epidemiology, ISSN no.
978-3-642-95534-1, page no. 35-50. Springer Berlin
Heidelberg, 1988.
[3]. James, W. Clive. "Assessment of plant diseases and
losses." Annual Review of Phytopathology Vol. 12,
issue no. 1, page no. 27-48, 1974.
[4]. Khirade, Sachin D., and A. B. Patil. "Plant Disease
Detection Using Image Processing." In Computing
Communication Control and Automation (ICCUBEA),
2015 International Conference on, pp. 768-771. IEEE,
2015.
[5]. Mahlein, Anne-Katrin, Erich-Christian Oerke, Ulrike
Steiner, and Heinz-Wilhelm Dehne. "Recent advances
in sensing plant diseases for precision crop
protection." European Journal of Plant Pathology 133,
no. 1 (2012): 197-209.
[6]. Oostendorp, Michael, Walter Kunz, Bob Dietrich, and
Theodor Staub. "Induced disease resistance in plants by
chemicals." European Journal of Plant Pathology 107,
no. 1 (2001): 19-28.
[7]. Sladojevic, Srdjan, Marko Arsenovic, AndrasAnderla,
DubravkoCulibrk, and DarkoStefanovic. "Deep Neural
Networks Based Recognition of Plant Diseases by Leaf
Image Classification." Computational Intelligence and
Neuroscience 2016 (2016).
[8]. Naik, M. Ravindra, and Chandra Mohan Reddy
Sivappagari. "Plant Leaf and Disease Detection by
Using HSV Features and SVM
Classifier." International Journal of Engineering
Science 3794 (2016).
[9]. Mohanty, Sharada P., David P. Hughes, and Marcel
Salathé. "Using Deep Learning for Image-Based Plant
Disease Detection." Frontiers in Plant Science 7
(2016).
[10]. Bhong, Vijay S., and B. V. Pawar. "Study and Analysis
of Cotton Leaf Disease Detection Using Image
Processing." International Journal of Advanced
Research in Science, Engineering and Technology 3,
no. 2 (2016).
[11]. Ramakrishnan, M., and A. Nisha. "Groundnut leaf
disease detection and classification by using back
probagation algorithm." In Communications and Signal
Processing (ICCSP), 2015 International Conference
51

6. IJEMT Volume 4, Issue 4 ( OCT-DEC, 2016) ISSN: 2320-7043 2016
International Journal of Engineering & Management Technology [http://www.ijemt.net]
on, ISNB no. 978-1-4799-8081-9, page no. 0964-0968.
IEEE, 2015.
[12]. Singh, Vijai, and A. K. Misra. "Detection of unhealthy
region of plant leaves using image processing and
genetic algorithm." In Computer Engineering and
Applications (ICACEA), 2015 International Conference
on Advances in, ISBN no 978-1-4673-6911-4, page no.
1028-1032. IEEE, 2015.
[13]. Dandawate, Yogesh, and RadhaKokare. "An automated
approach for classification of plant diseases towards
development of futuristic Decision Support System in
Indian perspective." In Advances in Computing,
Communications and Informatics (ICACCI), 2015
International Conference on, ISNB no. 978-1-4799-
8792-4, page no. 794-799. IEEE, 2015.
[14]. Sannakki, Sanjeev S., Vijay S. Rajpurohit, V. B.
Nargund, and ParagKulkarni. "Diagnosis and
classification of grape leaf diseases using neural
networks." In Computing, Communications and
Networking Technologies (ICCCNT), 2013 Fourth
International Conference on, ISBN no. 978-1-4799-
3926-8 , page no. 1-5. IEEE, 2013.
[15]. Akhtar, Asma, AasiaKhanum, Shoab Ahmed Khan, and
ArslanShaukat. "Automated Plant Disease Analysis
(APDA): Performance Comparison of Machine
Learning Techniques." In Frontiers of Information
Technology (FIT), 2013 11th International Conference
on, ISBN no. 978-1-4799-2503-2, page no. 60-65.
IEEE, 2013.
52