data hiding in a binary image full report

Upload: ankit-sharma

Post on 13-Apr-2018

254 views

Category:

Documents


0 download

TRANSCRIPT

  • 7/27/2019 Data Hiding in a binary image Full Report

    1/38

    1

    Data Hiding in a Binary Image

    Enrol. No: 9910103417

    Name of Student: Ankit Sharma

    Name of Supervisor: Ms. Shraddha Porwal

    December-2013

    Submitted in partial fulfillment of the Degree of

    Bachelors of Technology

    In

    Computer Science Engineering

    DEPARTMENT OF COMPUTER SCIENCE ENGINEERING &

    INFORMATION TECHNOLOGY

    JAYPEE INSTITUTE OF INFORMATION TECHNOLOGY, NOIDA

  • 7/27/2019 Data Hiding in a binary image Full Report

    2/38

    2

    (I)

    TABLE OF CONTENTS

    Chapter No. Topics Page No.

    Student Declaration III

    Certificate from the Supervisor IV

    Acknowledgement VSummary (Not more than 250 words) VI

    List of Figures VII

    List of Tables VIII

    List of Symbols and Acronyms IX

    Chapter-1 Introduction X-X11

    1.1 General Introduction

    1.2 List some relevant current/open problems.

    1.3 Problem Statement

    1.4 Overview of proposed solution approach and Novelty/benefits

    Chapter-2 Background Study XIII-XVIII

    2.1 Literature Survey

    2.1.1 Summary of papers2.1.2 Integrated summary of the literature studied

    2.1.3 Solution to the problem framed

    2.2 Details of Empirical Study

    Chapter 3: Analysis, Design and Modeling XIX-XXVII

    3.1 Requirements Specifications

    3.2 Functional and Non Functional requirements

    3.3 Overall architecture with component description

    3.4 Design Documentation

    3.4.1Use Case diagrams

    3.4.2 Class diagrams / Control Flow Diagrams

    3.4.3 Sequence Diagram/Activity diagrams3.4.4 Data Structures and Algorithms / Protocols

    3.5 Risk Analysis and Mitigation Plan

    Chapter-4 Implementation and Testing XXVIII-XXXIV

    4.1 Implementation details and issues

    4.2 Testing

    4.2.1 Testing Plan

    4.2.2 Component decomposition and type of testing

    4.2.3 List all test cases in prescribed format

    4.2.4 Limitations of the solution

    Chapter-5 Findings & Conclusion XXXV-XXXVI

    5.1 Findings5.2 Conclusion

    5.3 Future Work

    References ACM Format (Listed alphabetically) XXVIII

    Appendices XXVII

    Brief Bio-data (Resume) of Student

  • 7/27/2019 Data Hiding in a binary image Full Report

    3/38

    3

    DECLARATION

    I hereby declare that this submission is my own work and that, to the best of my knowledge

    and belief, it contains no material previously published or written by another person nor

    material which has been accepted for the award of any other degree or diploma of the

    university or other institute of higher learning, except where due acknowledgment has been

    made in the text.

    Place: Delhi Signature:

    Date: 18.11.2013 Name: Ankit Sharma

    Enrollment No: 9910103417

  • 7/27/2019 Data Hiding in a binary image Full Report

    4/38

    4

    CERTIFICATE

    This is to certify that the work titled Data Hiding in a Binary Imagesubmitted by Ankit

    Sharma in partial fulfillment for the award of degree of B. Tech. from Jaypee Institute of

    Information Technology University, Noida has been carried out under my supervision. Thiswork has not been submitted partially or wholly to any other University or Institute for the

    award of this or any other degree or diploma.

    Signature of Supervisor:

    Name of Supervisor: Ms. Shraddha Porwal

    Designation:

    Date: 18/11/2013

  • 7/27/2019 Data Hiding in a binary image Full Report

    5/38

    5

    ACKNOWLEDGEMENT

    My most humble and sincere thanks to:

    My mentor, Ms. Shraddha Porwal for helping me and guiding me throughout the project

    My teachers for guiding me and giving me new ideas on how to make this a successful

    project. My parents for supporting me at every point.

