STEGANOGRAPHY AND CRYPTOGRAPHY USING

COLOR IMAGE BASED ON DIGITAL SIGNATURE

CONCEPT

A PROJECT REPORT

Submitted by

AKRAM BASHA.I 422518106004

LOGANATHAN.S 422518106024

MEGAVANNAN.S 422518106705

in partial fulfillment for the award of the degree

of

BACHELOR OF ENGINEERING

in

ELECTRONICS AND COMMUNICATION ENGINEERING

UNVERSITY COLLEGE OF ENGINEERING VILLUPURAM

ANNA UNIVERSITY: CHENNAI 600 025

JUNE 2022
 ANNA UNIVERSITY, CHENNAI-600 025
BONAFIDE CERTIFICATE

Certified that this project report “STEGANOGRAPHY AND

CRYPTOGRAPHY USING COLOR IMAGE BASED ON DIGITAL
SIGNATURE CONCEPT” is the work of “AKRAM BASHA.I (422518106004),
LOGANATHAN.S (422518106024), MEGAVANNAN.S (42251806705)” who
carried out the project work under my supervision.

SIGNATURE SIGNATURE

Dr.A.SARASWATHI ,M.Tech,Ph.D., Dr. D.PALANI ,M.E.,Ph.D.,

HEAD OF THE DEPARTMENT SUPERVISOR
Department of ECE, Assistant Professor,
University College of Engineering Department of ECE,
Villupuram, Villupuram-605 103. University College of Engineering
Villupuram, Villupuram-605 103.

Submitted for the university examination held on …………………

Internal Examiner External Examiner

 ACKNOWLEDEMENT

We would like to thank our respected Dean. Dr. R.SENTHIL, ME, Ph.D., for
Providing good environment and facilities to complete the project.

We express our sincere thanks to our respectful Head of the Department Dr.
A.SARASWATHI, M. Tech., Ph.D., for her great support in completing this
project.

We thank our beloved project guide Dr. D.PALANI, M.E., Ph.D., for providing
perfect guidance and continuously inspiring us in positive way and to learn more
about our project, instead of just finishing it.

We would like to thank the project Co-ordinators Dr.D.PALANI, Mr.

E.VENKATRAMAN and Mr. V. RAJA for their valuable suggestions and
guidance for the development and completion of this project.

We deliver our profound and benevolent thanks to all the Staff members in the
Department of Electronics and Communication Engineering, who enunciated the
project with their encouraging guidance.

We will be faulty in our duty if we don’t thank our parents for their benevolence
and blessings which stood us in good stead during the course of the project.

AKRAM BASHA.I

LOGANATHAN.S

MEGAVANNAN.S
 ABSTRACT

Data Transmission in network security is one of the most vital issues in

today’s communication world. The vigorous growth in the field of information
communication has made information transmission much easier. But this type of
advancement has opened up many possibilities of information being snooped. So,
day-by-day maintaining of information security is becoming an inseparable part
of computing and communication.

In this project, we explored techniques that blend cryptography &

steganography together. In steganography, information is kept hidden behind a
cover image.

In this project, approaches for information hiding using both cryptography

& steganography is proposed keeping in mind two considerations - size of the
encrypted object and degree of security.

Here, signature image information is kept hidden into cover image using
private key of sender & receiver, which extracts the information from stego image
using a public key.

This approach can be used for message authentication, message integrity

& non- repudiation purpose.

