lOMoARcPSD|44399087

Practical Review Report

Computer Programming (Birla Institute of Technology and Science, Pilani)

Scan to open on Studocu

Studocu is not sponsored or endorsed by any college or university

Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

CROP HEALTH MONITORING USING MACHINE

LEARNING

A PROJECT REPORT

Submitted by

M.PARAMESH (810018104060)

M.SHANMUGAVEL (810018104087)

in partial fulfillment for the award of the degree

of

BACHELOR OF ENGINEERING

in

COMPUTER SCIENCE AND ENGINEERING

UNIVERSITY COLLEGE OF ENGINEERING –BIT CAMPUS

TIRUCHIRAPALLI-620024

ANNA UNIVERSITY:: CHENNAI 600 025

JUNE 2022

i
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

ANNA UNIVERSITY: CHENNAI 600 025

BONAFIDE CERTIFICATE

Certified that this project report titled <CROP HEALTH MONITORING

USING MACHING LEARNING= is a bonafide work of <M.PARAMESH,
Reg. No. 810018104060 and M.SHANMUGAVEL, Reg. No.
810018104087= who carried out the project work under my supervision..

SIGNATURE SIGNATURE

Dr.G.ANNAPOORANI Mr.M.KRISHNAKUMAR

HEAD OF THE DEPARTMENT TEACHING FELLOW

Department of CSE/IT, Department of IT

University College of Engineering, University College of Engineering,

Anna University-BIT Campus, Anna University-BIT Campus,

Tiruchirappalli-620 024. Tiruchirappalli-620 024.

Submitted for the VIVA-VOCE to be held on

Internal Examiner External Examiner

ii
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

DECLARATION

We hereby declare that the work entitled <CROP HEALTH

MONITORING USING MACHINE LEARNING= is submitted in partial
fulfilment of the requirement for the award of the degree in B.E. University
College of Engineering, BIT Campus, Anna University, Tiruchirappalli, is
record of our own work carried out by us during the academic year 2021 – 2022
under the supervision and guidance of Mr.M.Krishnakumar, Teaching fellow,
Department of Information Technology, University College of Engineering,
BIT Campus, Anna University, Tiruchirappalli. The extent and source of
information are derived from the existing literature have been indicated through
the dissertation at the appropriate places. The matter embodied in this work is
original and has not been submitted for the award of any degree, either in this or
any other University.

M.PARAMESH (810018104060)

M.SHANMUGAVEL (810018104087)

I certify that the declaration made above by the candidate

Signature of the Guide,

Mr.M.Krishnakumar
TEACHING FELLOW,
Department of IT
University College of Engineering
Anna University –BIT Campus
Tiruchirappalli-620 024.

iii
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

ACKNOWLEDGEMENT

We would like to thank our honorable Dean Dr. T. SENTHILKUMAR,

Professor for having provided us with all required facilities to complete our
project without hurdles.

We would also like to express our sincere thanks to Dr. G. ANNAPOORANI,

Head of the Department of Computer Science and Engineering for her valuable
guidance, suggestions and constant encouragement paved way for the
successful completion of this project work.

We would like to thank our Project Coordinators Dr.I.SHAHANAZ BEGAM

Assistant Professor, Department of Computer Science and Engineering, Mr. K.
SARAVANA KUMAR, Teaching fellow, Department of Information
Technology, for their kind support.

We would like to thank and express our deep sense of gratitude to our project
guide, Mr.M.Krishnakumar, Teaching fellow, Department of Information
Technology BIT Campus, Anna University, Tiruchirappalli, for her valuable
guidance throughout the project. We also extend our thanks to all other teaching
and non-teaching staff for their encouragement and support.

We thank our beloved parents and friends for their full support in the moral
development of this project.

iv
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

ABSTRACT

In this project, we have developed a crop health monitoring system,

which will help a farmer to identify any visible disease in the crop leaf and
help him to limit the spread of the disease throughout the field. The sensors
installed in the field will continuously collect data about physical
parameters such as temperature, the humidity of the atmosphere, the
moisture content in soil and rain detection. If any of these parameters are
not suitable for a particular plant for which the system is configured, farmer
whose number is registered will get an alert about it. To check the plant
disease, farmers will have to upload a picture of the diseased area of the
plant on a web/android application. Once the disease is detected farmers
can take necessary actions to restrict the spread of disease and to cure it. To
determine the affected crop in the field. To determine the type of disease in
the crop .

v
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

TABLE OF CONTENTS

CHAPTER TITLE PAGE

NO NO

ABSTRACT V

LIST OF FIGURES Ix

LIST OF TABLES X

LIST OF ABBREVIATIONS XI

1 INTRODUCTION 1

1.1 Introduction in crop health monitoring 1

1.2 Problem identification 2

1.3 Effects of poor crop health monitoring 3

1.4 Crop health monitoring using Remote sensing 3

1.5 Crop health monitoring using IOT 5

1.5.1 Machine Learning 6

1.5.2 Types of Machine learning 7

1.6 Convolutional Neural Network 8

2 LITERATURE SURVEY 9

3 SYSTEM ANALYSIS 10

vi
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

3.1 Existing System 10

3.1.1 Disadvantage 11

3.1.2 Limitation 11

3.2 Proposed System 12

3.2.1 Adavantage of Proposed System 14

3.2.2 Architecture Description 16

4 SYSTEM SPECIFICATION 18

4.1 Requirements Analysis and Specification 18

4.2 Resource Requirements 18

4.3 Functional Requirements 19

4.4 NON-Functional Requirements 19

4.5 Software Requirements 20

4.6 Hardware Requirements 20

4.7 Technological Overview 20

4.7.1 Python 20

4.7.2 Python Programming Language 20

4.7.2.1 Python as a platform 26

4.8 History of Python 27

4.8.1 Python Platform 29

4.8.2 Open CV 30

vii
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

4.8.3 CNN in Python 33

5 SYSTEM DESIGN-UML DIAGRAMS 36

5.1 UML Diagrams 36

5.2 Goals 36

5.3 Data Flow Diagram 37

6 MODULE DISCRIPTION 40

6.1 Data Set Module 40

6.2 CNN Module 41

6.3 Checking Module 44

7 CONCLUSION 45

7.1 Conclusion 45

7.2 Future Enhancement 45

APPENDICES 46

REFERENCES 49

viii
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

LIST OF FIGURES
FIGURE NO TITLE PAGE
NO

3.1 Existing System Architecture 12

3.2 Proposed System Architecture 15

4.1 Working Module Of Python 25

4.2 Python Platform 27

5.1 Data Flow Diagram 38

ix
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

LIST OF TABLES

TABLE NO TITLE PAGE

NO

4.5 Software Requirements 20

4.6 Hardware Requirements 20

x
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

LIST OF ABBREVIATIONS

CNN Convolutional Neural Network

ML Machine Learning

DIP Digital Image Processing

CSV Comma Seperated Files

LoRA Long Range Communication

DLA Deep Learning Algorithm

DFD Data Flow Diagram

UML Unified Modelling Language

xi
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

CHAPTER 1

1. INTRODUCTION

1.1 Introduction in crop health monitoring

Crop health management utilizes modern information and communication

technologies, like IOT-enabled sensors or drones, to monitor the condition of crops as
well as critical environmental factors, like moisture levels. Smart agriculture
applications boast improved operational efficiency and allow farmers to quickly
respond to if conditions threaten their yield. Traditional methods for monitoring crops
rely heavily on human labour, sometimes including a physical inspection of each
individual plant for parasites or disease. This method is not only costly, but it8s also
highly prone to human error 3 say, missing a diseased leaf or failing to notice an
infestation, which can quickly degrade the quality of an entire yield. While IOT crop
health management or monitoring solutions require a higher upfront cost, they can
provide much more flexibility to scale, decrease operational costs over time, and
provide a more reliable long-term solution. Crop monitoring solutions use sensors to
track environmental changes in real-time. This can include conditions like
temperature, humidity, precipitation, and soil quality. In cases of swift environmental
changes, like an overnight freeze, crop monitoring solutions can enable farmers to
respond immediately, even if they aren8t on-site.

