Government College University Faisalabad Page i

Automatic plant detection

By

M. Ali 2016-GCUF-071948
Hassan Mehmood 2016-GCUF-071938
Khurram shehzad Ali 2016-GCUF-071944

Associate Degree Program

IN
COMPUTER SCIENCE

____________________________________________________
DEPARTMENT OF COMPUTER SCIENCE
 Government College University Faisalabad
2022
Government College University Faisalabad Page ii

Table of Contents
Table of
Contents ...........................................................................................................................2
Revision
History .............................................................................................................................3
1.
Introduction ................................................................................................................................1
1.1 General Information ...........................................................................................................................1
1.2 Purpose ..............................................................................................................................................2
1.3 Project Objective ...............................................................................................................................4
1.4 Intended Audience and Reading Suggestions ...................................................................................6
1.5 Project Scope ..................................................................................................................................... 7
2. Overall
Description ..................................................................................................................10
2.1 Product Perspective .........................................................................................................................10
2.2 Product Features ..............................................................................................................................11
2.3 User Classes and Characteristics .....................................................................................................14
2.4 Operating Environment ....................................................................................................................18
3. System
Features ........................................................................................................................20
3.1 System Feature 1 ..............................................................................................................................20
3.2 System Feature 2 (and so on) ...........................................................................................................21
4. External Interface Requirements ...........................................................................................23
4.1 User Interfaces .................................................................................................................................23
4.2 Hardware Interfaces .........................................................................................................................23
4.3 Software Interfaces ..........................................................................................................................23
5. Other Nonfunctional
Requirements .......................................................................................24
5.1 Performance Requirements ..............................................................................................................24
5.2 Safety Requirements ........................................................................................................................24
5.3 Security Requirements .....................................................................................................................25
5.4 Software Quality Attributes .............................................................................................................25
6. WBS Project Management .................................................................................................26
7. Tools &
Technologies................................................................................................................29
7.1 Programming Languages .................................................................................................................29
 7.2 Databases/Data storages ..................................................................................................................29
7.3 Operating System..............................................................................................................................29
Appendix A: Glossary ................................................................................................................30
Appendix B: Analysis
Models .....................................................................................................31 Appendix C: Check
List ..............................................................................................................32 Appendix D:
Supervisory Committee ........................................................................................33

Revision History

Name Date Reason For Changes Version

Government College University Faisalabad Page 1

1.Introduction

1.1 General Information

Project Name: | Automatic plant detection.

Starting Date: | 13/12/2022

Final Date: | 15/12/2022
Controlling Agency: | LGES
Prepared By: | M.ALI, HASSAN MEHMOOD,
KHURRAM SHEHZAD ALI

Authorized by: | LGES

Government College University Faisalabad Page 2

1.2 Purpose
The purpose of this SRS to elaborate the topic Automatic plant
disease detection in the field of agriculture .
Agriculture is a milestone and a booster of early human social
development. The substantial advances in science and technology
brought about by the prosperity of human society have been assisting
in developing agriculture. In recent decades, modern technology has
empowered humans to produce enough food to feed seven billion
people (Mohanty et al., 2016). However, many developing countries
face a food crisis (Erokhin and Gao, 2020), suffering from famine and
economic loss. Although political factors in developing countries, such
as social unrest and economic instability, indeed affect the production
and distribution of food, it is undeniable that those countries lack
cutting-edge science and technology in agriculture.
Moreover, food security is typically threatened by diverse objective
aspects, including climate change (Anderson et al., 2020), plant pests
and diseases (Trebicki and Finlay, 2019), and others. In addition, at
the stage of plant’s leaf quality testing, underdeveloped regions rely
mainly on the workforce to perform leaf classification in terms of
quality or omit this process due to high cost. This decision leads to
stagnation of the agricultural economy in these regions and further
constrains the improvement of the local population’s living standard.
Therefore, developing a positively automated and low-cost leaf
disease detection method is imperative.
Object detection of plant diseases retains a wide range of application
prospects in agriculture, providing timely feedback on plant
conditions, guiding crop cultivation and post-treatment, and thus
significantly declining costs. Thanks to the blossoming of
microcomputers and mobile computing devices, hardware support
has been supplied for plant object detection. Meanwhile,
backpropagation algorithms-based deep learning methods (especially
Government College University Faisalabad Page 3

convolutional neural networks) provide software support. Accordingly,

several researchers have initiated developing automatic deep
learning-based algorithms for plant disease detection applications.

