INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 5, ISSUE 02, FEBRUARY 2016

ISSN 2277-8616

A Leaf Recognition Of Vegetables Using Matlab

Nadine Jaan D. Caldito, Eusebelle B. Dagdagan, Mark G. Estanislao, Kim Leonard B. Jutic, Mary Regina B. Apsay, Marissa G.
Chua, Jeffrey F. Calim, Florocito S. Camata
Abstract: Recognizing plants is a vital problem especially for biologists, agricultural researchers, and environmentalists. Plant recognition can be
performed by human experts manually but it is a time consuming and low-efficiency process. Automation of plant recognition is an important process for
the fields working with plants. This paper presents an approach for plant recognition using leaf images. In this study, the proponents demonstrated the
development of the system that gives users the ability to identify vegetables based on photographs of the leaves taken with a high definition camera. At
the heart of this system is a modernize process of identification, so as to automate the way of identifying the vegetable plants through leaf image and
digital image processing. The system used the Gabor Filter, Edge Detection, RGB Color and Grayscale Image to acquire the physical parameter of the
leaves. The output parameters are used to compute well documented metrics for the statistical and shape. Base on the study, the following conclusion
are drawn: The system can extract the physical parameters from the leafs image that will be used in identifying Vegetable`s. From the extracted leaf
parameters, the system provides the statistical analysis and general information of the identified leaf. The used algorithm can organize data and
information to useful resources to the future researchers.
Keywords: Plant Recognition; Gabor Filter; Edge Detection; RGB Color; Grayscale Image

I. INTRODUCTION
In Agriculture, vegetables plants have become an important
source of energy and source of living of Filipino farmers.
Correctly identifying a vegetable leaf allows farmers to
differentiate between vegetables as well as a vegetable
seedling and weed in the garden. With so many varieties of
leafy greens coming from our local farmers each week, it
can be difficult to figure out which is which. Though these
leaves may appear similar at a glance, they are actually
quite unique in terms of Shape, Texture and Color. And with
the increasing use of innovative computer technology,
digitalized ways have become a possibility for plant
identification. There is a tool in programming that be able to
develop a system where, just having an image, can
recognized an image and match it with the information in
the database. This tool may solve a case in determining
easily the vegetables just through the photograph of their
leaves and it is called image processing. Image
processing is a method to convert an image into digital form
and perform some operations on it, in order to get an
enhanced image or to extract some useful information from
it. It is a type of signal dispensation in which input is image,
like video frame or photograph and output may be image or
characteristics associated with that image. Usually Image
Processing system includes treating images as two
dimensional signals while applying already set signal
processing methods to them. With the help of image
processing, developers can now do research study wherein
it involves pattern recognition and automatic classification
tools that will determine the species of the subject. And,
Leaf Recognition is now emerging for research purposes.
Leaf recognition technology plays an important role in plant
classification and its key issue lies in whether selected
features are stable and have good ability to discriminate
different kinds of leaves. It is well known that the correct
way to extract plant features involves plant recognition
based on leaf images. In particular, identification process is
carried out by gathering leaves detached from the plants,
treated and stained prior to the imaging. The first step of the
algorithm is the isolation of the leaf by thresholding. In the
following, the image is transformed from RGB to gray scale
and proceeds to the method of extracting and matching.
The main objective of the study, A Leaf Recognition of
Vegetables using Matlab, is to create an Informative
Vegetables Leaf Recognition using Matlab to help the

farmers, botanist and Agricultural Researchers in identifying

a vegetable and its common details in a convenient and
reliable way. For the specific objectives, researchers came
up with the following: to analyze the phases of which the
image leaf undergo; to design Leaf Recognition that can
determine the vegetables identity through their Leaves; to
code a Leaf Recognition using MATLAB as the primary
language; to test the program to calculate the accuracy and
reliability of the system; and to implement a system that
may help student researchers. This study covers
computerized identification of a leaf of Vegetables only. To
be specific, the captured image of a leaf will undergo
through image processing in the propose system and in few
seconds, it gives the result of what kind of vegetable is the
leaf. Part of the result would also consist of the vegetables
Common name, Description, Fertilization, Cultivation and
Weeding, Irrigation, Harvesting and Land Preparation. For
the limitation, the Leaf Recognition may have difficulty in
recognizing an image where position and angle of the
image is not fix with the set of criteria in taking the photo.
And there is a chance that the program will not able to
recognize a leaf that has a damage part. Also, the study
focuses only to the limited number of vegetables. This study
presented by the researchers to benefit the Botanist and
Agricultural Researchers even ordinary people in
recognizing a vegetable through an image of its leaf in an
easier and an efficient way and future researchers in their
own academic works and can contribute in the developing
their own system. The study is also open for development.