Benefits:

Reduce the human labour required to monitor the condition and health of crops,
minimizing human error and reducing labour costs. Maintain historical records of

1
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

changes in environmental factors to make better, more informed decisions. Receive

real-time alerts to infestations, disease or changes in critical environmental conditions
to reduce crop loss and decrease response time. Loop in remote stakeholders by
providing access to crop conditions from anywhere.

Types of crop diseases:

Bacterial Crop Diseases.

Fungal Crop Diseases.

Nematode Crop Diseases.
Viral Crop Diseases.
Parasitic Plants.
Disease Management via Satellite Data.

1.2 Problem identification:

Crop health monitoring is an area which requires lot of attention as a wrong

action taken would lead to crop failure.The challenge is to design a smart
application to monitor the crop health and provide the solution for the identified
pest attack.

2
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

1.3 Effects of poor crop health monitoring

Assessment of the health of a crop, as well as early detection of crop

infestations, is critical in ensuring good agricultural productivity. Stress associated
with, for example, moisture deficiencies, insects, fungal and weed infestations, must
be detected early enough to provide an opportunity for the farmer to mitigate. This
process requires that remote sensing imagery be provided on a frequent basis (at a
minimum, weekly) and be delivered to the farmer quickly, usually within 2 days.

Also, crops do not generally grow evenly across the field and consequently crop yield
can vary greatly from one spot in the field to another. These growth differences may
be a result of soil nutrient deficiencies or other forms of stress. Remote sensing allows
the farmer to identify areas within a field which are experiencing difficulties, so that
he can apply, for instance, the correct type and amount of fertilizer, pesticide or
herbicide. Using this approach, the farmer not only improves the productivity from his
land, but also reduces his farm input costs and minimizes environmental impacts.
There are many people involved in the trading, pricing, and selling of crops that never
actually set foot in a field. They need information regarding crop health worldwide to
set prices and to negotiate trade agreements. Many of these people rely on products
such as a crop assessment index to compare growth rates and productivity between
years and to see how well each country's agricultural industry is producing. This type
of information can also help target locations of future problems, for instance the
famine in Ethiopia in the late 1980's, caused by a significant drought which destroyed
many crops. Identifying such areas facilitates in planning and directing humanitarian
aid and relief efforts.

1.4 Crop health monitoring using remote sensing

Remote sensing has a number of attributes that lend themselves to monitoring

the health of crops. One advantage of optical (VIR) sensing is that it can see beyond
the visible wavelengths into the infrared, where wavelengths are highly sensitive to

3
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

crop vigour as well as crop stress and crop damage. Remote sensing imagery also
gives the required spatial overview of the land. Recent advances in communication
and technology allow a farmer to observe images of his fields and make timely
decisions about managing the crops. Remote sensing can aid in identifying crops
affected by conditions that are too dry or wet, affected by insect, weed or fungal
infestations or weather related damage. Images can be obtained throughout the
growing season to not only detect problems, but also to monitor the success of the
treatment. In the example image given here, a tornado has destroyed/damaged crops
southwest of Winnipeg, Manitoba.

Healthy vegetation contains large quantities of chlorophyll, the substance that gives
most vegetation its distinctive green colour. In referring to healthy crops, reflectance in
the blue and red parts of the spectrum is low since chlorophyll absorbs this energy. In
contrast, reflectance in the green and near-infrared spectral regions is high. Stressed or
damaged crops experience a decrease in chlorophyll content and changes to the
internal leaf structure. The reduction in chlorophyll content results in a decrease in
reflectance in the green region and internal leaf damage results in a decrease in near-
infrared reflectance. These reductions in green and infrared reflectance provide early
detection of crop stress. Examining the ratio of reflected infrared to red wavelengths is
an excellent measure of vegetation health. This is the premise behind some vegetation
indices, such as the normalized differential vegetation index (NDVI) (Chapter 4).
Healthy plants have a high NDVI value because of their high reflectance of infrared
light, and relatively low reflectance of red light. Phenology and vigour are the main
factors in affecting NDVI. An excellent example is the difference between irrigated
crops and non-irrigated land. The irrigated crops appear bright green in a real-colour
simulated image. The darker areas are dry rangeland with minimal vegetation. In a
CIR (colour infrared simulated) image, where infrared reflectance is displayed in

4
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

red, the healthy vegetation appears bright red, while the rangeland remains quite low
in reflectance.

Examining variations in crop growth within one field is possible. Areas of consistently
healthy and vigorous crop would appear uniformly bright. Stressed vegetation would
appear dark amongst the brighter, healthier crop areas. If the data is georeferenced, and
if the farmer has a GPS (global position satellite) unit, he can find the exact area of the
problem very quickly, by matching the coordinates of his location to that on the image.

1.5 Crop health monitoring using IOT

It is worth pondering how farmers have been managing crop health in recent
times as the demand for food is increasingly growing with an upsurge in the human
population. Previously, it was not considered much challenging to manage everything
manually, but with the growing production, population, and demand, it is now
becoming quite difficult for the farmers to keep a proper check on the quality of the
crops.
IoT in the farming sector is a significant advancement in terms of different sensors and
gateway connectivity. It is further attached to a user-friendly dashboard, which enables
an automated management system for simplified monitoring. Traditional crop health
management usually involves the use of fungicides, pesticides, manual labor, and
others. However, it is constantly changing due to scientific developments, financial
constraints, and societal pressures. The use of IoT technology is set to bring a
considerable change in the farming sector, involving development and improvements
concerning pest management and crop management programs. Crop management
integrates with pest monitoring to optimize plant health and profitable economic
returns, minimizing the negative effect on the environment. With the advent of IoT
technology, disease management has improved considerably. Farmers can now keep a

5
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

real-time check on various data parameters like nutrient effects, calcium, etc., to
ensure maximum yield and quality produce.