Mohanty et al. (2016) trained a deep convolutional neural

network(CNN) to recognize 14 crops and 26 diseases (with or without
disease). The trained model achieved 99.35% accuracy on a
reserved test set, reflecting the viability of deep learning in crop
detection. More specifically, Ramcharan et al. (2017) suggested a
deep CNN-based disease detection method, attempting to deploy the
program to mobile devices. Liu and Wang (2020) improved the
existing technique of tomato pest image recognition based on the
YOLO-v3 model (an efficient object detection algorithm based on
CNNs), improve the existing technique of tomato pest image
recognition in the natural. Xu et al. (2022) provided an approach for
data augmentation that can fully utilize data from non-target regions
of sample images to optimize deep learning models for disease
detection. Their method is more applicable to plant disease detection
than common data enhancement approaches. Zhang et al. (2021b)
employed an enhanced CNN model to detect pear flaws; more
precisely, the defect images were expanded by a deep convolutional
adversarial generation network (DCGAN). On the three thousand
validation set, the detection accuracy reached 97.35% exactly.
Besides, various mainstream CNNs were compared to thoroughly
evaluate the performance of models. Subsequently, the top
performed one was chosen to conduct additional comparative
experiments using traditional machine learning approaches. Agarwal
et al. (2020) suggested a CNN-based approach to detect tomato leaf
diseases. They conceived three convolution-pooling layers and two
fully connected layers. Experimentally, the efficacy of the presented
model outstripped the pre-trained model, namely, Mobile Net,
InceptionV3, and VGG16. The classification accuracy fluctuated
between 76 and 100%, and the offered model’s average accuracy
was 91.2% for nine diseases and one healthy category. Pantazi et al.
(2019) utilized one-class classification and local binary patterns
(LBPs) to demonstrate an automated strategy for identifying crop
Government College University Faisalabad Page 4

diseases on multiple leaf images matching diverse crop species. The

suggested methodology employs a separate one-class classifier for
each plant health state. They tested the algorithms developed on vine
leaves in various plants, finding them highly applicable when applied
to other plants. The 46 plant-condition combinations reached an
entire success rate of 95%. A multi-activation function (MAF) module
was suggested to improve the CNN by Zhang et al. (2021a). The
diseased samples were expanded and supplemented using image
preprocessing measures, and the training speed was raised using
transfer learning and warm-up approaches. The proposed system
could efficiently and correctly detect three types of maize diseases,
achieving a 97.41% accuracy rate in the validation set, exceeding
conventional artificial intelligence methods.

1.3 Project Objective

Agricultural productivity is something on which economy highly
depends. This is the one of the reasons that disease detection in
plants plays an important role in agriculture field, as having disease in
plants are quite natural. If proper care is not taken in this area then it
causes serious effects on plants and due to which respective product
quality, quantity or productivity is affected. For instance a disease
named little leaf disease is a hazardous disease found in pine trees in
United States. 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. This paper
presents an algorithm for image segmentation technique which is
used for automatic detection and classification of plant leaf diseases.
It also covers survey on different diseases classification techniques
that can be used for plant leaf disease detection. Image
segmentation, which is an important aspect for disease detection in
plant leaf disease, is done by using genetic algorithm.
Government College University Faisalabad Page 5

Plant diseases and pests are important factors determining the yield
and quality of plants. Plant diseases and pests identification can be
carried out by means of digital image processing. In recent years,
deep learning has made breakthroughs in the field of digital image
processing, far superior to traditional methods. How to use deep
learning technology to study plant diseases and pests identification
has become a research issue of great concern to researchers. This
review provides a definition of plant diseases and pests detection
problem, puts forward a comparison with traditional plant diseases
and pests detection methods. According to the difference of network
structure, this study outlines the research on plant diseases and pests
detection based on deep learning in recent years from three aspects
of classification network, detection network and segmentation
network, and the advantages and disadvantages of each method are
summarized. Common datasets are introduced, and the performance
of existing studies is compared. On this basis, this study discusses
possible challenges in practical applications of plant diseases and
pests detection based on deep learning. In addition, possible
solutions and research ideas are proposed for the challenges, and
several suggestions are given. Finally, this study gives the analysis
and prospect of the future trend of plant diseases and pests detection
based on deep learning.