i
 TABLE OF CONTENTS

CHAPTER TOPIC PAGE NO

1 INTRODUCTION 01

1.1 OBJECTIVE 01

1.2 NEED FOR THE PROJECT 01

2 LITERATURE SURVEY 02

2.1 EXISTING SYSTEM 02

2.2 PROPOSED SYSTEM 02

2.3 ADVANTAGES OF PROPOSED WORK 03

2.4 LIST OF EVALUTION OF EXISTING WORK 04

3 METHODOLOGY 07

3.1 BLOCK DIAGRAM 07

3.2 DESIGN METHODOLOGY 07

3.2.1 Hiding Text Image 07

3.2.1.1 Algorithm for encoding 07

3.2.1.2 Algorithm for decoding 08

3.2.2 Hiding Text Inside Image 09

ii
 3.2.2.1 Algorithm for encoding 09

3.2.2.2 Algorithm for decoding 10

3.3 BRIEF METHODOLOGY 11

3.4 APPROACH FOR HIDING INFORMATION 12

3.5 CONCEPT 12

3.5.1 Steganography 12

3.5.2 Cryptography 13

3.5.3 Specification of design 13

3.5.4 Digital Signature Image 14

3.5.5 Pixel Concept 15

3.5.6 Implementation of User Interface 16

3.5.7 Requirements of the information 18

4 COMPONENTS 19

4.1 COMPONENTS 19

4.1.1 Specification 19

4.1.2 User Interface Requirements 20

4.1.3 Usability 20

4.2 SYSTEM REQUIREMENT 21

4.2.1 Minimum Hardware Requirement 21

iii
 4.2.2 Minimum Software Requirement 21

5 SOFTWARE REQUIREMENTS 22

INTRODUCTION 22

5.1 DATA MINING 22

5.2 BIG DATA 23

5.2.1 The Four Dimension of Big Data 23

5.3 THE BIG DATA PLATFORM MANIFESTO 24

5.4 SOME CONCEPT 25

5.5 HADOOP 25

5.5.1 Some Hadoop Related Names to Know 26

5.5.2 What to do with data 26

6 RESULT AND DISCUSSION 28

7 CONCLUTION 30

REFERENCE 31

iv
 LIST OF FIGURES

NO TITLE PAGE NO

3.1 FUNCTIONAL BLOCK DIAGRAM 07

3.2.1.1 ENCODING PROCESS 07

3.2.1.2 DECODING PROCESS 08

3.2.2 STEGO IMAGE WITH HIDDEN MESSAGE 09

3.5.4 DIGITAL SIGNATURE 15

3.5.5 8 BIT REPRESENTATION 15

3.5.5.1 RGB COLOR MODEL 16

3.5.6.1 IMPORTED LIBRARY 17

3.5.6.2 CREATED USER INTERFACE 17

v
 LIST OF ABBREVIATIONS

S.NO ABBREVIATION MEANING

1 LSB Least Significant Bit

2 RSA Riverst Shamir Adleman

3 RGB Red Green Blue

4 ASCII American Standard Code for Information Interchange

5 PyPI Python Package Indexes

6 CLI Command Libraries Interface

7 SQL Structured Query Language

8 HDFS Hadoop Distributed File System

9 ACID Atomicity Consistency Isolation Durability

10 HQL Hive Query Language

11 AI Artificial Intelligence

12 PSNR Peak Signal to Noise Ratio

13 MSE Mean Squared Error

14 SSIM Structural Similarly Index for Measuring

15 KDD Knowledge Discovery in Databases

16 DCT Discrete Cosine Transforms

17 CISPDM Cross Industry Standard Process for Data Mining

vi
 CHAPTER 1

INTRODUCTION

1.1 OBJECTIVE

For secured data transmission with reduced encrypted object and high degree
of security. Hacking by 3rd party is completely reduced.

In this approach, color image information is encrypted by sender’s private

key and then embedded into cover object. Along with this, blending of
steganography is as usual providing the support for secrecy in transmission.

This approach supports the concept of Digital Signature. At the receiver end,
from the stego image, the encrypted color image information is being extracted
and using the sender’s public key, original image information is decrypted.

1.2 NEED FOR THE PROJECT

This permits a person to conceal information in the file and assure that no
human involvement could notice the alteration in the file. The LSB method
performs in a superior way in image files which needs to have an inflated
resolution and locate various colors.

LSB method also performs well with audio files that have dissimilar
sounds and an enhanced bit rate. The LSB procedure normally does not only
facilitate the file size, but depending on the magnitude of the information that is
to be concealed inside the file, the file can become perceptively twisted.

1
 CHAPTER 2

LITERATURE SURVEY

2.1 EXISTING SYSTEM

A digital signature scheme is a strategy for signifying the authenticity of a

digital message or document. A genuine digital signature supplies the receiver a
motive to consider that the digital message was generated by a familiar sender
and that it was not altered.

Digital signatures are generally used to distribute software, deal financially

and to unearth counterfeit. Image information is being hidden using RSA
algorithm, thereby generating a private key.

The LSB procedure normally does not only facilitate the file size, but
depending on the magnitude of the information that is to be concealed inside the
file, the file can become perceptively twisted.

Here, some innovative algorithm is applied that will help to bring the
modification very less. The algorithm will support to prevent illusion regarding
the hidden data within the original image.

Image information is being hidden using RSA algorithm, thereby generating a

private key. Then, that encrypted data is being hidden into a cover image file and
thus a stage image is obtained. Thus, the encrypted data is retrieved at receiver’s
end and then using the public key the original information is obtained by the
receiver.

DISADVANTAGES

Here, some innovative algorithm is applied that will help to bring the
modification very less. The algorithm will support to prevent illusion regarding
the hidden data within the original image.

2
 In steganography, information is kept hidden behind a cover image. In this
paper, approaches for information hiding using both cryptography &
steganography is proposed keeping in mind two considerations - size of the
encrypted object and degree of security.