1.5 Machine learning

Machine learning (ML) is a type of artificial intelligence (AI) that allows software
applications to become more accurate at predicting outcomes without being explicitly
programmed to do so. Machine learning algorithms use historical data as input to
predict new output values. Recommendation engines are a common use case for
machine learning. Other popular uses include fraud detection, spam filtering, malware
threat detection, business process automation (BPA) and Predictive maintenance.
Machine learning is important because it gives enterprises a view of trends in customer
behavior and business operational patterns, as well as supports the development of
new products. Many of today's leading companies, such as Facebook, Google and
Uber, make machine learning a central part of their operations. Machine learning has
become a significant competitive differentiator for many companies. There are certain
advantages

Automation of Everything. Machine Learning is responsible for cutting the workload

and time.
Wide Range of Applications.
Scope of Improvement.
Efficient Handling of Data.
Best for Education and Online Shopping.
Possibility of High Error.
Algorithm Selection.
Data Acquisition.

6
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

1.5.1 Types of Machine learning

Classical machine learning is often categorized by how an algorithm learns to

become more accurate in its predictions. There are four basic approaches supervised
learning, unsupervised learning, semi-supervised learning and reinforcement learning.
The type of algorithm data scientists choose to use depends on what type of data they
want to predict.

Supervised learning:

In this type of machine learning, data scientists supply algorithms with labeled training
data and define the variables they want the algorithm to assess for correlations. Both
the input and the output of the algorithm is specified.

Unsupervised learning:

This type of machine learning involves algorithms that train on unlabeled data. The
algorithm scans through data sets looking for any meaningful connection. The data
that algorithms train on as well as the predictions or recommendations they output are
predetermined.

Semi-supervised learning:

This approach to machine learning involves a mix of the two preceding types. Data
scientists may feed an algorithm mostly labeled training data, but the model is free to
explore the data on its own and develop its own understanding of the data set.

Reinforcement learning:

Data scientists typically use reinforcement learning to teach a machine to complete a

multi-step process for which there are clearly defined rules. Data scientists program an
algorithm to complete a task and give it positive or negative cues as it works out how

7
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

to complete a task. But for the most part, the algorithm decides on its own what steps
to take along the way.

Deep learning algorithm

Deep learning is a subset of machine learning, which is essentially a neural

network with three or more layers. These neural networks attempt to simulate the
behavior of the human brain4albeit far from matching its ability4allowing it to
5learn6 from large amounts of data. While a neural network with a single layer can still
make approximate predictions, additional hidden layers can help to optimize and refine
for accuracy.Deep learning drives many artificial intelligence (AI) applications and
services that improve automation, performing analytical and physical tasks without
human intervention. Deep learning technology lies behind everyday products and
services (such as digital assistants, voice-enabled TV remotes, and credit card fraud
detection) as well as emerging technologies (such as self-driving cars).

1.6 Convolutional Neural Network:

A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm

which can take in an input image, assign importance (learnable weights and biases) to
various aspects/objects in the image and be able to differentiate one from the other. The
pre-processing required in a ConvNet is much lower as compared to other classification
algorithms. While in primitive methods filters are hand-engineered, with enough
training, ConvNets have the ability to learn these filters/characteristics.

The architecture of a ConvNet is analogous to that of the connectivity pattern of

Neurons in the Human Brain and was inspired by the organization of the Visual Cortex.
Individual neurons respond to stimuli only in a restricted region of the visual field
known as the Receptive Field. A collection of such fields overlap to cover the entire
visual area.

8
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

CHAPTER 2

LITERATURE SURVEY

Plant Disease Detection Techniques: A Review in the year of 2019 by

Gurleen Kaur Sandhu, Rajbir Kaur [1]

Image based Plant Disease Detection in Pomegranate Plant for Bacterial

Blight in the year of 2019 by Sharath D M, Akhilesh, S Arun Kumar, Rohan G,
Prathap C[2]

A survey on Plant Disease Identification using Machine Learning Approach

in the year of 2018 by Jyoti Shirahatti, Rutuja Patil, Pooja Akulwar[3]

Diseases Detection of Various Plant Leaf using Image Processing

Techniques A review in the year of 2019 by Santhosh Kumar S, Raghavendra
B[4]

Semi-automatic leaf disease detection and classification for soyabean culture

in the year of 2018 by Sukhvir Kaur, Shreelekha Pandey, Shivani Goel[5]

OpenCV Based Disease Identification of Mango Leaves in the year of

2016 by Jayaprakash Sethupathy, Veni S[6]
A Faster Technique on Rice Disease Detection using Image Processing of
Affected Area in Agro-Field in the year of 2018 by Taohidul Islam, Manish Sah,
Sudipto Baral, Rudra Roy Choudhury[7]

Recent Technologies of Leaf Disease Detection using Image Processing

Approach3 A Review in the year of 2017 by Bharat Mishra, Sumit Nema, Swapnil
Nema, Mamta Lambert[8]

9
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

CHAPTER 3

SYSTEM ANALYSIS
3.1 Existing System

Crop Health Monitoring System Using loT and Machine Learning Due to the inherent
agrarian aspect of the economy, the agricultural sector holds paramount importance in
many countries. Some countries have their GDP dependent on agriculture, but they
rely on manual crop monitoring, which is a system that is labor intensive and
ineffective. In comparison to this, in developing countries, many cutting-edge
technology based technologies are being used to increase crop yield with optimum
resource utilization. To this end, this invention suggested an integrated approach using
IoT, machine learning and drone technology for monitoring crop health. The
incorporation of these sensing modalities produces heterogeneous data which is not
only differing in absorbed parameter also in the temporal fidelity. The spatial
resolution of these approaches is also different, so the proposed scheme suggests the
optimum integration of these sensing modalities and their implementation in practice.
The proposed work is essentially an indigenous, technology-based agricultural solution
capable of providing important insights into crop health by extracting additional
features from the multi-modal data set and minimizing the effort to survey crops,
particularly useful when the agricultural land is large. Agriculture is the backbone of
our Nation. In olden days farmers used to guess the fertility of the soil and assumed to
grow which type of crop. They didn8t know about the moisture, level of water, and
particularly weather condition which terrifies a farmer more. They use pesticides based
on some assumptions which made leads to a serious effect on the crop if the

10
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

assumption is wrong. The productivity depends on the final stage of the crop on which
the farmer depends.

3.1.1 Disadvantages
1) Productivity may or may not be more
2) We cannot estimate weather conditions as pollution is increasing gradually etc

3.1.2 Limitations

1. Security and privacy: Security and privacy remain a major concern

deterring users from using IoT technology for medical purposes,
as healthcare monitoring solutions have the potential to be breached or
hacked. The leak of sensitive information about the patient8s health and
location and meddling with sensor data can have grave consequences, which
would counter the benefits of IoT.
2. Risk of failure: Failure or bugs in the hardware or even power failure can
impact the performance of sensors and connected equipment placing
healthcare operations at risk. In addition, skipping a scheduled software
update may be even more hazardous than skipping a doctor checkup.
3. Integration: There8s no consensus regarding IoT protocols and standards, so
devices produced by different manufacturers may not work well together.
The lack of uniformity prevents full-scale integration of IoT, therefore
limiting its potential effectiveness.
4. Cost: While IoT promises to reduce the cost of healthcare in the long-term,
the cost of its implementation in hospitals and staff training is quite high.