We can reduce the attack of pests by using proper pesticides and

remedies We can reduce the size of the images by proper size
reduction techniques and see to it that the quality is not compromised
to a great extent. The main Objective is to identify the plant diseases
using image processing. It also, after identification of the disease,
suggest the name of pesticide to be used. It also identifies the insects
and pests responsible for epidemic. Apart from these parallel
objectives, this drone is very time saving.
The budget of the model is quite high for low scale farming purposes
but will be value for money in large scale farming. It completes each
of the process sequentially and hence each of the output.
Government College University Faisalabad Page 6

Thus the main objectives are:

1) To design such system that can detect crop disease and pest
accurately.

2) Create database of insecticides for respective pest and dies

3) To provide remedy for the disease that is detected

1.4 Intended Audience and Reading Suggestions

While the software requirement specification (SRS) document is
written for a more general audience, this document is intended for
individuals directly involved in the development of this RSR. This
includes software developers, project consultants, and team
managers. This document need not be read sequentially; users are
encouraged to jump to any section they find relevant.

Below is a brief overview of each part of the document.

• Part 1
Introduction
• Part 2
Overall description
Government College University Faisalabad Page 7

• Part 3
System features
• Part 4
External Interface Requirements
• Part 5
Other Nonfunctional Requirements
• Part 6
WBS project management
• Part 7
Tool and technologies

1.5 Project Scope

Object detection is a vibrant topic in computer vision research and is
a crucial visual content analysis and comprehension. The benefits in
applications such as autonomous vehicles and medical diagnosis
brought by object detection are noticeable.

Plant diseases and pests detection is a very important research

content in the field of machine vision. It is a technology that uses
machine vision equipment to acquire images to judge whether there
are diseases and pests in the collected plant images .

At present, machine vision-based plant diseases and pests

detection equipment has been initially applied in agriculture and has
replaced the traditional naked eye identification to some extent.

For traditional machine vision-based plant diseases and pests

detection method, conventional image processing algorithms or
manual design of features plus classifiers are often used [2]. This
Government College University Faisalabad Page 8

kind of method usually makes use of the different properties of plant

diseases and pests to design the imaging scheme and chooses
appropriate light source and shooting angle, which is helpful to
obtain images with uniform illumination. Although carefully
constructed imaging schemes can greatly reduce the difficulty of
classical algorithm design, but also increase the application cost. At
the same time, under natural environment, it is often unrealistic to
expect the classical algorithms designed to completely eliminate the
impact of scene changes on the recognition results [3]. In real
complex natural environment, plant diseases and pests detection is
faced with many challenges, such as small difference between the
lesion area and the background, low contrast, large variations in the
scale of the lesion area and various types, and a lot of noise in the
lesion image. Also, there are a lot of disturbances when collecting
plant diseases and pests images under natural light conditions. At
this time, the traditional classical methods often appear helpless,
and it is difficult to achieve better detection results.

In recent years, with the successful application of deep learning

model represented by convolutional neural network (CNN) in many
fields of computer vision (CV, computer-vision), for example, traffic
detection [4], medical Image Recognition [5], Scenario text detection
[6], expression recognition [7], face Recognition [8], etc. Several
plant diseases and pests detection methods based on deep
learning are applied in real agricultural practice, and some domestic
and foreign companies have developed a variety of deep learning-
based plant diseases and pests detection Wechat applet and photo
recognition APP software. Therefore, plant diseases and pests
detection method based on deep learning not only has important
academic research value, but also has a very broad market
application prospect.
Government College University Faisalabad Page 9

The detection of plant disease is of vital importance in practical

agricultural production. It scrutinizes the plant’s growth and health
condition and guarantees the regular operation and harvest of the
agricultural planting to proceed successfully. In recent decades, the
maturation of computer vision technology has provided more
possibilities for implementing plant disease detection. Nonetheless,
detecting plant diseases is typically hindered by factors such as
variations in the illuminance and weather when capturing images
and the number of leaves or organs containing diseases in one
image. Meanwhile, traditional deep learning-based algorithms attain
multiple deficiencies in the area of this research:

(1) Training models necessitate a significant investment in hardware

and a large amount of data.