Here, signature image information is kept hidden into cover image using
private key of sender & receiver, which extracts the information from stego image
using a public key.

This approach can be used for message authentication, message integrity

& non- repudiation purpose. The LSB procedure normally does not only facilitate
the file size, but depending on the magnitude of the information that is to be
concealed inside the file, the file can become perceptively twisted.

2.2 PROPOSED SYSTEM

Digital signature is also deployed other than image authentication. When

combined with timestamp, a digital signature can be used to demonstrate of its
first authorship.

Size constraint for Text File: To store 1 byte information (8 bits), at least 8
pixels are needed for the cover image. File should be at least 8 times bigger (in
terms of pixels) than the Text File. In the current work, .bmp file with RGB color
format provided by Microsoft is used as cover image. Each pixel is constituted
by the colors red, green & blue that occupies 1 byte space to store each of the
colors.

3
2.3 ADVANTAGES OF PROPOSED WORK

1) Generate Private and Public Key pair through RSA algorithm.

2) Signature image information is being encrypted using Private Key of

Sender

3) At the sender end, encrypted signature header information is embedded

at LSB of blue color. Then the pixel information is embedded at LSB of the red
color of the cover image pixels.

4) At the receiver end, embedded information is retrieved from the stego

image.

5) From this encrypted information, original information is decrypted using

sender’s Public Key.

2.4 LIST OF EVALUATION OF EXISTING WORK

YEAR AUTHOR TITLE KEY POINTS

A Compressed LSB A least significant bit

2017 Nadeem Akhtar Steganography Method (LSB) Steganography
is mainly characterized
by its hiding capacity
and imperceptibility
which is measured by
Peak Signal to Noise
Ratio (PSNR).

4
 A New Hybrid Steganalysis Steganalysis is the
2016 A.Fatnassi Based Approach for mechanism of
Embedding Image in Audio and detecting the presence
Image Cover Media of hidden information
in the stego media

2019 Sabyasachi A New Encrypted Method in Steganography is data

Pramanik Image Steganography hiding technique in
internet

A New LSB-S Image The combinations of

Kamaldeep Joshi Steganography Method Blend Cryptography and
2016 with Cryptography for Secret steganography method
Communication enhance the security
of embedded data.

5
 Sabyasachi Application of The proposed
2013 Pramanik Steganography in Symmetric technique is the
Key Cryptography with application of
Genetic Algorithm steganography for
confidential
transmission of
symmetric
Design of Image steganography deals
Steganography based on RSA with the concealment
2017 Richard Apau Algorithm and LSB Insertion or hiding of a secreted
for Android Smartphones. message from the
unauthorized person.

A Secure Steganography The technological

Creation Algorithm for Advancements in the
2019 Apau Richard Multiple File Formats. information sharing
and the develoment of
many techniques to
make the information
conveyance easy.

6
 CHAPTER 3

METHODOLOGY

3.1 BLOCK DIAGRAM

T
T T

T T T T

T T
T

FIG 3.1 Functional Block Diagram

3.2 DESIGN METHEDOLOGY

3.2.1 Hiding Text Image

3.2.1.1 Algorithm for encoding

(a) Step1: Read the cover image file

(b) Step 2: Perform edge detection of the cover image file chosen.

(c) Step 3: Remold the ASCII character or text message (P) into array form,
then convert it into ASCII format (Q).

(d) Step 4: Remold the text message (P) into array form, then convert itinto
ASCII format (Q).

7
(e) Step 5: Convert the ASCII message into a binary matrix.

(f)Step 6: Generate the key (k) encrypt the matrix using key P= (Q+K) Pi,
where i =2; Perform the embed process with the LSB replacement algorithm.
The result generated is Stego-image (Z)

P T

P T
T T
T T

P T

P T

Fig 3.2.1.1 Encoding process

3.2.1.2 Algorithm for decoding

(a) Step1: The input in the decoding process is the Stego-image (Z). Then, read
the Stego-image and convert it into binary format.

(b) tep 2: n the receiver’s side the image is multiplied with the inverse of the
original matrix. i.e., a(x, y).

(c) Step 3: The decoded audio i.e. b(x, y)is not exactly equal to the original
audio due to the image compression hiding i.e. DCT(Discrete cosine
transformation) technique.

8
(d) Step 4: After decoding the audio file (M) using the reverse process of the
LSB algorithm the next step is to decode the text message (p) from the Stego-
image (z). Now, read the edge area along with the key to obtain the extraction
matrix.