11
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Fig 3.1 Existing System Architecture

3.2 Proposed System

To enhance the productivity of the crop thereby supporting both farmer and nation we
have to use the technology which estimates the quality of crop and giving suggestions.
The wireless sensor network is sensors of different types are used to collect the
information of crop conditions and environmental changes this information is
transmitted through the network to the farmer or devices that initiate corrective action.

12
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Some disadvantages in communication must be overcome by advancing the

technology to consume less energy and also by making the user interface ease of use.
The main objective of this project is to design a smart Agriculture to monitor crop
growth. The system mainly consists of ESP-32 Microcontroller, Humidity Sensor,
Moisture Sensor, Temperature Sensor, Water level sensor along with LCD Display.
Initially the system will collect all the parameters regarding the crop and displays in
the LCD-Display.
All these parameters value is sent to the Thing Speak server using the Wi-Fi feature of
ESP-32. The server will display these values and send them to the webpage and on the
GUI based on Lab VIEW.
A GUI based on Lab View software is made the will display the data send by the
Thing speak server. The GUI is made for agricultural ministry who can access the real-
time data of a farmer8s field. The GUI will also display which disease is probable to
cause in particular crops due to changing environmental conditions.
The Overall system had been powered by using renewable energy resource i.e. Solar
Energy. The Solar-powered system had solved the problem of sustainable
development for agricultural fields. The system that we were proposing can be run
on the energy derived from the sun as well as the water motor pump that is used to
irrigate the fields that can also run on solar power.The additional feature of this project
is an automated irrigation facility. The farmer need not worry about watering his fields
whenever the soil becomes dry. The System continuously monitors the soil moisture
level and for the particular type of crop the requirement of water can be given
automatically by activating motor ON/OFF.
The various environment parameters can be accessed by farmers through his phone.
Farmers can access the website as well as the mobile app. The physical database that is
given to farmers will help him in predicting the disease in crops. The physical database
consists of different crops and their diseases with favorable conditions.

13
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

3.2.1 Advantage of proposed system

The project 5Crop Health Monitoring System6 is used to monitor the environmental
conditions like atmospheric temperature, atmospheric humidity, and soil moisture.
Depending on the values of these factors the health of the crop can be determined.
Different pathogens that cause different types of diseases in different crops. In our
project we have considered only three major crops of India i.e. Sugarcane, Wheat,
and Maize. The results of the collection of data i.e. atmospheric temperature,
atmospheric humidity, and soil moisture level on ThingSpeak IOT platform and as
well as on the website created based on Word Press is updated. The presence of
detection and classification of paddy disease can help the farmer to identify the
type of disease and take remedial measures based upon its classification. This can
prevent the over use of pesticides in the paddy field because using large amount of
pesticides in the field can damage the soil and water in the field and its surrounding
area.

14
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Architecture diagram

Fig 3.2 Proposed System Architecture

15
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

3.2.2 Architecture Description

Input documents

The input document is the database where all the predefined input files are
stored .The file stored will be checked for disease detection and classification

CSV File

A CSV is a comma-separated values file, which allows data to be saved in a

tabular format. CSVs look like a garden-variety spreadsheet but with a .csv
extension. Here we use the CSV file to save the input and the processing image.

Convolutional Neural Network

A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm

which can take in an input image, assign importance (learnable weights and biases) to
various aspects/objects in the image and be able to differentiate one from the other. The
pre-processing required in a ConvNet is much lower as compared to other classification
algorithms. While in primitive methods filters are hand-engineered, with enough
training, ConvNets have the ability to learn these filters/characteristics.

The architecture of a ConvNet is analogous to that of the connectivity pattern of

Neurons in the Human Brain and was inspired by the organization of the Visual Cortex.
Individual neurons respond to stimuli only in a restricted region of the visual field
known as the Receptive Field. A collection of such fields overlap to cover the entire
visual area.

16
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Machine learning:
Machine learning (ML) is a type of artificial intelligence (AI) that allows software
applications to become more accurate at predicting outcomes without being explicitly
programmed to do so. Machine learning algorithms use historical data as input to
predict new output values. Recommendation engines are a common use case for
machine learning. Other popular uses include fraud detection, spam filtering, malware
threat detection, business process automation (BPA) and Predictive maintenance.
Machine learning is important because it gives enterprises a view of trends in customer
behavior and business operational patterns, as well as supports the development of
new products. Many of today's leading companies, such as Facebook, Google and
Uber, make machine learning a central part of their operations. Machine learning has
become a significant competitive differentiator for many companies

17
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

CHAPTER 4

SYSTEM SPECIFICATION

4.1 Requirement Analysis and Specification

The requirement engineeering process consists of feasibility study, requirements

elicitation and analysis, requirements specification, requirements validation and
requirements management requirements elicitation and analysis is an iterative process
that can be represented as a spiral of activities, namely requirements discovery,
requirements classification and organization, requirements negotiation and
requirements documentation.

4.2 Resource Requirements

Software requirements is a sub-field of software engineering that deals with the

elicitation, analysis, specification and validation of requirements for software
requirements analysis in systems engineering and software engineering, encompasses
those tasks that go into determining the needs or conditions to meet for a new or
altered product, taking account of the possibly conflicting requirements of the various
stakeholders such as users. Requirements analysis is critical to the success of the
development project requirements must be actionable, measurable, testable related to
identified business needs or opportunities and defined to a level of detailed sufficient
for system design.

18
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

4.3 Functional Requirements

Functional Requirement defines a function of a software system and how the

system must behave when presented with specific inputs or conditions. These may
include calculations, data manipulation and processing and other specific functionality.

In this system following are the functional requirements: The Admin has to
login by using valid user name and password. After login Successful the admin gets
the input file and checks for any plagiarized content against all the available journals
in the database. The admin analysis the entire database and then proceeds with the
process of plagiarism detection.

4.4 Non– Functional Requirements

Non 3 Functional requirements, as the name suggests, are those requirements

that are not directly concerned with the specific functions delivered by the system.
They may relate to emergent system properties such as reliability response time and
store occupancy. Alternatively, they may define constraints on the system such as the
capability of the Input Output devices and the data representations used in system
interfaces. Many non-functional requirements relate to the system as whole rather than
to individual system features. This means they are often critical than the individual
functional requirements. The following non-functional requirements are worthy of
attention.

19
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

4.5 Software Requirements

Operating system Windows10

Front end Python

Back end PHP

Language Python

Database Csv.file

4.6 Hardware Requirements

Processor Core i5 8th gen

Hard disk 1 TB

RAM 4GB-6GB

4.7 TECHNOLOGY OVERVIEW

4.7.1 Python
Python technology is both a programming language and a platform.

4.7.2 Python Programming Language

Python is an interpreter, object-oriented, high-level programming language with
dynamic semantics. Its high-level built in data structures, combined with dynamic
typing and dynamic binding, make it very attractive for Rapid Application
20
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Development, as well as for use as a scripting or glue language to connect existing

components together. Python's simple, easy to learn syntax emphasizes readability and
therefore reduces the cost of program maintenance. Python supports modules and
packages, which encourages program modularity and code reuse. The Python
interpreter and the extensive standard library are available in source or binary form
without charge for all major platforms, and can be freely distributed.