(2) Due to their slow inference speed, models are tough to

acclimate to practical production.

(3) Models are unable to generalize well enough. Provided these

impediments, this study suggested a Tranvolution detection network
with GAN modules for plant disease detection. Foremost, a
generative model was added ahead of the backbone, and GAN
models were added to the attention extraction module to construct
GAN modules.

Afterward, the Transformer was modified and incorporated with the

CNN, and then we suggested the Tranvolution architecture.
Eventually, we validated the performance of different generative
models’ combinations. Experimental outcomes demonstrated that
the proposed method satisfyingly achieved 51.7% (Precision),
48.1% (Recall), and 50.3% (mAP), respectively.
Government College University Faisalabad Page 10

2. Overall Description

2.1 Product Perspective

Plant disease identification is one of the most basic and important
activities in agriculture. In most cases, identification is performed
manually, either visually or by microscopy. The problem with visual
assessment is that, being a subjective task, it is prone to
psychological and cognitive phenomena that may lead to bias,
optical illusions and, ultimately, to error. On the other hand,
laboratorial analyses such as molecular, immunological or pathogen
culturing-based approaches are often time consuming, failing to
provide answers in a timely manner. In this context, it is compelling
to develop automatic methods capable of identifying diseases in a
rapid and reliable way. The vast majority of automatic methods
proposed so far rely on digital images, which allows the use of very
fast techniques. However, intrinsic and extrinsic factors mean these
methods remain too error prone, which was the motivation for the
current review.

Most of the methods described in the literature are based on digital

images of symptoms in the visible and near-infrared bands
(Barbedo, 2013), with those bands being considered in isolation or
represented in multi and hyperspectral images. Although multi and
hyperspectral images can potentially carry more information than
normal photographs, they are usually captured by expensive and
bulky sensors, while conventional cameras are ubiquitous and
present in many consumer-level electronics stores. This has
resulted in developing systems based on the visible range, which
also leads to a more focused discussion. More information on multi
and hyperspectral imaging applied to plant pathology can be found
in Sankaran, Mishra, Ehsani, and Davis (2010) and Bock, Poole,
Parker, and Gottwald (2010).
Government College University Faisalabad Page 11

Some of the methods exploring visible range images focus on

detecting a single disease of interest amidst other diseases, healthy
tissue, nutritional problems and pests (Barbedo et al., 2015, Oberti
et al., 2014, Polder et al., 2014, Pourreza et al., 2015a, Pourreza et
al., 2015b, Zhang et al., 2014a, Zhou et al., 2014), while others try
to detect and discriminate different diseases. Although progress has
been made regarding the disease classification problem, the vast
majority of the methods are only capable of discriminating among a
small number of diseases (Phadikar et al., 2013, Pydipati et al.,
2006, Sanyal and Patel, 2008). In general, this is too limited for real-
world applications, because the number of pathogens that can
simultaneously infect a plant and cause disease symptoms is
usually higher. Also, nutritional deficiencies (Pagola et al., 2009,
Romualdo et al., 2014, Wiwart et al., 2009) and pests (Clément et
al., 2015, Koumpouros et al., 2004, Škaloudová et al., 2006) may
produce symptoms that mimic very closely the characteristics of
some diseases. To make matters even more complicated, there are
some challenges that affect virtually all studies devoted to the
automation of the disease diagnosis process and that have not yet
been properly investigated

2.2 Product Features

Classification of plants based on leaf features is a critical job as
feature extraction (includes shape, margin, and texture) from binary
images of leaves may result in duplicate identification. However,
leaves are an effective means of differentiating plant species
because of their unique characteristics like area, diameter,
perimeter, circularity, aspect ratio, solidity, eccentricity, and narrow
factor.
Government College University Faisalabad Page 12

Fig : Plant disease detection

 Detects

The reason for using this Image for this presentation is that this
image show as many detection scenarios as possible in the dataset.
Government College University Faisalabad Page 13
Government College University Faisalabad Page 14

2.3 User Classes and Characteristics

Shape is the most popular feature used in plant leaf identification,
be it manual or automatic plant identification.