(e)Step 5: Decode the text message with the key to generate decode matrix P=
(P-Q) Pi, where i=2. (f) Step 6: Convert the decode matrix into ASCII form

(g) Step 7: Remold and display the original text message

PT

P TK T T

TT T

Fig 3.2.1.2 Decoding Process

3.2.2 Hiding Text Inside Image

3.2.2.1 Algorithm for encoding

(a) Step 1: To hide an image inside another, the image which will be hidden
needs to have at most the same size of the image which will hide it.

(b) Step 2: We must create two loops to go through all rows and columns from
the images.

(c) Step 3: So, we get the RGB from the image 1 and image 2 as binary values

9
(d) Step 4 : We can use the ”int to bin” method to convert a decimal value to a
binary value.

(e) Step 5: We merge the most significant bits from the image 1 with the most
significant bits from the image 2 sing the ” merge rgb” method

(f) Step 6: Finally, we convert the new binary value to a decimal value using the
”Z bin to int” method and after that set it to a new pixel position from the
resulted image.

(g) Step 7: Now we have an image hidden inside another image.

FIG 3.2.2 STEGO IMAGE WITH HIDDEN MESSAGE

3.2.2.2 Algorithm for decoding

(a) Step 1: To reveal an image, we must know how many bits were used to hide
the image. In this case, we are using a fixed number of 8 bits.

(b) Step 2: First of all, we need to create two loops to go through all pixels from
the image

10
(c) Step 3: So, we extract each RGB channel as a binary value from the current
pixel sing the ” int to in” method

(d) Step 4 : Then, we create a new RGB value by concatenating only the 4
rightmost bits from the current pixel with zero values (to create a new 8-bit
value).

(e) Step 5: . Finally, we convert the binary value to a decimal value and set it to
the current pixel in the new image.

(f) Step6: The developed algorithm as only one more last step to remove the
black borders when the hidden image was smaller than the image which is
hiding it.

(g) Step 7: Now we have the decoded message from the image.

3.3 BRIEF METHODOLOGY

1. Generate Private and Public Key pair through RSA algorithm.

2.Signature image information is being encrypted using Private Key of

Sender.

3.At the sender end, encrypted signature header information is embedded

at LSB of blue colour. Then the pixel information is embedded at LSB of the
red colour of the cover image pixels. Thus the stego image is kept ready.

4.At the receiver end, embedded information is retrieved from the stego
image.

11
3.4 APPROACH FOR HIDING INFORMATION

Signature image data hiding in color image using steganography blended

with cryptography to support message authentication based on digital signature
concepts.

Steganography hides the existence of files. It provides high security for

data transmission. No one can predict that the files even exist. Here, it is
considered that the message is hidden in the LSB of the blue color of each pixel
of cover image.

Some assumptions regarding the proposed work are as follows:

• ize constraint for Text ile: To store 1 byte information (8 bits), at

least 8 pixels are needed for the cover image. File should be at least

times bigger (in terms of pixels) than the Text File.

• n the current work, .bmp file with color format provided by icrosoft

is used as cover image. Each pixel is constituted by the colors red, green & blue
that occupies 1 byte space to store each of the colors.

• Text ile’s ormat is maintained in such a way that the text must be
terminated by a . (dot). It may be any other negotiated character/symbol.

3.5 CONCEPT

3.5.1 Steganography

Steganography is the technique of hiding secret data within an ordinary,

non-secret, file or message in order to avoid detection; the secret data is then
extracted at its destination.

12
 The use of steganography can be combined with encryption as an extra step
for hiding or protecting data.

Steganography can be used to conceal almost any type of digital content,

including text, image, video or audio content; the data to be hidden can be hidden
inside almost any other type of digital content. The content to be concealed
through steganography called hidden text often encrypted before being
incorporated into the innocuous-seeming cover text file or data stream.

If not encrypted, the hidden text is commonly processed in some way in

order to increase the difficulty of detecting the secret content.

3.5.2 Cryptography

Cryptography is the study of secure communications techniques that allow

only the sender and intended recipient of a message to view its contents. The term
is derived from the Greek word kryptos, which means hidden.

When transmitting electronic data, the most common use of cryptography

is to encrypt and decrypt email and other plain-text messages. The simplest
method uses the symmetric or "secret key" system. Here, data is encrypted using
a secret key, and then both the encoded message and secret key are sent to the
recipient for decryption.

3.5.3 Specification of design

Explanation of the techniques/methods used for text, image and audio

hiding inside a cover image, the design follows the procedure, The secret text
message in the proposed program is concealed within the cover image format.

13
 The hidden text in the cover image is concealed in the first phase,
whereas the secret audio file is stored in the cover image file in the second
phase.