Python programming language is one of dynamic and object-oriented programming

languages used for the development of diverse kinds of software developed by the
Python Software foundation. Its significant advantage is that facilitates integration
with other programing languages and software development tools. In addition, it has
in-built standard libraries that are extensive. This means that it facilitates the
development of a better source code.

The programming paradigm of Python language embarks on the readability of the

source code enhanced through clear syntax. Apart from object-oriented programming
paradigm, Python can implement other programming methodologies such as functional
programing and imperative programming (Beazley 67).

Another important feature of Python language that makes it suitable as a software

development tool is that it has a dynamic type system and its memory management
strategy is automatic. In addition, it can support the implementation of scripting
applications. It is important to note that the development model of Python language is
community based, implying that its reference implementation is free and bases on the
open source platform. There are various interpreters for the language for various
systems software, although programs developed by Python are executable in any
environment irrespective of operating system environment (Hetland 78).

21
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Brief history of Python programming language

The development of Python language began during the late 80s, with its
implementation done on the December of 1989. Python was a successor of the ABC
programming language, which had the capabilities of exception handling and
implementing an interface with the Amoeba System Software. The release of Python
2.0 during 2000 saw the inclusion of newer features such as offering support for
Unicode and garbage collection (Beazley 89).

The significant change was its transformation making its development process
community based. The release of Python 3.0 took place during 2008. Python language
boasts of winning two awards by the TIOBE as the programming of language of the
year during 2007 and 2010, resulting to an increase in the popularity of the language
(Hetland 56).

Implementation of web services in Python

A web service is defines as a program that can transform any client application to a
web-based application. The development of web services significantly depends on the
scripting abilities of a programming language. An important aspect of Python language
is that it can be used in scripting, implying that it is an effective development tool for
web services. Web services developed by Python function using the standard
messaging formats and they can be interfaced with other software development tools
using the conventional Application Programming Interface (API).

Web programming using Python entails two major paradigms: server programming
and client programming (Beazley 90). Server programming entails the development of
web services that run on the web server, while client programming entails the
development of web services that that run on the client side (Hetland 90). There are
diverse approaches to server programming, examples include the WebFrameworks

22
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

used for development of server side services using Python; CgiScripts used to write
scripting applications in Python; Webservers, which are server solutions developed
using Python.

Web services developed in Python are primarily used to offer access and functionality
of the APIs via the web. On the client side, Python language can be used in a number
of ways including Web Browser Programming, Web Client Programming and Web
services. There are various libraries in Python for the development of web services;
examples include the Simple Object Access Protocol (SOAP) and the Web Services
Description Language (WSDL).

Python language has extensive in-built tools that can provide support to Internet
protocols, coupled with its code readability characteristic, Python is therefore one of
the most appropriate programming languages that can be used in the development of
dynamic web content using the concept of dynamic programming. Some of the in-built
facilities included in Python that can facilitate dynamic programming and development
of web services include (Beazley 123):

1. Python comes with HTTP 1.1 server implementations, which has both file
servers and CGI servers. An important feature of this characteristic is that their
customization is easy and they incorporate the concept of automation of web
tasks. HTTP 1.1 has tools for the implementation of HTTP requests. In addition,
HTTP 1.1 implements secure web services.
2. Another important feature of Python is that is has features used for parsing and
constructing of Uniform Resource Locators (URLs). This is used to facilitate the
handling of URLs by the web service in a more efficient manner.
3. Python also has an included HTML and SGML modules used for parsing
HTML tags during the development of web services. SGNL is a part of the
parent language of Python language.

23
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

4. Python can also support XML since it has in-built XML parsing features and
SAX libraries embedded in the standard library.
5. Python can also handle CGI requests, facilitating the process of developing
codes for handling CGI.
6. Low-level sockets serve to enhance network programming, which is an
important strategy in the development web based applications.

Web Frameworks used in the development of web services in Python language

A web framework is an important aspect in the development of web services and web-
based applications. They allow the web developer to design web services without the
need deploy low-level protocols and sockets. Most of the available web frameworks
technology based on server side scripting, with a few frameworks supporting client
side scripting (Hetland 122).

Python language uses web frameworks for the development of web services through
providing an avenue through which web developers can simply write codes basing on
some standards of conformity to that particular framework. This concept of web
service development in Python is known as plugging. Python language web
frameworks provide diverse activities such as the interpretation of requests, production
of responses and persistent data storage.

These processes are an integral part of the web services development (Beazley 67). An
example of Python web frameworks is the Full stack frameworks, which consists of
high-level components such as Django, Grok, Pylons and TurboGears. Python
language can support other full stack web frameworks. The ability of Python language
to support diverse web frameworks makes it one of the best programming languages
that can be used for web service development.

24
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Often, programmers fall in love with Python because of the increased productivity it
provides. Since there is no compilation step, the edit-test-debug cycle is incredibly
fast. Debugging Python programs is easy: a bug or bad input will never cause a
segmentation fault. Instead, when the interpreter discovers an error, it raises an
exception. When the program doesn't catch the exception, the interpreter prints a stack
trace. A source level debugger allows inspection of local and global variables,
evaluation of arbitrary expressions, setting breakpoints, stepping through the code a
line at a time, and so on. The debugger is written in Python itself, testifying to Python's
introspective power. On the other hand, often the quickest way to debug a program is
to add a few print statements to the source: the fast edit-test-debug cycle makes this
simple approach very effective.

Fig 4.1 WORKING MODULE OF PYTHON

25
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Python uses code modules that are interchangeable instead of a single long list
of instructions that was standard for functional programming languages. The
standard implementation of python is called 5cpython6

4.7.2.1 Python as a Platform

A platform is the hardware or software environment in which a program runs.

We8ve already mentioned some of the most popular platforms like Windows 2000,
Linux, Solaris, and MacOS. Most platforms can be described as a combination of the
operating system and hardware. The Python platform differs from most other
platforms in that it8s a software-only platform that runs on top of other hardware-based
platforms. Python defines a an in-built module platform that provides system
information.

The Platform module is used to retrieve as much possible information about the
platform on which the program is being currently executed. Now by platform info, it
means information about the device, it8s OS, node, OS version, Python version, etc.
This module plays a crucial role when you want to check whether your program is
compatible with the python version installed on a particular system or whether the
hardware specifications meet the requirements of your program.

This module already exists in the python library and does not require any
installation using pip. Most commonly used python platforms

1. IDLE. IDLE (Integrated Development and Learning Environment)

2. PyCharm. PyCharm is a widely used Python IDE created by JetBrains.
3. Visual Studio Code. Visual Studio Code is an open-source (and free) IDE created by
Microsoft.
4. Sublime Text 3.
5. Atom.
26
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

6. Jupyter.
7. Spyder.
8. Pydev.

Fig 4.2 PYTHON PLATFORM

4.8 History of Python

The history of python is very interesting. Python is a widely-used general-purpose,

high-level programming language. It was initially designed by Guido van Rossum in
1991 and developed by Python Software Foundation. It was mainly developed for
emphasis on code readability, and its syntax allows programmers to express concepts
in fewer lines of code.