II. RELATED LITERATURE AND STUDIES

Interest in digital image processing methods stems from
two principal application areas: improvement of pictorial
information for human interpretation; and processing of
image data for storage, transmission, and representation for
autonomous machine perception. This chapter has several
objectives: (1) to define the scope of the field that we call
image processing; (2) to give a historical perspective of the
origins of this field; (3) to give an idea of the state of the art
in image processing by examining some of the principal
areas in which it is applied;(4) to discuss briefly the principal
approaches used in digital image processing; (5) to give an
overview of the components contained in a typical, generalpurpose image processing system; and (6) to provide
direction to the books and other literature where image
38

IJSTR2016
www.ijstr.org

INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 5, ISSUE 02, FEBRUARY 2016

processing work normally is reported. [1] An image may be

defined as a two-dimensional function f(x,y), where x and y
are spatial (plane) coordinates, and the amplitude of f at
any pair of coordinates is called the intensity of the image at
that point. The term gray level is used often to refer to the
intensity of monochrome images. Color images are formed
by a combination of individual images. For example, in the
RGB color system a color image consists of three individual
monochrome images, referred to as the red (R), green (G),
and blue (B) primary (or component) images. For this
reason, many of the techniques developed for monochrome
images can be extended to color images by processing the
three component images individually. [2] Recognition of
plant images is one of the research topics of computer
vision. The use of shape for recognizing objects has been
actively studied since the beginning of object recognition in
1950s. Several authors suggest that object shape is more
informative than its appearance properties such as texture
and color vary between object instances more than the
shape. Initially we have scanned leaf images which are two
dimensional in nature and segmented the images by
mathematical morphological segmentation and then
extracted the high frequency feature of image. For
removing the noise, the image has been converted into
binary, than complemented and multiplied by filtered image.
We quantitatively establish the use of texture for detection
various leaf images of same tree that are difficult by other
classical methods of image processing. Further we use
Nearest Neighborhood classification method to classify
plant leaf. In this paper we focuses mainly on image
enhancement, image segmentation, high frequency feature
extraction, noise remove from background, volume fraction,
inverse difference moment, moment invariant and
morphological feature such as area convexity. [3] Plant leaf
images of three plant types are analyzed using Gabor Filter
by varying the filter parameters. Leaf images are convolved
with Gabor filters followed by a separation of the real and
imaginary portions of the signal. Absolute difference
between the real and imaginary signals from the scalar
feature value used for discrimination. Associated
parameters like filter size, standard deviation, phase shift
and orientation are varied to investigate which combination
provides the best recognition accuracies. Classification is
done by subtracting the test samples from the mean of the
training set. The data set consists of 120 images divided
into 3 classes. Accuracy obtained is comparable to the best
results reported in literature. It is well known that plants play
a crucial role in preserving earths ecology and environment
by maintaining a healthy atmosphere and providing
sustenance and shelter to innumerable insect and animal
species. Plants are also important for their medicinal
properties, as alternative energy sources like bio-fuel and
for meeting our various domestic requirements like timber,
clothing, food and cosmetics. Building a plant database for
quick and efficient classification and recognition of various
flora diversities is an important step towards their
conservation and preservation. This is more important as
many types of plants are now at the brink of extinction. In
recent times computer vision methodologies and pattern
recognition techniques have been successfully applied
towards automated systems of plant cataloguing. From this
perspective the current paper proposes the design of a
system which uses shape recognition techniques to