Firstly, every text character and each cover picture pixel value is
translated into binary. The Stego-key on the sender side is used as the password
for embedding the hidden message in the cover picture format.

Once the process of embedding the text file into the cover image is
complete, an audio file is selected which is embed in same image file where the
text file is inserted previously.

The audio file in the WAV format is selected and embedded in the image
file. The resulting final or Stego-image is sent to the receiver through the
desired channel of communication. While inserting the binary bit of secret text
message into the conceal picture document.

Each and every values of pixels in the cover image in decimal is

converted into binary values and replaced using the LSB algorithm. Similarly,
each value of the hidden text message is replaced by the cover images of LSB
bit, this procedure is repeated until each text bits in image file are replaced.

Similarly, the DCT (Discrete Cosine Transforms) technique is used to

compress a hidden audio file. The audio samples will vary between -1 and + 1.
When the samples are plotted in a graph, they are retrieving from the audio and
transformed to digitized form and then embed into the shielded image file.

3.5.4 Digital Signature Image

We can describe it as a finite set of digital values, called pixels. Pixels are
the smallest individual element of an image, holding values that represent the
brightness of a given color at a specific point.

14
 Hence, we can think of an image as a matrix (two-dimensional array) of
pixels which contain a fixed number of rows and columns.

Here, it is referenced to the raster graphic, which are basically dot matrix
data structure, representing a grid of pixels, which in turn can be stored in image
files with varying formats.

FIG 3.5.4 DIGITAL SIGNATURE

3.5.5 Pixel Concept

The intensity of each pixel is variable. In color imaging systems, a color

is typically represented with three or four component intensities. Here, the
project will be explained through the working of the RGB color model.

The RGB color model is an additive color model in which Red, Green
and Blue lights are added together in numerous ways to reproduce a broad array
of colors.

So each pixel from the image is composed of three values (Red, Green,
Blue) which are 8- bit values that ranges from 0 – 255.

15
 FIG 3.5.5 : 8-BIT REPRESENTATION

Every pixel has three values (RGB), each RGB value is 8-bit (this infers
that it can store 8 binary values) and the rightmost bits are less substantial.

Therefore, changing the rightmost bits will have a small visual impact on
the final image. This is the steganography key to hide an image inside another
by changing the less significant bits from an image and including the most
significant bits from the other image.

FIG 3.5.5.1 RGB COLOR MODEL

3.5.6 Implementation of User Interface

A step-wise implementation of our Steganographic encryption process to

hide information in the LSB is as follows:

a. The user will start the application and run the code.

b. As soon as the code is run user has to import various libraries, Some
Libraries are installed from external sources as It provides a Command Line

16
Interface (CLI)to find, install, download and remove packages from PyPI and
other Python Package indexes.

After the libraries are installed the application starts up and a user
interface is presented on the users screen as shown :

c. Now the given set of data or information, be it text, audio or image is taken,
converted into ASCII values.

d. The user then imports the cover image and the input file that has chosen.

e. After the selection of the encryption of the information under the cover image
begins.

f. Convert the disintegrated each ASCII in 4 value. Divide 8-bit number into 2-
bit digit, which helps the user at the time of hiding the data.

g. Now the converted form of information is changed into an image format,

mostly png. (lossless compression), which will be hidden under the cover
image, which we are using for Steganography.

h. The converted and hidden image containing different form of information is

then sent to receiver.

i. The receiver then starts the decryption of the sent image file.

j. Message input is extracted from the cover image.

k. The hidden message image is then decrypted and the information is extracted
from the image in its original form.

l. This is how Steganography is done to hide different form of information

under a ‘ over mage’ using encryption and decryption algorithms.

17
 FIG 3.5.6 IMPORTED LIBRARY

FIG 3.5.6 CREATED USER INTERFACE

3.5.7 Requirements of The Information

For experimentation a coloured image of 512 X 512 is considered.

Duration of the audio is less than 4 seconds.

For the experiment of hiding the image inside another image we need to
make sure that the image which is being hidden i.e. our data should be less than
or equal to the cover image.

18
 CHAPTER 4

4.1 COMPONENTS:

The security of the modification of the secret data can be obtained by two
ways: encryption and steganography. A blend of encryption and steganography
can be used to enhance the data security. Here steganography is to hide data,
whereas cryptography is used to encrypt data. Steganography can also be used
with cryptography, thus encrypted data is hidden into cover image, thereby
generating a stego image.

4.1.1 Specifications

The following table is an example format for requirements. Choose

whatever format works best for your project.