In the late 1980s, history was about to be written. It was that time when working on
Python started. Soon after that, Guido Van Rossum began doing its application-based
work in December of 1989 at Centrum Wiskunde & Informatica (CWI) which is
situated in the Netherlands. It was started firstly as a hobby project because he was
looking for an interesting project to keep him occupied during Christmas. The
programming language in which Python is said to have succeeded is ABC
Programming Language, which had interfacing with the Amoeba Operating System
27
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

and had the feature of exception handling. He had already helped to create ABC
earlier in his career and he had seen some issues with ABC but liked most of the
features. After that what he did was really very clever. He had taken the syntax of
ABC, and some of its good features. It came with a lot of complaints too, so he fixed
those issues completely and had created a good scripting language that had removed
all the flaws. The inspiration for the name came from BBC8s TV Show 3 7Monty
Python8s Flying Circus8, as he was a big fan of the TV show and also he wanted a
short, unique and slightly mysterious name for his invention and hence he named it
Python! He was the 5Benevolent dictator for life6 (BDFL) until he stepped down
from the position as the leader on 12th July 2018. For quite some time he used to
work for Google, but currently, he is working at Dropbox.
The language was finally released in 1991. When it was released, it used a lot fewer
codes to express the concepts, when we compare it with Java, C++ & C. Its design
philosophy was quite good too. Its main objective is to provide code readability and
advanced developer productivity. When it was released it had more than enough
capability to provide classes with inheritance, several core data types exception
handling and functions. The two of the most used versions has to Python 2.x & 3.x.
There is a lot of competition between the two and both of them seem to have quite a
number of different fanbases.

For various purposes such as developing, scripting, generation, and software testing,
this language is utilized. Due to its elegance and simplicity, top technology
organizations like Dropbox, Google, Quora, Mozilla, Hewlett-Packard, Qualcomm,
IBM, and Cisco have implemented Python.

Python has come a long way to become the most popular coding language in the
world. Python has just turned 30 and just recently at pycon22(python confrence) a
new feature was released by Anaconda foundation it8s known as pyscript with this
now python can be written and run in the browser like javascript which was
previously not possible, but it still has that unknown charm & X factor which can be
28
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

clearly seen from the fact that Google users have consistently searched for Python
much more than they have searched for Kim Kardashian, Donald Trump, Tom
Cruise, etc.
Python has been an inspiration for many other coding languages such as Ruby,
Cobra, Boo, CoffeeScript ECMAScript, Groovy, Swift Go, OCaml, Julia, etc.

4.8.1 PYTHON Platform

There are two types of platforms software-based and hardware-based.

Python provides a software-based platform. A platform is the hardware or software
environment in which a program runs. We8ve already mentioned some of the most
popular platforms like Windows 2000, Linux, Solaris, and MacOS. Most platforms
can be described as a combination of the operating system and hardware. The Python
platform differs from most other platforms in that it8s a software-only platform that
runs on top of other hardware-based platforms. Python defines a an in-built module
platform that provides system information.

The Platform module is used to retrieve as much possible information about the
platform on which the program is being currently executed. Now by platform info, it
means information about the device, it8s OS, node, OS version, Python version, etc.
This module plays a crucial role when you want to check whether your program is
compatible with the python version installed on a particular system or whether the
hardware specifications meet the requirements of your program.
29
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

This module already exists in the python library and does not require any
installation using pip. Most commonly used python platforms

1.IDLE. IDLE (Integrated Development and Learning Environment)

2.PyCharm. PyCharm is a widely used Python IDE created by JetBrains.
3.Visual Studio Code. Visual Studio Code is an open-source (and free) IDE created by
Microsoft.
4.Sublime Text 3.
5.Atom.
6.Jupyter.
7.Spyder.
8.Pydev.
4.8.2 Open CV
OpenCV (Open Source Computer Vision Library) is an open source
computer vision and machine learning software library. OpenCV was built to provide
a common infrastructure for computer vision applications and to accelerate the use of
machine perception in the commercial products. Being a BSD-licensed product,
OpenCV makes it easy for businesses to utilize and modify the code.

The library has more than 2500 optimized algorithms, which includes a comprehensive
set of both classic and state-of-the-art computer vision and machine learning
algorithms. These algorithms can be used to detect and recognize faces, identify
objects, classify human actions in videos, track camera movements, track moving
objects, extract 3D models of objects, produce 3D point clouds from stereo cameras,
stitch images together to produce a high resolution image of an entire scene, find
similar images from an image database, remove red eyes from images taken using
flash, follow eye movements, recognize scenery and establish markers to overlay it
with augmented reality, etc. Open CV has more than 47 thousand people of user

30
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

community and estimated number of downloads exceeding 18 million. The library is

used extensively in companies, research groups and by governmental bodies.

Along with well-established companies like Google, Yahoo, Microsoft, Intel, IBM,
Sony, Honda, Toyota that employ the library, there are many startups such as Applied
Minds, Video Surf, and Zeitera, that make extensive use of OpenCV. OpenCV8s
deployed uses span the range from stitching streetview images together, detecting
intrusions in surveillance video in Israel, monitoring mine equipment in China, helping
robots navigate and pick up objects at Willow Garage, detection of swimming pool
drowning accidents in Europe, running interactive art in Spain and New York,
checking runways for debris in Turkey, inspecting labels on products in factories
around the world on to rapid face detection in Japan.

The library has more than 2500 optimized algorithms, which includes a comprehensive
set of both classic and state-of-the-art computer vision and machine learning
algorithms. These algorithms can be used to detect and recognize faces, identify
objects, classify human actions in videos, track camera movements, track moving
objects, extract 3D models of objects, produce 3D point clouds from stereo cameras,
stitch images together to produce a high resolution image of an entire scene, find
similar images from an image database, remove red eyes from images taken using
flash, follow eye movements, recognize scenery and establish markers to overlay it
with augmented reality, etc. Open CV has more than 47 thousand people of user
community and estimated number of downloads exceeding 18 million. The library is
used extensively in companies, research groups and by governmental bodies.

Along with well-established companies like Google, Yahoo, Microsoft, Intel, IBM,
Sony, Honda, Toyota that employ the library, there are many startups such as Applied
Minds, Video Surf, and Zeitera, that make extensive use of OpenCV. OpenCV8s
deployed uses span the range from stitching streetview images together, detecting
intrusions in surveillance video in Israel, monitoring mine equipment in China, helping
31
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

robots navigate and pick up objects at Willow Garage, detection of swimming pool
drowning accidents in Europe, running interactive art in Spain and New York,
checking runways for debris in Turkey, inspecting labels on products in factories
around the world on to rapid face detection in Japan.