In the following paper, a study is conducted to investigate the most

contributing features among three low-level features for plant leaf
identification. Intra- and inter-class identification are conducted
using 455 herbal medicinal plant leaves, with 70% allocated for
training and 30% for testing dataset. Shape feature is extracted
using Scale Invariant Feature Transform (SIFT); color is
represented using color moments; and Segmentation-Based Fractal
Texture Analysis (SFTA) is utilized to describe texture feature. Intra-
class analysis showed that fusion of texture and shape surpassed
fusion of texture, shape and color. Single texture feature
identification also achieved highest identification rate compared to
identification using color or shape. Inter-class analysis further
support texture to be the discriminative feature among the low-level
features. Results demonstrate that single texture feature
outperformed color or shape feature achieving 92% identification
rate. Furthermore, fusion of all three features accomplished 94%
identification rate.

Leaf-based plant identification is favorable against molecular

biology techniques as it does not require the expertise of a
botanist1. Leaves are easier accessible and abundance compared
to other plant morphological structures such as flowers, barks or
fruits. In almost all automatic leaf plant identification, shape of the
leaves is the most common feature used for identification2 as it is
claimed to be the most discriminative features of a leaf.

As early as 1912, botanist such as Schneider4 has been using leaf

shape as taxonomic keys for text-based plant identification.
Government College University Faisalabad Page 15

Different species of plants have distinct shape characteristic, thus

the shape differences can be obvious even for non-expert. One of
the earliest automatic leaf identification that utilized leaf shape
parameters to differentiate weed species is done by Petry and
Kuhbauch5 in 1989. Recent similar work such as6,7,8 also used
leaf’s shape as one of the feature for plant identification. Leaf’s
shape, however is subject to deformations caused by disease,
insects or even human and mechanical damage. Therefore, colour
and texture features are further investigated to improve leaf-based
plant identification. Color is the most obvious morphological feature
of a leaf. In spite of that, color is the least popular low-level feature
for plant identification because it is considerably unstable due to its
seasonal color changes. In 9,10,13, color moments in RGB color
space comprising mean, standard deviation, skewness and kurtosis
are adopted to represent color features of plant leaves. This color
feature is known for its low dimension and low computational
complexity11, thus making it convenient for real-time applications.
Texture is another feature that can be used in plant identification to
describe the vein structure or leaf’s surface. Similar to color feature,
texture is considered as an additional feature to better describe
properties of the leaves. Kadir et al.9 extracted angular second
moment, contrast, inverse different moment, entropy and correlation
from the gray-level occurrence matrix of the leaf. More recent
studies utilized Radial Base function12, Gabor filters8, Haar
wavelet13 and multifractal detruded fluctuation analysis14 to
improve identification accuracy. A summary of the common features
used in selected leaf-based plant identification for the previous five
years is tabulated in Table 1.
Government College University Faisalabad Page 16

As can be seen in Table 1, shape has always been the de facto

feature for leaf-based plant identification.

Color and texture features are seen as contributing features to

improve the identification accuracy. Other than the most recent work
by Fang et al.14, previous work has always considered shape to be
the upmost feature for plant identification. Up to the time of this
writing, no study has been done to identify the most contributing
features among these three low-level features. Therefore, the aim of
this paper is to revisit the performance of the low-level features for
the purpose of plant leaf identification.
Government College University Faisalabad Page 17

In following table, some major shapes of leaves are given.

Government College University Faisalabad Page 18

2.4 Operating Environment

Important environmental factors that may affect development of
plant diseases and determine whether they become epiphytotic
include temperature, relative humidity, soil moisture, soil pH, soil
type, and soil fertility.

 Temperature
Each pathogen has an optimum temperature for growth. In
addition, different growth stages of fungi, such as the
production of spores (reproductive units), their germination,
and the growth of the mycelium (the filamentous main fungus
body), may have slightly different optimum temperatures.
Storage temperatures for certain fruits, vegetables, and
nursery stock are manipulated to control fungi and bacteria that
cause storage decay, provided the temperature does not
change the quality of the products. Little, except limited frost
protection, can be done to control air temperature in fields, but
greenhouse temperatures can be regulated to check disease
development.

