Undergraduate Final Year Project Proposal

Comsats University Islamabad, Vehari Campus

Project Proposal for

“Image Based Plant Disease Detection”

By

Muhammad Nabeel Qamar CIIT/FA17-BCS-060/VHR

Ihtsham Akbar CIIT/FA17-BCS-029/VHR

Supervisor

Rab Nawaz Bashir

Bachelor in Computer Science

(2017-2021)
Undergraduate Final Year Project Proposal

Table of Contents

Comsats University Islamabad, Vehari Campus......................................1

Abstract:.........................................................................................................................3
1. Introduction:............................................................................................................4
2. Problem Statement:.................................................................................................5
3. Proposed Solution:..................................................................................................5
4. Advantages of Proposed Project:............................................................................5
5. Scope:......................................................................................................................6
5.1 Goals and features...........................................................................................6
5.2 Task:................................................................................................................6
6. Modules:.................................................................................................................6
6.1 Menu Module:.................................................................................................6
6.2 Registration Module:.......................................................................................6
6.3 Classification of diseases:................................................................................6
6.4 Taking Photos:.................................................................................................7
6.5 OpenCv:...........................................................................................................7
7. System Limitations/Constraints:.............................................................................7
8. Software Process Methodology:.............................................................................7
8.1 Advantages of Agile model:............................................................................8
9. Tools and Technologies:.........................................................................................9
10. Project Stakeholders and Roles:.............................................................................9
11. Team Members Individual Task/Work Division:.................................................10
12. Concepts:..............................................................................................................10
12.1 Machine Learning:.....................................................................................10
12.1.1 Supervised and unsupervised machine learning:...................................10
12.2 Python:.......................................................................................................10
13. Gantt chart:...........................................................................................................11
14. Conclusion:...........................................................................................................12
15. References:............................................................................................................13
Undergraduate Final Year Project Proposal

Abstract:

Economy of our country majorly depends on the Agricultural sector. It remained

the major source of income for almost 80% of small landholders. But most of them
are facing problems due to diseases in the plants which is also effecting the crops
productivity. Then disease detection in plants will play an important role in
agriculture field, as having disease in plants are quite natural. Detection of plant
disease through some automatic technique is beneficial as it reduces a large work of
monitoring in big farms of crops, and at very early stage itself it detects the symptoms
of diseases i.e. when they appear on plant leaves. If proper care is not taken in this
area then it causes serious effects on plants and due to which product quality is also
affected. This proposed system of plant disease detection and recognition based on
deep learning, by which disease detection and better accuracy for the treatment of
crops will increase. First of all, the Artificial Neural Network (ANN) is utilized to
recognize and localize the leaves in complex surroundings. Then, images segmented
based on the results of ANN algorithm contain the feature of symptoms through Open
CV algorithm. Finally, the segmented leaves are input into the transfer learning model
and trained by the dataset of diseased leaves under simple background. Furthermore,
the system will be examined with Bacterial leaf spot, Sun burn, Fungal and Early
scorch diseases.  
Undergraduate Final Year Project Proposal

1. Introduction:

Pakistan’s economy is highly dependent of agricultural productivity. Therefore in

field of agriculture, detection of disease in plants plays an important role. To detect a
plant disease in very initial stage, use of automatic disease detection technique is
beneficial. The already existing methods for plant disease detection is simply done by
naked eye by experts through which identification and detection of plant diseases is
done. For doing so, a large team of experts as well as continuous monitoring of plants
is required, which costs very high when we do with large farms. At the same time,
some countries like Pakistan’s farmers do not have proper facilities or even idea that
they can contact to experts. Due to which consulting experts even cost high as well as
time consuming too. In such conditions, the proposed technique proves to be
beneficial in monitoring large fields of crops. Automatic detection of the diseases by
just seeing the symptoms on the plant leaves makes it easier as well as cheaper for the
farmers. This also supports machine vision to provide image based automatic process
control and inspection. Plant disease identification by visual way is more complex
task and at the same time, less accurate and can be done only in limited areas.
Whereas if automatic detection technique is used it will take less efforts, less time and
become more accurate. In plants, some general diseases are occurred like Bacterial
leaf spot, Sun burn, Fungal and Early scorch diseases. Image processing is used for
detecting images in which plant having disease or not.
Plant disease detection through naked eye observation of the symptoms on plant
leaves, which increases the complexity in detecting plant diseases. Due to this
complexity and to the large number of crops and their existing problems, even
experienced agricultural experts may often fail to successfully diagnose specific
diseases, and are consequently led to mistaken conclusions and concern solutions. An
automated system designed to help identify plant diseases by the plants appearance
and visual symptoms could be of great help to amateurs in the agricultural process.
This will be prove as useful technique for farmers and will alert them at the right time
before spreading of the disease over large area. So, we are going to make a web
application for the detection of leaf diseases of the plants through capturing their
images and classification of them whether any disease exist in leaves or not.
Undergraduate Final Year Project Proposal