ISSN 2277-8616

recognize and catalogue plants based on the shape of their

leaves, extracted from digital images. The organization of
the paper is as follows : section 2 discusses an overview of
related works, section 3 outlines the proposed approach
with discussions on feature computation and classification
schemes, section 4 provides details of the dataset and
experimental results obtained, and section 5 brings up the
overall conclusion and scopes for future research. [4] Image
segmentation is to partition an image into meaningful
regions with respect to a particular application. Object
recognition is the task of finding a given object in an image
or video sequence. In this paper, interaction between image
segmentation (using different edge detection methods) and
object recognition are discussed. Edge detection methods
such as Sobel, Prewitt, Roberts, Canny, Laplacian of
Guassian(LoG) are used for segmenting the image.
Expectation-Maximization (EM) algorithm, OSTU and
Genetic algorithms were used to demonstrate the synergy
between the segmented images and object recognition. [5]
Due to the rapid development of digital technology, there is
an opportunity for image processing technology to be used in
the field of agricultural research which could help the
researcher to solve a complex problem. Image analysis
provides informative and accurate information about
vegetables. Image processing is the analysis and
manipulation of graphical images from sources such as
photographs and videos. There are three main steps in
image processing; first, is the conversion of captured images
into binary values that a computer can process; second, is the
image enhancement and data compression; and the third is
the output step that consists of the display or printing of the
processed image. Image processing is used in such
applications as satellite weather mapping, machine vision,
and computer-based pattern recognition. [6] This research
investigated the use of a machine vision system and multilayer
neural networks for automatic identification of the sizes, shapes,
and variety of samples of 52 rice grains belonging to five (5)
varietal groups of rice in the Philippines. Several multilayer
neural networks were developed for sizes, shapes and varietal
types classification using thirteen (13) grain features extracted
from each sample image. These grain features were the major
axis length, minor axis length, area, perimeter, Feret diameter,
shape factor, compactness, elongatedness, mean major axis
length, rectangularity, equivalent rectangular length, equivalent
rectangular width, and number of pixels. The Artificial Neural
Networks classifiers developed were able to identify the grain
sample sizes and shapes at overall average accuracies of 98.76
per cent and 96.67 percent, respectively. The individual rice
varietal types of the lowland irrigated, lowland rained, saline
prone, cool elevated, and upland rice groups were classified at
average overall accuracy of 85.81, 94.58, 96.16, and 97.39
percent respectively. An average overall accuracy of about 70
percent was obtained when the sample images of the 52
varieties were included in the group classification. The study
results have demonstrated the capability and potential of
machine vision with a well trained multilayer neural network
classifiers for sizes, shapes, and varietal types identification of
rough rice grain samples grown in the diverse agro ecological
zones in the country. [7]

39
IJSTR2016
www.ijstr.org

INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 5, ISSUE 02, FEBRUARY 2016

III. METHODOLOGY
The researchers used Linear Sequential Model as a
research design of the study. Each phase has a set of welldefined goals, and the activities within any phase contribute
to the satisfaction of that phase's goals or perhaps a
subsequent phase's goals.

ISSN 2277-8616

Most of the buttons/controls are located in the main form of

the system; Open Camera, Capture, Reset, Add New
Vegetables and the Leaf Recognition Button. Also, the
captured image of the vegetable leaf will show in this form.
Buttons

Functions
This button will allow
the user to open the
camera in the studio
that is connected in
computer.
Once the user opened
the camera the Capture
button will enable and
allow the user to
capture the vegetable
leaf that is inside the
studio.
If the captured image is
not properly taken, you
can use the Re-capture
function that will allow
the user to capture I
vegetable leaf again.

Fig. 1 Linear Sequential Model

If the image is properly

captured, this button will
allow user to match the
captured image to the
image that are saved in
the
database
and
display the information
of
the
matched
vegetable.

A. System Analysis
In this phase, the researchers started gathering different
vegetable leaves to be used in the study. Also, determining
what leaf feature the program should process in leaf
recognizing was established.
Research Subject
The vegetable leaves are the subject of this study. The
researchers decided to conduct an experimental method for
acquiring results using vegetable leaf recognition software.
The researchers gather different kinds of vegetable leaves
to analyze, gathered data and capture images in the studiotype box afterward to be use on recognizing process for
experimental testing.

This button will allow

users to add another
leaf in the database.

B. System Design
The researchers, in this phase, determine how the project
will be physically created.

Graphical User Interface (GUI)

Fig. 3 Add New Vegetable Leaf Form

In this form the user will allow to add new vegetable by
taking vegetable leaves pictures and inputting the vegetable
information.

Fig.2 Vegetable Leaf Recognition Main Form

40
IJSTR2016
www.ijstr.org

INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 5, ISSUE 02, FEBRUARY 2016

Buttons

ISSN 2277-8616

method. The object contains the data used for training, so

can compute resubstitution predictions.