It has C++, Python, Java and MATLAB interfaces and supports Windows,
Linux, Android and Mac OS. OpenCV leans mostly towards real-time vision
applications and takes advantage of MMX and SSE instructions when available. A
full-featured CUDA and OpenCL interfaces are being actively developed right now.
There are over 500 algorithms and about 10 times as many functions that compose or
support those algorithms. OpenCV is written natively in C++ and has a templated
interface that works seamlessly with STL containers. OpenCV is the huge open-source
library for the computer vision, machine learning, and image processing and now it
plays a major role in real-time operation which is very important in today8s systems.
By using it, one can process images and videos to identify objects, faces, or even
handwriting of a human. When it integrated with various libraries, such as NumPy,
python is capable of processing the OpenCV array structure for analysis. To Identify
image pattern and its various features we use vector space and perform mathematical
operations on these features.

The first OpenCV version was 1.0. OpenCV is released under a BSD license and
hence it8s free for both academic and commercial use. It has C++, C, Python and Java
interfaces and supports Windows, Linux, Mac OS, iOS and Android. When OpenCV
was designed the main focus was real-time applications for computational efficiency.
All things are written in optimized C/C++ to take advantage of multi-core processing.

32
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

4.8.3 Convolutional Neural Network in Python

 Convolutional Neural Network is a Deep Learning algorithm specially designed

for working with Images and videos. It takes images as inputs, extracts and learns
the features of the image, and classifies them based on the learned features. CNNs
are neurobiological-driven by the findings of locally sensitive and orientation-
selective nerve cells in the visual cortex.

 They are a multi-layer neural network.

 They implicitly extract relevant features.

 They are a feed-forward network that can extract topological features from images.

 They recognize visual patterns directly from pixel images with minimal
preprocessing.

 They are astonishingly powerful because they can easily recognize patterns that
have extreme variability. e.g., hand-writing.

 CNNs are trained with a version of the backpropagation algorithm.

 CNNs have the neuronal cells in the visual cortex, making the base behind CNNs
and watches for particular features.
 t has been very helpful in monitoring suspicious banking transactions, as well as
in video surveillance systems or CCTV.Figure 4: A typical CNN
architecture .Besides input and output layers, CNN has many hidden layers in
between which may be classified as-Convolutional Layer:- This layer performs
the core operations of training and forms the basis of CNN.
 Each layer has a single set of weights for all neurons and each neuron is
responsible for processing a small part of the input space. Thus, the

33
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

convolutional layer is just an image convolution of the previous layer, where the
weights specify the convolution filter . Pooling Layer:- This layer also known as
downsampling layer, is placed after the convolutional layer. Pooling layer is
responsible for reducing the spatial size (Width x Height) of the Input Volume
which will be passed to the next convolutional Layer.
 Fully Connected Layer:- This layer connects each neuron on previous layer with
all the neurons present on the next layer. Facial detection/Recognition using
CNN:- A human brain sees multiple images in a day and is able to distinguish
each one accurately without realizing how the processing is done.
 But, there is a different case with machines because they have to recognize an
image on the basis of learning. Facial detection is a method to identify a person
or object based on their unique features and this process involves the detection
and extraction of the face from the original image or video. After this, the face
recognition takes place where different complex computer algorithms are used
to recognize a face.
 Here, we will understand the entire process of face detection and recognition. A
face detection system involves two phases: Enrollment Phase. Face Detection.
In this phase, several pictures of the same person is captured to whom the
system should recognize as "known" with different facial expressions and head
positions.
 Feature Extraction- In this step, different feature measures are applied which
can better describe a human face. There are different algorithms such as
Principal Component Analysis (PCA), Haar Features, Local Binary Pattern
(LBP) etc. available for the facial measurement. On the basis of these
measurements, CNN is trained for learning in future. Storing in Database- All
the extracted features are stored in a database so that they can be used further in
identification process.
 Face Detection- When an image is admitted for identification, It is checked that
whether it matches with the captured and stored images from the database by
34
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

using face detection algorithms. Pre-processing- Pre-processing is necessary to

make an easier and smooth training phase.
 The collected face images or video frames need to be passed through Pre-
processing phase to eliminate the noise, blur, shadows, lighting and other
unwanted factors. The final smooth image obtained so, will be passed to the
next feature extraction phase.Feature Extraction- After Pre-processing phase,
feature extraction is carried out by the CNN which was trained during
Enrollment phase.
 Recognition- This is the last step where a suitable classifier such as Nearest
Neighbor, Bayesian classifier, Euclidean Distance classifier etc., can be chosen.
This classifier compares the feature vector stored in the database with the query
feature vector and finally the best matched face image comes as a recognition
output.
 Conclusion

 Biometric verification/authentication is going to be deployed everywhere from

government to private organizations in coming days. In this paper, we studied
the relation among AI, ML, DL, ANN and CNN. We have also demonstrated
the way CNN carries facial detection with improved accuracy. The field of AI
has a wide spectrum and open for researchers. So, it aims to provide better result
in biometric security in future.

35
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

CHAPTER 5

SYSTEM DESIGN-UML DIAGRAMS

5.1 UML Diagrams

UML stands for unified modeling language. UML is a standardized general-

purpose modeling language in the field of object-oriented software engineering. The
standard is managed, and was created by, the object management group.
The goal is for UML to become a common language for creating models of
object oriented computer software. In its current form UML is comprised of two major
components: a meta-model and a notation. In the future, some form of method or
process may also be added to; or associated with, UML.
The Unified Modeling Language is a standard language for specifying,
visualization, constructing and documenting the artifacts of software system, as well as
for business modeling and other non-software systems.
The UML represents a collection of best engineering practices that have proven
successful in the modeling of large and complex systems.
The UML is a very important part of developing objects oriented software and
the software development process. The UML uses mostly graphical notations to
express the design of software projects.
5.2 Goals
The primary goals in the design of the UML are as follows:

36
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

1. Provide users a ready-to-use, expressive visual modeling language so that

they can develop and exchange meaningful models.
2. Provide extendibility and specialization mechanisms to extend the core
concepts.
3. Be independent of particular programming languages and development
process.
4. Provide a formal basis for understanding the modeling language.
5. Encourage the growth of OO tools market.
6. Support higher level development concepts such as collaborations,
frameworks, patterns and components.
7. Integrate best practices.
5.3 Data flow diagram
A Data Flow Diagram (DFD) maps out the flow of information for any process
or system. It uses defined symbols like rectangles, circles and arrows, plus short text
labels, to show data inputs, outputs, storage points and the routes between each
destination. Data flowcharts can range from simple, even hand-drawn process
overviews, to in-depth, multi-level DFD that dig progressively deeper into how the
data is handled. They can be used to analyze an existing system or model a new one.
Like all the best diagrams and charts, a DFD can often visually 5say6 things that would
be hard to explain in words, and they work for both technical and nontechnical
audiences, from developer to CEO. That8s why DFD remain so popular after all these
years. While they work well for data flow software and systems, they are less
applicable nowadays to visualizing interactive, real-time or database-oriented software
or systems.

37
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Data Flow Diagram

LEVEL 0:

38
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

LEVEL 1:

39
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

CHAPTER 6

MODULE DESCRIPTION

For detecting disease in crop , it has three modules to test them functionality:

1. Dataset module
2. CNN module
3. Checking module

6.1 Dataset module:

40
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

The first module is the database module here all the databases of crop are
collected and stored in csv.file format

6.2 CNN module

41
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

Here all the crops are classified under CNN algorithm. CNN algorithm takes the input
from the user in the form of image or digital format and classify them according to
their similarities and differences

Here all the crops are differentiated and their loss and valency modes are
identified.