2. Problem Statement:

Systems already present are doing plant disease detection through naked eye which is
done by experts. And doing this task in large farms will be time consuming as well as
less accurate and costly for plants disease detection. At the same time, in some
countries, farmers do not have proper facilities or even idea that they can contact to
experts. Due to which consulting experts even cost high as well as time consuming
too. Particularly in Pakistan most of the farmers are far behind the technology then the
world and are facing rapid decrease in growth of agricultural field due to unknown
diseases in plants .When they are unaware of the diseases they cannot find solution
for them. And especially these facilities are not available to most of the farmers. So
there is must need of an automatic system that can detect diseases in leaves of the
plants in time.

3. Proposed Solution:

Due to low technology in the agriculture field of the Pakistan there is must need of an
automatic system for the farmers to detect the diseases in the leaves of the plants in
initial growth of crops. So they can take proper precautions for best growth of the
crops. In such conditions, the suggested technique proves to be beneficial in
monitoring large fields of crops. Automatic detection of the diseases by just seeing the
symptoms on the plant leaves makes it easier as well as for the farmers of our country
and also will be very beneficial for rapid growth of the crops. This also supports
machine vision to provide image based automatic process control, inspection, and
proper guidance.

4. Advantages of Proposed Project:

 Ease of use.
 This web-application assists the farmers to recognize diseases in leaves in initial
stage.
 Growth of the crops will increase rapidly.
 It will save their time as farmers can check diseases sitting at home.
 Accuracy of the diseases will surely help in production increase.
 Low complexity for the farmers.
 It can overcome the complexity of the environment and improve the accuracy of
disease identification.
Undergraduate Final Year Project Proposal

5. Scope:

Numerous approaches have been designed for the detection of diseases in leaves of
crops. And talking about the current situation all around Pakistan growth of the crops
has been disturbed due to numerous diseases in plants. Locusts has also destroyed
major part of the crops all around country but even after they have moved forward to
new places but the point to ponder is the diseases they have injected in the crops. So
there must need of a system which can deal with these diseases and take the growth to
the normal level.

5.1 Goals and features

Our goal is to make our system as valuable product which may be used by maximum
farmers from our community. Users can take pictures of the diseased leaves and can
test them on our web application.

5.2 Task:
Our first step is to launch our system in our city as soon as possible and then we will
try to customize our system more and more.

6. Modules:

6.1 Menu Module:

Menu module is the framework module of the whole application. All the sub-modules
are switched by a Menu View Controller. This control contains the views of menu,
home page and plants information. The menu page is not displayed in the default start
up page. User calls up the menu page by clicking the upper-left icon of the default
page or sliding to the right in the home page.

6.2 Registration Module:

User registration module is used for the management of registered users. Registered
users enjoy the VIP promotion activities. Unregistered users enter the registration
page by clicking the registration button.

6.3 Classification of diseases:

In this phase of classification, the numbers of leaf disease samples that were classified
into five classes of leaf disease are Bacterial leaf spot, Frog eye leaf spot, Sun burn
disease, Fungal disease and Early scorch.

6.4 Taking Photos:

Digital camera or similar devices are using to take images of leafs of different types,
and then those are used to identify the affected area in leafs. Then different types of
image-processing techniques are applied on them, to process those images, to get
Undergraduate Final Year Project Proposal

different and useful features needed for the purpose of analyzing later.

6.5 OpenCv:
Open-source machine learning and computer vision software, OpenCV is a free-to-
use library. OpenCV offers access to over 2,500 algorithms to be used for deployment
of various machine learning and computer vision capabilities like object identification
and facial recognition.

7. System Limitations/Constraints:

Our system will not work without internet. Anyone cannot use our system without
signing up to our system.