SME
Prior Date Reviewed
Req# Requirement Comments
ity Rvwd /
Approved

BR_LR The system should Business Process = 3 7/13/0 Bob

_05 associate a supervisor “ aintenance 4 Dylan,
indicator with each Mick
job class. Jagger

19
 SME
Prior Date Reviewed
Req# Requirement Comments
ity Rvwd /
Approved

BR_LR The system should Business Process = 2 7/13/0 Bob

_08 handle any number of “ hanging ues in 4 Dylan,
fees (existing and the ystem” Mick
new) associated with Jagger
An example of a new
unions.
fee is an initiation fee.

4.1.2 User Interface Requirements

In addition to functions required, describe the characteristics of each

interface between the product and its users (e.g., required screen
formats/organization, report layouts, menu structures, error and other messages,
or function keys).

4.1.3 Usability

Include any specific usability requirements, for example,

Learnability

The user documentation and help should be complete

The help should be context sensitive and explain how to achieve common tasks

The system should be easy to learn

(See http://www.usabilitynet.org/)

20
4.2 SYSTEM REQUIREMENTS

4.2.1 Minimum Hardware Requirements

• System : Pentium IV 2.4 GHz.

• Hard Disk : 40 GB.

• Monitor : 15 inch VGA Color.

• Mouse : Logitech Mouse.

• Ram : 512 MB

• Keyboard : Standard Keyboard

4.2.2 Minimum Software Requirements:

• Operating System : Windows XP.

• Platform : PYTHON TECHNOLOGY

• Tool : Python 3.6

• Front End : Python anaconda script

• Back End : Spyder

21
 CHAPTER 5

SOFTWARE REQUIREMENTS

INTRODUCTION

5.1 DATA MINING

Data mining is an interdisciplinary subfield of computer science. It is the

computational process of discovering patterns in large data sets ("big data")
involving methods at the intersection of artificial intelligence, machine
learning, statistics, and database systems. The overall goal of the data mining
process is to extract information from a data set and transform it into an
understandable structure for further use.

Aside from the raw analysis step, it involves database and data
management aspects, data pre-processing, model and inference considerations-
interestingness metrics, complexity considerations, post-processing of
discovered structures, visualization, and online updating. Data mining is the
analysis step of the "knowledge discovery in databases" process, or KDD.

The actual data mining task is the automatic or semi-automatic analysis of

large quantities of data to extract previously unknown, interesting patterns such
as groups of data records (cluster analysis), unusual records (anomaly detection),
and dependencies (association rule mining).

This usually involves using database techniques such as spatial indices.

These patterns can then be seen as a kind of summary of the input data, and may
be used in further analysis or, for example, in machine learning and predictive
analytics. For example, the data mining step might identify multiple groups in the
data, which can then be used to obtain more accurate prediction results by
a decision support system.

22
 Neither the data collection, data preparation, nor result interpretation and
reporting is part of the data mining step, but do belong to the overall KDD process
as additional steps.

The related terms data dredging, data fishing, and data snooping refer to
the use of data mining methods to sample parts of a larger population data set that
are (or may be) too small for reliable statistical inferences to be made about the
validity of any patterns discovered. These methods can, however, be used in
creating new hypotheses to test against the larger data populations.

Big Data concern large-volume, complex, growing data sets with multiple,
autonomous sources. With the fast development of networking, data storage, and
the data collection capacity, Big Data are now rapidly expanding in all science
and engineering domains, including physical, biological and biomedical sciences.
This paper presents a HACE theorem that characterizes the features of the Big
Data revolution, and proposes a Big Data processing model, from the data mining
perspective.

This data-driven model involves demand-driven aggregation of

information sources, mining and analysis, user interest modelling, and security
and privacy considerations. We analyze the challenging issues in the data-driven
model and also in the Big Data revolution.

5.2 BIG DATA

Big data is a collection of data sets so large and complex that it becomes
difficult to process using on-hand database management tools. The challenges
include capture, curation, storage, search, sharing, analysis, and visualization.
The trend to larger data sets is due to the additional information derivable from
analysis of a single large set of related data, as compared to separate smaller sets
with the same total amount of data, allowing correlations to be found to "spot

23
business trends, determine quality of research, prevent diseases, link legal
citations, combat crime, and determine real-time roadway traffic conditions.

Put another way, big data is the realization of greater business intelligence
by storing, processing, and analyzing data that was previously ignored due to the
limitations of traditional data management technologies

5.2.1The four dimensions of Big Data

• Volume: Large volumes of data

• Velocity: Quickly moving data

• Variety: structured, unstructured, images, etc.

• Veracity: Trust and integrity is a challenge and a must and is important for
big data just as for traditional relational DBs

• Big Data is about better analytics!