Functions
This button will allow the user to
open the camera in the studio that is
connected in computer.
This button will temporarily save the
captured vegetable leaf image in the
add new folder.
After taking several picture of the
vegetable leaves. This button will
allow user to input the vegetables
information.
After capturing the images of
vegetable leaf and filling the
vegetable information, user can now
save the new vegetable with this
button. The captured images that
are temporarily save in add new
folder will move to the database
folder then using Gabor filter, the
program will save the features
vector of the leaves and the
information of the new vegetable in
the database.

Fig.5 Matching captured image to Database

Fig.4 Leaf Information Form

This form will show the matched vegetable image of that
image loaded as well as the information of the vegetable
such as the common name, description, fertilization,
cultivation and weeding, irrigation, harvesting and land
preparation.
C. Coding
Digital Processing techniques help in manipulation of the
digital images by using computers. To get over such flaws
and to get originality of information, it has to undergo
various phases of processing. After capturing the leaf
image, the RGB image is firstly resize to 384 x 256 to
fasten the process then convert it into a grayscale image.
The code used to convert RGB value of a pixel into its
grayscale value is rgb2gray. Then from grayscale, system
will use the Gabor filters. It will extract the Gabor features of
the image and finally, it will create a column vector,
consisting of the image's Gabor features. Then training and
testing of the data will start using (K-NN) k-nearest neighbor
classification is often used in classification problems. A
nearest-neighbor classification object, where both distance
metric ("nearest") and number of neighbors can be altered.
The object classifies new observations using the predict

D. Testing and Evaluation

In order to find some bugs that the proposed study might
have, researchers administer series of sample leaves if it
can acquire the results needed and correctly. The
researchers test the accuracy and accuracy of the system
by conducting trials of commands. The proponents used 20
trials per leaves in the system has. The accuracy is being
tested by how the system correctly responds to the trials
conducted by the user. The reliability is tested by how long
the system will give correct results as the leaves changes.
Research Instrument
The researchers used experimentation table as research
instrument to conduct testing to the chosen experts. It is a
table composed of 20 trials of 5 different vegetable leaves
with the response of 1, if it is matched and 0, if not. The
respondents will evaluate accuracy and reliability. The
researchers obviously need photographs for complete
collection records of captured images. The researchers
used a 16 megapixel Web camera for acquiring images for
good quality of 1080p per image and a studio-type box for
fix distance and stable positioning of camera. By the use of
this strategy the researchers are able to obtain first hand
information about the subject.
Validation of Instrument
For validity of the instruments of the study, researchers
sought for professional assistance of the research adviser.
Consultation resulted on having a fix distance in taking
image sample and to have a high definition camera for the
image of the sample leaf. Researchers test different camera
with different megapixels to came up with an image that the
41

IJSTR2016
www.ijstr.org

INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 5, ISSUE 02, FEBRUARY 2016

ISSN 2277-8616

TABLE I. ACCURACY

propose program can clearly process and also do an

improvise studio that can handle the distance in capturing
photographs. At least 16 megapixel of Web camera can use
with at least 40 centimeter of distance in capturing an
image.
Data Gathering Procedure
The methods researchers used to gather data is the data
mining that considered a good data gathering procedure.
Researchers find related files, documents and books that
contain informations that the study needed. The use of
Library to take a look some vegetable information from
different books that comes from different reputable sources
is a good move in data mining. Also researchers went to
different farms/gardens to get different vegetable leaves
sample that used in testing the proposed program. And
researchers conducted interviews to farmers and
agriculture researchers for some vegetables profiles and for
additional information on how they do recognizing their
plant. After gathering enough sample, vegetable leaves will
now undergo image processing where researchers should
get the algorithm of each leaves that will be save to the
database.
Statistical Treatment
The researchers used Percentage for vegetable leaf
sample testing to get the accuracy and reliability and the
formula is:
P = x/n x 100
Where:
X = Frequency of Matched results
N = Total number of trials
P = Percentage

The first table shows the results of the experimentation

conducted by the respondents with answer 1 if the leaf was
matched and 0 if not in the testing form. The respondents
were given two (2) leaves of each vegetable that they will
be testing. Respondents tested the system in real-time with
twenty (20) trials. This is to compute the accuracy of the
system.

E. Implementation
This is the stage where the system is first transferred to the
users premises and the users get a chance to work with the
new system. The system requires Matlab 7.12.0 (R2011a)
stable version in order to implement the system with
Microsoft Office Access 2003 for database. And also the
system needs a high definition camera and a studio-type
box with a good lighting. These two will help to give a clear
image of the vegetable leaf.