42
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

The crop is selected for disease is called as input file. Here the selected crop is
classified and detected

43
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

6.3 Checking Module

The output screen is displayed in the form of crop image. The graphical lines in
the crop shows the size of the crop. The biggest black spot refers the type of infection
in the crop.

44
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

CHAPTER 7

7.1 Conclusion

The presence of detection and classification of paddy disease can help the farmer to
identify the type of disease and take remedial measures based upon its
classification. This can prevent the over use of pesticides in the paddy field because
using large amount of pesticides in the field can damage the soil and water in the
field and its surrounding area. The mobile application provided to the farmer can
help them in taking best remedies for the affected crop.

7.2Future Enhancement

The project can be developed by sending an alert message to the agricultural

department. The agricultural department can use these alert messages to know
about the condition of farming in the nearby villages. When the agricultural
department gets more than 10 alert messages they can infer that the nearby villages
are facing a critical problem. Another development can be made in the
classification part. We can use better classification algorithms to speed up the
process and improve the accuracy in classifying the disease. In case of rural areas
where there is no proper Wi-Fi connection we can use the GSM and GPS modules
for sending the alert to the farmer and finding the location of the farmer8s field. We
can also use the LoRA (Long Range Communication) network for faster and long
range communication. We can develop the mobile application with more
commonly known languages like Hindi, Tamil, Telugu, etc.

45
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

APPENDICES

import numpy as np
os.listdir("../input/new-plant-diseases-dataset/New Plant Diseases
Dataset(Augmented)/New Plant Diseases Dataset(Augmented)/train/") def
prediction(path):

img = load_img(path, target_size = (256,256)) i =

img_to_array(img)

plt.figure(figsize = (5,5))
plt.imshow(img) plt.show()
im = preprocess_input(i)
img = np.expand_dims(im, axis = 0) pred =
np.argmax(model.predict(img))
print(f"CLASSIFICATION {ref[pred]}
from keras.layers import Dense, Flatten from
keras.models import Model
from keras.applications.vgg19 import VGG19
import keras
base_model = VGG19(input_shape=(256, 256,
3), include_top = False) for layer in
base_model.layers:
layer.trainable = False
X = Flatten()(base_model.output)
X = Dense(units = 38, activation = 'softmax')(X)
model = Model(base_model.input, X)
from keras.callbacks import ModelCheckpoint,
EarlyStopping

46
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

es = EarlyStopping(monitor = 'val_accuracy',
min_delta = 0.01, patience = 3, verbose = 1)
mc = ModelCheckpoint(filepath =
"best_model.h5", monitor = "val_accuracy",
min_delta = 0.01,
patience = 3,
verbose = 1, save_best_only = True)

cb = [es, mc]
his = model.fit_generator(train,
steps_per_epoch = 16,
epochs = 50,
verbose = 1, callbacks = cb, validation_data =
val,
validation_steps = 16)

h = his.history h.keys() plt.plot(h['accuracy'])

plt.plot(h['val_accuracy'], c = "red")
plt.title("Accuracy vs Validation Accuracy")
plt.show()
im = preprocess_input(i)

img = np.expand_dims(im, axis = 0) pred =

np.argmax(model.predict(img))
print(f"CLASSIFICATION {ref[pred]}")
path = "../input/new-plant-diseases-dataset/New
Plant Diseases
Dataset(Augmented)/New Plant Diseases
Dataset(Augmented)/valid/Corn_(maize)__
_Cercospora_leaf_spot
Gray_leaf_spot/00120a18-ff90-46e4-92fb-
2b7a10345bd3___RS_GLSp 9357.JPG"

47
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

prediction(path)
his = model.fit_generator(train,
steps_per_epoch = 16,
epochs = 50,
verbose = 1, callbacks = cb, validation_data =
val,
validation_steps = 16)

h = his.history h.keys() plt.plot(h['accuracy'])

plt.plot(h['val_accuracy'], c = "red")
plt.title("Accuracy vs Validation Accuracy")
plt.show()
im = preprocess_input(i)

img = np.expand_dims(im, axis = 0) pred =

np.argmax(model.predict(img))
print(f"CLASSIFICATION {ref[pred]}")
path = "../input/new-plant-diseases-dataset/New
Plant Diseases
Dataset(Augmented)/New Plant Diseases
Dataset(Augmented)/valid/Corn_(maize)__
_Cercospora_leaf_spot
Gray_leaf_spot/00120a18-ff90-46e4-92fb-
2b7a10345bd3___RS_GLSp 9357.JPG"
prediction(path)

48
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

REFERENCES

[1]Abdelouahab Moussaoui, Kamel Boukhalfa and Mohammed Brahimi,

5Deep Learning for Tomato Diseases: Classification and Symptoms
Visualization6, vol. 31, no.4, 2993315, Taylor & Francis, 2017.
[2]Abu Bakar.M.N, A.H. Abdullah, N. Abdul Rahim and H. Yazid, 5Rice Leaf
Blast Disease Detection Using Multi-Level Color Image Thresholding6 in
proceedings of Research Gate, Article· August-2018.

[3]Akhil, Sujatha R and Y Sravan Kumar, 5Leaf Disease Detection using

Image Processing6 in Journal of Chemical and Pharmaceutical
Sciences,March2017
[4]Al-Hiary.H. AlRahamneh.Z, Bani-Ahmad.S, M.Braik and M.Reyalat, 5Fast and
Accurate Detection and Classification of Plant Diseases6, International Journal of
Computer Applications, Vol.17,No.1, pp.31-38.March 2011.

[5]Andras Anderla, Dubravko Culibrk, Darko Stefanovic, Marko Arsenovic, and

Srdjan Sladojevic, 5Deep Neural Networks Based Recognition of Plant Diseases
by Leaf Image Classification6, Hindawi Publishing Corporation Computational
Intelligence and Neuroscience, Vol 2016, Article ID 3289801, 11 pages.

[6]Dhivya, R.Latha, S.Rajesh, R.Saradhambal, 5Plant Disease Detection and its

Solution using Image Classification6, International Journal of Pure and Applied
Mathematics, Volume 119, Issue 14, pp. 879-884, 2018.

49
Downloaded by Barb Olivia (barbolivia47@gmail.com)
 lOMoARcPSD|44399087

[7]Geethaiakshmi S.N and Valliammai.N, 5Multiple noise reduction using

hybrid method for leaf recognition6 2012 International Conference on
Devices,Circuits and Systems (ICDCS), 15-16 March 2012, Coimbatore, India.

[8]Gittaly Dhingra, Hem Dutt Joshi and Vinay Kumar, 5Study of digital image
processing techniques for leaf disease detection and classification,6Springer-
Science, 29 November.

[9]Guan Wang, Jianxin Wang and Yu Sun, 5Automatic Image-Based Plant Disease
Severity Estimation Using Deep Learning6 Hindawi Computational Intelligence
and Neuroscience Volume 2017.

50
Downloaded by Barb Olivia (barbolivia47@gmail.com)