5.3 The Big Data platformManifesto

24
5.4 SOME CONCEPTS

• No SQL (Not Only SQL): Databases that “move beyond” relational data
models (i.e., no tables, limited or no use of SQL)

– Focus on retrieval of data and appending new data (not necessarily

tables)

– Focus on key-value data stores that can be used to locate data objects

– Focus on supporting storage of large quantities of unstructured data

– SQL is not used for storage or retrieval of data

– No ACID (atomicity, consistency, isolation, durability)

5.5 HADOOP

• Hadoop is a distributed file system and data processing engine that is

designed to handle extremely high volumes of data in any structure.

• Hadoop has two components:

– The Hadoop distributed file system (HDFS), which supports data in

structured relational form, in unstructured form, and in any form in
between

– The MapReduce programming paradigm for managing applications

on multiple distributed servers

• The focus is on supporting redundancy, distributed architectures, and

parallel processing

25
5.5.1 Some Hadoop Related Names to Know

• Apache Avro: designed for communication between Hadoop nodes

through data serialization

• Cassandra and Hbase: a non-relational database designed for use with

Hadoop

• Hive: a query language similar to SQL (HiveQL) but compatible with

Hadoop

• Mahout: an AI tool designed for machine learning; that is, to assist with
filtering data for analysis and exploration

• Pig Latin: A data-flow language and execution framework for parallel

computation

• ZooKeeper: Keeps all the parts coordinated and working together

5.5.2 What to do with the data

26
The Knowledge Discovery in Databases (KDD) process is commonly defined
with the stages:

(1) Selection
(2) Pre-processing
(3) Transformation
(4) Data Mining
(5) Interpretation/Evaluation.
It exists, however, in many variations on this theme, such as the Cross
Industry Standard Process for Data Mining (CRISP-DM) which defines six
phases:
(1) Business Understanding
(2) Data Understanding
(3) Data Preparation
(4) Modelling
(5) Evaluation
(6) Deployment or a simplified process such as
• pre-processing
• data mining, and
• results validation.

27
 CHAPTER 6

RESULTS AND DISCUSSION

n this approach signature image information is encrypted by sender’s

private key and then embedded into cover object. At the receiver, it is decrypted
by the sender’s public key.

Signature image information is working as digital signature with private

and public key pair of asymmetric key cryptography and provides support for
message authentication, message integrity and non-repudiation.

Along with this, blending of steganography is as usual providing the

support for secrecy in transmission.

1. Together or Separate: In writing these components of your report, you are

faced with one major decision with significant implications:

i) combine the results and the discussion sections,

ii) keep them separate? Both require attention to the organization and
division into topics and subtopics.

i. Combining the results and discussion section allows for more coherence,
because it allows you to discuss results of a particular test or method immediately
after presenting them. However, if you decide to forego the distinction between
results and discussion, you will need to divide your section into appropriate
subsections, potentially into different topics or tests: for example,

ii. Keeping results and discussion separate, on the other hand, allows you to
discuss all of the results at one time. In the above example, it may be more
important to discuss the relationships between composition, strength and
flexibility of individual samples than it is to compare the features of all four

28
samples. In this case, you may want to hold off on discussing the results until you
have presented all of them.

2. Conducting Discussion: There are two key elements to discussion: analysis

and interpretation. The difference between these two elements is subtle, but both
aspects are essential for a complete understanding of the material (See also Types
of Documents / Lab Report for genre specific instruction on results / discussion
and particularly

Both analysis and interpretation involve drawing conclusions from the data
presented in results. In doing either, be sure to clearly link your claims to specific
sets of data, and logically explain how the data supports your claim.

Analysis involves explaining the results and identifying the conclusions

you can draw from them. This can involve highlight key results and placing them
in the context of other results, as in the below example.

29
 CHAPTER 7

CONCLUSION

The addition of security is necessory and also a major challenge as every-

thing is moving towards digital domain. Inclusion of security is a major challenge
and an active area of research over the years.

The project demonstrates the approach for hiding secret data inside a cover
image which later can be extracted by the receiver. Here we discuss, how
steganography can be blended with the concept of digital signature to provide a
better support for improved secrecy and safety of data transmission through the
internet.

The proposed secured communication of text, audio and image

steganography using image steganography approach ensures safety of the text,
audio and image. Here the text, audio and image files are converted into binary
and encoded it into the cover file using bit-wise encoding.

LSB algorithm is preferred over the already existing wavelet transform

method as it provides dual security and is faster than the conventional method.
The work carried out provided us with efficient techniques for secure
transmission of information.

Also, we may enhance our work by providing the support for error
detection and subsequently error correction. The researchers provide a continuing
support that can enhance the capability of better message authentication , privacy,
security and integrity for the communication of e-world.