TABLE II. RELIABILITY

Research Setting
The researchers based the setting of the study where the
availability of vegetable leaves needed is present. These
places were Bureau of Agriculture Researches (BAR) and
Bureau of Plant Industry (BPI) located at Visayas Avenue
Cor. Elliptical Road, Diliman Quezon City.

IV. RESULTS
This chapter includes an experiment and data gathering of
the program, A Leaf Recognition of Vegetables. With the
real-time testing, each of twenty (20) different vegetables
leaves undergo in twenty (20) trials. It is to determine the
Level of Accuracy and the Reliability of the propose system.
Next table shows the consistency in producing correct
results of the system though it changes into 20 different
leaves accordingly.
42
IJSTR2016
www.ijstr.org

INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 5, ISSUE 02, FEBRUARY 2016

TABLE III. OVERALL PERFORMANCE

Criteria

Percentage

Accuracy

90.5

Reliability

90.75

Average

90.625

The accuracy of the system tested by the respondent and

computed by the proponents is 90.5%. The reliability of the
system tested by the respondent and computed by the
proponents is 90.75%. And the overall performance of the
system, A Leaf Recognition of Vegetable, is 90.625%.

V. DISCUSSION
The findings are based on how the respondents evaluate
the system through experimental method. Experimental
form with 1-0 response was used by the respondents to test
the system. Based on the data gathered by the researchers
through testing the system in terms of accuracy, The
vegetable leaf Bottle gourd test twenty out of twenty (20 out
of 20) matched. The accuracy percentage of Bottle gourd is
100%. The vegetable leaf Bitter gourd test twenty out of
twenty (20 out of 20) matched. The accuracy percentage of
Bitter gourd is 100%. The vegetable leaf Cassava test
seventeen out of twenty (17 out of 20) matched. The
accuracy percentage of Cassava is 85%. The vegetable
leaf Eggplant test fifteen out of twenty (15 out of 20)
matched. The accuracy percentage of Eggplant is 75%.
The vegetable leaf Hot Pepper test eighteen out of twenty
(18 out of 20) matched. The accuracy percentage of Hot
Pepper is 90%. The vegetable leaf Jute test eighteen out of
twenty (18 out of 20) matched. The accuracy percentage of
Jute is 90%. The vegetable leaf Malabar nightshade test
fifteen out of twenty (15 out of 20) matched. The accuracy
percentage of the Malabar nightshade is 75%. The
vegetable leaf Miracle of Hyacint Beans test forteen out of
twenty (14 out of 20) matched. The accuracy percentage of
Miracle of Hyacint Beans is 70%. The vegetable leaf
Moringa test eighteen out of twenty (18 out of 20) matched.
The accuracy percentage of Moringa is 90%. The vegetable
leaf mustard test sixteen out of twenty (16 out of 20)
matched. The accuracy percentage of mustard is 80%. The
vegetable leaf onion test nineteen out of twenty (19 out of
20) matched. The accuracy percentage of onion is 95%.
The vegetable leaf papaya test twenty out of twenty (20/20)
matched. The accuracy percentage of papaya is 100%. The
vegetable leaf pechay test sixteen out of twenty (16 out of
20) matched. The accuracy percentage of pechay is 80%.
The vegetable leaf Sponge gourd test sixteen out of twenty
(16 out of 20) matched. The accuracy percentage of
Sponge gourd is 80%. The vegetable leaf String beans test
twenty out of twenty (20 out of 20) matched. The accuracy
percentage of String beans is 100%. The vegetable leaf
squash test twenty out of twenty (20 out of 20) matched.
The accuracy percentage of squash is 100%. The
vegetable leaf sweet potato test twenty out of twenty (20
out of 20) matched. The accuracy percentage of sweet
potato is 100%. The vegetable leaf taro test twenty out of
twenty (20 out of 20) matched. The accuracy percentage of
taro is 100%. The vegetable leaf tomato test twenty out of