 Relative humidity
Relative humidity is very critical in fungal spore germination
and the development of storage rots. Rhizopus soft rot of
sweet potato (Rhizopus stolonifer) is an example of a storage
disease that does not develop if relative humidity is maintained
at 85 to 90 percent, even if the storage temperature is optimum
for growth of the pathogen. Under these conditions, the sweet
potato root produces suberized (corky) tissues that wall off the
Rhizopus fungus.
Government College University Faisalabad Page 19

 Soil moisture
High or low soil moisture may be a limiting factor in the
development of certain root rot diseases. High soil-moisture
levels favour development of destructive water mold fungi,
such as species of Aphanomyces, Pythium, and Phytophthora.
Excessive watering of houseplants is a common problem.
Overwatering, by decreasing oxygen and raising carbon
dioxide levels in the soil, makes roots more susceptible to root-
rotting organisms.

 Soil fertility
Greenhouse and field experiments have shown that raising or
lowering the levels of certain nutrient elements required by
plants frequently influences the development of some
infectious diseases—for example, fire blight of apple and pear,
stalk rots of corn and sorghum, Botrytis blights, Septoria
diseases, powdery mildew of wheat, and northern leaf blight of
corn. These diseases and many others are more destructive
after application of excessive amounts of nitrogen fertilizer.
This condition can often be counteracted by adding adequate
amounts of potash, a fertilizer containing potassium.

 Water and humidity

Most growing plants contain about 90 percent water. Water
plays many roles in plants. It is:

A primary component in photosynthesis and respiration

Responsible for turgor pressure in cells (Like air in an inflated
balloon, water is responsible for the fullness and firmness of
plant tissue. Turgor is needed to maintain cell shape and
ensure cell growth.)
A solvent for minerals and carbohydrates moving through the
plant
Responsible for cooling leaves as it evaporates from leaf tissue
during transpiration
Government College University Faisalabad Page 20

A regulator of stomatal opening and closing, thus controlling

transpiration and, to some degree, photosynthesis
The source of pressure to move roots through the soil
The medium in which most biochemical reactions take place

3.System features

In our proposed technique, we used Histogram of Oriented

Gradients (HOG) and Local Binary Pattern (LBP)

3.1 System Feature 1

1) Histogram of Oriented Gradients (HOG)

One of the popular method of feature extraction is Histogram of

Oriented Gradients (HOG) [26]. In this method, an image is described
by a set of local histograms. Then, the occurrences of gradient
orientation is accumulated
Government College University Faisalabad Page 21

Is a small spatial localized portions of the image referred as cell. The

subsequent concatenation of 1-D histograms produces the features
vector. Let the intensity value of the image to be analyzed is L. If the
image is divided into N x N cells of size then the orientation ϴx, y of
the gradient in each pixel is calculated by using the following
Equation

The successive orientation i=1……..N2 belonging to the same cell j

are quantized and accumulated into an M-bins histogram. Then, we
ordered all the histograms and accumulated into a unique HOG
histograms which is our HOG features

3.2 System Feature 2

2) Binary Pattern (LBP)

One of the simple and efficient method of texture feature extraction is

Local Binary Pattern (LBP) introduced by Ojala and his colleagues
Government College University Faisalabad Page 22

used each pixel as a threshold, then transferred its 3 x 3

neighborhood into an 8-bit binary code.

The fixed order of this binary code reserves the texture direction
information around pixels. The number of variations in this way is 2P.
When in variation, there exist at most 2 times of 0 to 1 or 1 to 0, the
binary pattern is called uniform LBP and is denoted by LPBu2(P,R) .
The number of uniform pattern in a sampling density P is P2 – P + 2.
In our proposed system, we used uniform LBP to extract the feature
of leaves.
Government College University Faisalabad Page 23

4. External Interface Requirements

4.1 User Interfaces

 Front-end software: React Native
 Back-end software: .NET Core
 Database software: MySQL
 LDAP connection: Authentication in an enterprise environment

4.2 Hardware Interfaces

 Both Mac and Windows operating systems through their
default web browser
 iPhone
 Android
 Non-Functional Requirements
 Windows

4.3 Software Interfaces

Software used Description

Operating system We have chosen Windows operating

system for its best support and user-friendliness.
Government College University Faisalabad Page 24

Database To save the flight records, passengers

records we have chosen SQL+ database.

VB.Net To implement the project we have

chosen Vb.Net language for its more interactive support.