8. Software Process Methodology:

Agile model will be followed to develop this system.

Agile Methodology recognizes that software projects are fundamentally unpredictable
and that there are likely to be changes over the course of the project. These changes,
be it market changes or feature changes as the product comes to life will need to be
addressed. As shown in figure, Agile methodology welcomes this volatility by
breaking down projects into small chunks called sprints, to facilitate prioritization and
allowing engineers to add or drop features during the project.
Undergraduate Final Year Project Proposal

Fig-2: Agile Methodology

8.1 Advantages of Agile model:

 Customer satisfaction by rapid, continuous delivery of useful software.
 People and interactions are emphasized rather than process and tools.
 Customers, developers and testers constantly interact with each other.
 Working software is delivered frequently (weeks rather than months).
 Face-to-face conversation is the best form of communication.
 Close, daily cooperation between business people and developers.
 Continuous attention to technical excellence and good design.
 Regular adaptation to changing circumstances.
 Even late changes in requirements are welcomed.

9. Tools and Technologies:

Here is a list of all the hardware and software tools and technologies with their
versions we are going to use in implementation of our whole project.
Tools Version Rationale
MS Visual Studio 2017 IDE
Spyder 3.3.0 IDE
Tools MS SQL Server 2017 DBMS
And MS Word 2016 Documentation
Technologies MS Power Point 2016 Presentation
Technology Version Rationale
Python 3.8 Programming
Language
C# 6.0 Programming
language
SQL 2013 Query Language
ASP.NET 4.6 Web Development

Table-2: Tools and Technologies

Undergraduate Final Year Project Proposal

10.Project Stakeholders and Roles:

Project Comsats University Islamabad, Vehari Campus

Sponsor

Default Options Will be

Stakeholders  Students Name:1-Muhammad Nabeel 2-Ihtsham Akbar
 Project Supervisor: Rab Nawaz Bashir
 Final Year Project Committee: Evaluation of Project

Table-3: Project Stakeholders for proposed project

11. Team Members Individual Task/Work Division:

Student Name Registration No Responsibility

Muhammad Nabeel FA17-BCS-060 Module 1,2,3

Ihtsham Akbar FA17-BCS-029 Module 4,5

Table-4: Team Members work division for proposed project

12.Concepts:

Scripts are written in a language that unity understand and through this language we
can talk to the engine and give it our instructions.The language which we used in
unity for scripting is known as C#.

12.1 C#:
Machine Learning is “the study that gives computer the ability to learn without being
explicitly programmed.
12.1.1 Supervised and unsupervised machine learning:
Machine Learning is divided into two main areas: supervised learning and
unsupervised learning. You have the dataset represented as X, if you have Y labels,
corresponding to observation, then this is supervised learning. And if you have the
dataset represented as X, if you don’t have Y labels for observation, then you have to
make decision on the base of the X dataset itself then this is unsupervised learning.
Here we used supervised learning in our system. There will be training dataset is
Undergraduate Final Year Project Proposal

given for machine learning model train for virtual try on glasses/caps.

12.2 Python:

 Interpreted language: the language is processed by the interpreter at runtime,

like PHP or PERL, so you don’t have to compile the program before
execution.
 Interactive: you can directly interact with the interpreter at the Python prompt
for writing your program. We use Python programming for training ML
model.

13.Gantt chart:

Collecting Images Collecting...

…
Undergraduate Final Year Project Proposal

14.Conclusion:

Considering the numerous diseases present in the plants there is must need of a
system that can help farmers to detect those diseases and propose a better treatment
for them. As major part of the economy of Pakistan depends on Agricultural sector.
So, this proposed system will present an idea to detect diseases in leaves of the plants
through image detection technique that can be used for automatic detection as well as
classification of plant leaf diseases. Banana, beans, lemon, mango and peach are some
of those species on which proposed system will be tested initially. Another advantage
of using this method is that the plant diseases will be identified at the initial stage of
the plant growth. It will surely overcome the complexity of the environment and
improve the accuracy of identification.
Undergraduate Final Year Project Proposal

15.References:

1. https://www.sciencedirect.com/science/article/pii/S2214317316300154
#b0010
2. https://www.hindawi.com/journals/ddns/2020/2479172/
3. https://www.ukessays.com/essays/management/rapid-application-
development-vs-agile-methodologies.php