ISSN 2277-8616

twenty (20 out of 20) matched. The accuracy percentage of

Tomato is 100%. The vegetable leaf water spinach test
twenty out of twenty (20 out of 20) matched. The accuracy
percentage of water spinach is 100%. Most of the failure in
identifying the leaves was due to the position and angle of
the leaf that may change the feature value of the leaf.
Based on the data gathered by the researchers through
testing the system in term of reliability, 1st trial got
seventeen out of twenty (17 out of 20) with the percentage
of 85%.The 2nd trial got eighteen out twenty (18 out of 20)
with the percentage of 90%. The 3rd trial got sixteen out of
twenty (16 out of 20) with the percentage of 80%.The 4th
trial got nineteen out of twenty (19 out of 20) with the
percentage of 95%.The 5th trial got nineteen out twenty (19
out of 20) with the percentage of 95%.The 6th trial got
nineteen out twenty (19 out of 20) with the percentage of
95%.The 7th trial got nineteen out twenty (19 out of 20) with
the percentage of 95%. The 8th trial got nineteen out twenty
(19 out of 20) with the percentage of 95%. The 9th trial got
eighteen out twenty (18 out of 20) with the percentage of
90%. The 10th trial got nineteen out twenty (19 out of 20)
with the percentage of 95%. The 11th trial got eighteen out
twenty (18 out of 20) with the percentage of 90%.The 12th
trial got eighteen out twenty (18 out of 20) with the
percentage of 90%. The 13th trial got nineteen out twenty
(19 out of 20) with the percentage of 95%. The 14th trial got
nineteen out twenty (19 out of 20) with the percentage of
95%. The 15th trial got nineteen out twenty (19 out of 20)
with the percentage of 95%. The 16th trial got eighteen out
twenty (18 out of 20) with the percentage of 90%. The 17th
trial got sixteen out twenty (16 out of 20) with the
percentage of 80%. The 18th trial got eighteen out twenty
(18 out of 20) with the percentage of 90%. The 19th trial got
eighteen out twenty (18 out of 20) with the percentage of
90%. The 20th trial got seventeen out twenty (17 out of 20)
with the percentage of 85%. Based on the result of
experimentation testing conducted by the respondents, the
accuracy percentage of the proposed system is 90.5% and
the reliability percentage is 90.75% which gives the overall
Performance of 90.625%.

VI. CONCLUSIONS
After the processing of data gathered in this study, the
researchers have come up with the following conclusion:
1
The researchers were able to analyze where the
image leaf should undergo.
2
The researchers designed the proposed system, A
Leaf Recognition of Vegetable which can determine
the identification of the leaf tested with the use of
Linear Sequential Model as the Research Subject.
3
The researchers code or built an image processing
system using Matrix Laboratory (Matlab) as the
primary programming language.
4
The researchers tested the program by experimental
evaluation. By having the computed information, the
system gives an accuracy of ninety percent (90%).
And the researchers also conclude that the propose
system can give a reliable result with the percentage
of ninety (90%), as long as the vegetable leaf is in the
right position, the lighting and the camera device is in
good condition, and the shape of the leaf can be
distinguish, not deformed nor damaged.
43

IJSTR2016
www.ijstr.org

INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 5, ISSUE 02, FEBRUARY 2016

VII.

The researchers can able to implement a useful

system for the use of the student and future
researchers.

RECOMMENDATION

Based on the findings and conclusions presented,

the
researchers
have arrived at the following
recommendations:
1. The researchers recommend to choose a high quality
camera for capturing image for the vegetable leaf to
have a good results and a high quality image.
2. The researchers recommend the use of MATLAB
7.12.0 (R2011a) stable version in order to avoid
unexpected errors and to have consistency to the
project.
3. The researchers recommend using full-screen mode in
the program.
4. The researchers recommend to add more features
extraction of the leaf to improve the systems
recognition. Also reduce its failure rate of recognizing at
least how many percents so that the program will be
more accurate and powerful in recognizing even though
the leaf was damaged and deformed.
5. The researchers would like to recommend this study to
the future researchers to stand as their basis to create
a sensible system which focuses on more broad
species/varieties of plants like herbal, flower, trees and
fruit bearing plants for further studies development that
the society needs.

ACKNOWLEDGMENT
A lot of time, effort and sweat were spent in making this
study. For this, with sincere appreciation and deepest
gratitude, the researchers would like to acknowledge the
following who contributed much to realization of this
research paper. First, to All Mighty God, our creator, for
giving us strength to accomplished this research. To our
Alma Mater, the Our Lady of Fatima University for giving us
the opportunity to conduct this study which greatly
contributed towards the enhancement of our critical
thinking. To the faculty members of Information Technology
(IT) department, for teaching and sharing their knowledge,
time, as well as their skills towards improving the quality of
this research. To the respondents from Bureau of
Agricultural Resources (BAR) and Bureau of Plant Industry
(BPI) for their willingness and unselfishness cooperation on
answering our tool which made our experimentation a
successful one. More importantly, to our parents, relatives
and friends for their moral and financial support, and also
for the encouragement they have provided.