5. Other Nonfunctional Requirements

5.1 Performance Requirements

 The complete SRS of automatic plant detection should be read
before performing any particular working.
 The SRS should be understood in order to perform work of the
project in good manners.
 The SRS should be read and prof read by professionals only in
order to avoid any mistake.
 The SRS should be followed as compiled according to
headings.
 The working on SRS should start after reading and
understanding the whole project.
 The performance on this project shall start after taking
information and regulations from that person who has written
this project.
 The project should be performed in sequence.
 The safety and security requirements mentioned in the SRS
should be followed .

5.2 Safety Requirements

 This SRS should use shading to be redundant to prevent loss
of data.
Government College University Faisalabad Page 25

 Backups of the SRS should be done and be kept for one week.
 A duplicate file of the project should be saved in order to avoid
any inconveniences.
 The data put in project should be rechecked again and again to
avoid any mistakes until final publication.
 The data should be only shared to group of people working on
it in order to avoid any leakage of data.
 The data of this SRS should be easy to get.

5.3 Security Requirements

 Any keys used for the data collection should be stored
securely.
 Only the should be able to connect to the data.
 Databases should be behind a firewall.
 Data should be security in a private environment.
 Data should be secured by as much methods as possible.
 Data should not be shared to anyone who’s not part of the
project.
 Data should be made secured by only owners of projects.
 All data related to project should be stored in both software
and hardware forms

5.4 Software Quality Attributes

 Availability:
Because this application is critical to business communication, we will
have a goal of four nines(99.99%) availability.
 Correctness:
The application should never allow anyone to read data or
discussions not intended for that person.
 Maintainability:
Government College University Faisalabad Page 26

The application should use continuous integration so that features

and bug fixes can be deployed quickly without downtime.
 Usability:
The interface should be easy to learn without a tutorial and allow
users to accomplish their goals without errors.

6. WBS Project Management

Government College University Faisalabad Page 27

 Class diagram of automatic plant detection

Government College University Faisalabad Page 28

 Use case diagram

Government College University Faisalabad Page 29

7. Tools & Technologies

7.1 Programming Languages
Java, PHP, Ruby, C#, C / C++, SQL, PL/SQL, ASP .NET,
Objective-C, Visual Basic

7.2 Databases/Data storages

MySQL, PostgreSQL, Oracle, MS SQL Server, Derby,
Lucene/SOLR/Elastic Search, MongoDB, LDAP, etc.

7.3 Operating System

• Python. Java. Ruby/Ruby on Rails. HTML.
• JavaScript. C Language. C++ C#
• Objective-C. PHP. SQL. Swift
Government College University Faisalabad Page 30

Appendix A: Glossary

Abbreviations

 SQL = Structured Query Language

 NET = Network

 HOG = Histogram of Oriented Gradients

 BP = Binary Pattern

 SRS = Software requirements specifications

 CNN = Convolutional neural network

Government College University Faisalabad Page 31

Appendix B: Analysis Models

Government College University Faisalabad Page 32

Appendix C: Check List

Check List No
Yes

I. Starting/Ending Dates

II. Project Scope

III. Product modules (covering all aspects of

scope)

IV. System Features (covering scope)

V. Interface Requirements

VI. Non-Functional Requirements

VII. WBS

VIII. Tools and Technologies Detail (for

implementation)

IX. Plagiarism Report

Government College University Faisalabad Page 33

Appendix D: Supervisory Committee

For Approval of any two Consultant Teachers

Teacher Consulted Teacher Consulted

Name: ______________________________. Name: ______________________________.

Designation: _________________________ . Designation: _________________________ .

Comments:__________________________ Comments:__________________________

___________________________________ ___________________________________

___________________________________ ___________________________________

___________________________________ ___________________________________

___________________________________ ___________________________________

Signature: __________________________ Signature: __________________________

---------------------------------------------------------------------
Government College University Faisalabad Page 34

(For office use only)

Date:_____________

➢ Approved Group ID: ___________

____________

➢ Meeting Required: Date:___________ Time: ___________ Place: ___________________

➢ Rejected

Remarks:

___________________________________________________________________________________
___________________________________________________________________________________
___________________________________________________________________________________

___________________________________________________________________________________

Project Title (if Revised):

____________________________________________________________________________________

____________________________
Project Coordinator