30
 REFERENCES

[1] adeem khtar, asim hamad and ira Javed, “ ompressed

teganography ethod”, 3rd nternational onference on omputational
Intelligence and Communication Technology (IEEE-CICT 2017), pp. 1-7, 2017.

[2] . atnassi, . harsellaoui and . ouamama, “ ew ybrid teganalysis

ased pproach for mbedding mage in udio and mage over edia”, vol.
49, issue 12, pp. 1809-1814, 2016.

[3] abyasachi Pramanik, . P. ingh and amkrishna hosh, “ ew ncrypted

ethod in mage teganography”, ndonesian Journal of lectrical ngineering
and Computer Science, vol. 14, no. 3, pp. 1412-1419, 2019.

[4] Kamaldeep Joshi and ajkumar adav, “ ew -S Image Steganography

Method Blend with Cryptography for Secret ommunication”, Third
International Conference on Image Information Processing, pp. 86-90, 2015.

[5] Sabyasachi Pramanik and amir K andyopadhyay, “ pplication of

teganography in ymmetric Key ryptography with enetic lgorithm”,
International J of Computers and Technology, vol. 10, issue 7, pp. 1791-1799,
2013.

[6] ichard pau and lement domako, “ esign of mage teganography

based on lgorithm and nsertion for ndroid martphones”,
International Journal of Computer Applications, vol. 164, no. 1, 2017.

[7] Vinothkanna, M. R. (2019). A Secure Steganography Creation Algorithm for

Multiple File Formats. Journal of Innovative Image Processing (JIIP), 1(01), 20-
30.

[8] adhusudhan ishra, angadhar Tiwari and run Kumar adav, “ ecret
ommunication using Public Key teganography”, nternational
Conference on Recent Advances and Innovations in Engineering, 2014.

31
[9] Arati Appaso Pujari and unita unil hinde, “ ata ecurity using
ryptography and teganography”, Journal of omputer ngineering, vol.
18, issue 4, pp. 130-139, 2016.

[10] anjive Tyagi, akesh Kumar wivedi and shendra K. axena, “ igh
Capacity PDF Text Steganography Technique Based on Hashing Using
Quadratic Probing”, nternational Journal of ntelligent ngineering and ystems,
vol. 12, no. 3, pp. 192-202, 2018.

[11] . . . mad, . . . Qahtan, and . . . Jaafar, “ ecuring software

defined network transactions using visual cryptography in steganography,”
Periodicals of Engineering and Natural Sciences (PEN), vol. 8, no. 4, p. 2405,
Dec. 2020. DOI: 10.21533/pen.v8i4.1737. Journal of University of Shanghai for
Science and Technology ISSN: 1007-6735 Volume 23, Issue 6, June - 2021 Page
-719

[12] . atnassi, . harsellaoui, and . ouamama, “ new hybrid steganalysis

based approach for embedding image in audio and image covermedia,” -
PapersOnLine, vol. 49, no. 12, pp. 1809–1814, 2016. DOI:
10.1016/j.ifacol.2016.07.845.

[13]K. Joshi, . ill, and . adav, “ new method of image steganography

using 7th bit of a pixel as indicator by introducing the successive temporary pixel
in the gray scale image,” Journal of omputer etworks and ommunications,
vol. 2018, pp. 1–10, Aug. 2018. DOI: 10.1155/2018/9475142.

[14] . k andyopadhyay and . Pramanik, “ pplication of steganography in

symmet- ric key cryptography with genetic algorithm,” T T
JOURNAL OF COMPUTERS & TECHNOLOGY, vol. 10, no. 7, pp. 1791–
1799, Oct. 2013. DOI: 10.24297/ijct.v10i7.7027.

[15] . pau and . domako, “ esign ofimage steganography based on

algorithm and insertion for android smartphones,” nternational Journal of

32
Computer Applications, vol. 164, no. 1, pp. 13–22, Apr. 2017. DOI:
10.5120/ijca2017913557.

[16] . , “ T P T T
TP T ,” Journal of nnovative mage Processing, vol. 1,
no. 01, pp. 20–30, Oct. 2019. DOI: 10.36548/jiip.2019.1.003.

[17]A. A. AL-Shaaby and T. AlKharobi, “ ryptography and steganography:

New ap- proach,” Transactions on etworks and ommunications, vol. 5, no. 6,
Dec. 2017. DOI: 10.14738/tnc.56.3914.

[18]W. ang, .Tang, and .Wang, “ TPtimestamp steganography detection

method,” T Technical eview, vol. 35, no. sup1, pp. 59–67, Oct. 2018. DOI:
10.1080/ 02564602.2018.1536528.

33