REFERENCES
[1] Gonzalez R.C. & Woods R. E. (2002). Digital Image
Processing Second Edition. PWS Publishing, New
York.
[2] Gonzalez R. C., Woods R. E. & Eddins S. L. (2009).
Digital Image Processing Using MATLAB. PWS
Publishing, New York.
[3] Bhardwaj A., Kaur M. & Kumar A. (2013). Recognition
of plants by Leaf Image using Moment Invariant and

ISSN 2277-8616

Texture Analysis. International Journal of Innovation

and Applied Studies, vol. 3-no. 1, 237248.
[4] Chaki J. & Parekh R. (2012). DESIGNING AN
AUTOMATED
SYSTEM
FOR
PLANT
LEAF
RECOGNITION. IJAET Journal, Volume. 2, Issue 1,
149-158
[5] Y.Ramadevi, T.Sridevi, B.Poornima, B.Kalyani. (2010).
SEGMENTATION AND OBJECT RECOGNITION
USING
EDGE
DETECTION
TECHNIQUES.
International Journal of Computer Science &
Information Technology (IJCSIT), Volume 2, 59-121.
[6] Miranda J .L. & Gerardo B. D., & Tanguilig III B. T.
(2014). Pest Detection and Extraction Using Image
Processing Techniques. International Journal of
Computer and Communication Engineering, Volume. 3,
No. 3, 189-192.
[7] Guzman J, D, & Peralta E. K. (2008). Classification of
Philippine Rice Grains Using Machine Vision and Artificial
Neural Networks. IAALD AFITA WCCA 2008 World
Conference on Agricultural Information and IT, Volume 2,
241-481.
[8] Wang, Z., Chi, Z., Feng, D., & Wang, Q. (2000). Leaf
Image Retrieval with Shape Features. 4th International
Conference on Advances in Visual Information
Systems. Volume 3, 477-487.
[9] H. Fu, Z. Chi, D. Feng, & J. Song. (2004). Machine
learning
techniques
for
ontology-based
leaf
classification, in IEEE 2004 8th International
Conference on Control, Automation, Robotics and
Vision, Kunming, China. Volume 2, 201-348.
[10] Timmermans.A. J. M & Hulzebosch.A. A. (1996).
Computer vison system for on-line sorting of pot plants
using an artificial neural network classifier. Computers
and Electronics in Agriculture. Volume 1, 41-55.
[11] Beghin.T, Cope.J. S., Remagnino.P., & Barman.S.
(2010). Shape and texture based plant leaf
classification. International Conference on Advanced
Concepts for Intelligent Vision Systems (ACVIS).
Volume 3, 345-353.
[12] Smith T. S. (2006). MATLAB: Advanced
Development. Dog Ear Publishing 4010 W.

GUI

[13] Higham D. J & Higham N. J. (2005). MATLAB Guide:

Second Edition. Library of Congress Cataloging-inPublication Data, Datta,Biswa Nath.
[14] Kattan P. (2009). MATLAB for Beginners: A Gentle
Approach: Revised Edition. CreateSpace Independent
Publishing Platform.
[15] Singh S. (2005).Pattern Recognition and Image
Analysis: Third International Conference on Advances
in Pattern Recognition. Scientific Publishing Services,
Chennai, India.
44

IJSTR2016
www.ijstr.org

INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 5, ISSUE 02, FEBRUARY 2016

ISSN 2277-8616

[16] Lukas R., Capungay K. N. (2006). Color Image

Processing:
Methods
and
Applications.
Bombay,India,Narsosa Publishing House.
[17] John W. & Sons. (2011). Practical Image and Video
Processing Using MATLAB. Kluwer Academic
Publishers.
[18] Poon T. C., Banerjee P.P. (2001). Contemporary
Optical Image Processing with MATLAB. Elsevier`s
Optical, Electronic And Control Publishing
[19] Parekh J. C. (2012). Plant Leaf Recognition using
Gabor Filter, International Journal of Computer
Applications, Volume 56 - Number 10, 89-96.

45
IJSTR2016
www.ijstr.org