    Signature of the Student:

    Name of Student: Ankit Sharma

    Enrollment Number: 9910103417

    Date:18/11/2013

  • 7/27/2019 Data Hiding in a binary image Full Report

    6/38

    6

    Summary

    Data hiding represents a class of processes used to embed data into various forms of mediasuch as image, audio, or text with a minimum amount of perceivable degradation to the

    host signal. Data hiding, while similar to compression, is distinct from encryption. Its goal

    is not to restrict or regulate access to the host signal, but rather to ensure that embedded data

    remain hidden and recoverable.

    Data hiding has mainly two branches Steganography and Digital Watermarking.

    Digital watermarking is mainly used to show proof of ownership or for multimedia

    authenticity. While steganography is used for covert communication and for confidential data

    storage.

    I am going to deal with steganography. The main aim is to hide the existence of the message.

    It is the art and science of embedding message to datas noise. Only the sender and receiver

    know that the message even exits.

    In my major project I have implemented the data hiding algorithm given by Chang et al,

    Chung et al, Bergman and Davidson.

    During my study I found out that no such code implementation of these algorithms is

    available on internet, so any person thinking of creating something in data hiding field will

    have to first implement these algorithms from scratch. Thats where I come in; I am going to

    make my code freely available on internet. So that people can use it to further create new and

    exciting applications/inventions.

    The algorithms I am going to implement are all using SVD (singular value decomposition)

    for data hiding. SVD increases capacity, perceptibility, robustness, speed and decreases

    detectability. I will also be finding out which among the said algorithms is the best based on

    PSNR value. Peak signal-to-noise ratio, is an engineering term for the ratio between the

    maximum possible power of a signal and the power of corrupting noise that affects the

    fidelity of its representation

    __________________ __________________

    Signature of Student Signature of Supervisor:

    Name: Ankit Sharma Name: Ms. Shraddha Porwal

    Date: 10/12/2013 Date:10/12/2013

  • 7/27/2019 Data Hiding in a binary image Full Report

    7/38

    7

    List of Figures

    Types of Data Hiding Pg. 15

    Architecture with component description Pg. 20

    Use Case Pg. 21

    Control Flow Pg. 22

    Sequence Pg. 23

    Tested Images Pg. 35

  • 7/27/2019 Data Hiding in a binary image Full Report

    8/38

    8

    List of Tables

    Risk Analysis and Mitigation Plan Pg. 27

    Testing Plan Pg.29-31

    Test Schedule Pg.31

    Test Environment Pg.32

    Component Decomposition and type of testing required Pg. 3334

    Project Plan Pg. 37

  • 7/27/2019 Data Hiding in a binary image Full Report

    9/38

    9

    List of Symbols & Acronyms

    AlgorithmAlgo

    Method1Bergmann Method

    Method2- Chung et al

    Method3- Chang et al

  • 7/27/2019 Data Hiding in a binary image Full Report

    10/38

    10

    Introduction

    General Introduction

    Data hiding, a form of steganography, embeds data into digital media for the purpose of

    identification, annotation, and copyright. Several constraints affect this process: the quantity

    of data to be hidden, the need for invariance of these data under conditions where a host

    signal is subject to distortions, e.g., lossy compression, and the degree to which the data must

    be immune to interception, modification , or removal by a third party.

    Data hiding represents a class of processes used to embed data, such as copyright

    information, into various forms of media such as image, audio, or text with a minimum

    amount of perceivable degradation to the host signal; i.e., the embedded data should be

    invisible and inaudible to a human observer. Note that data hiding, while similar to

    compression, is distinct from encryption. Its goal is not to restrict or regulate access to the

    host signal, but rather to ensure that embedded data remain inviolate and recoverable.

    Two important uses of data hiding in digital media are to provide proof of the copyright, and

    assurance of content integrity. Therefore, the data should stay hidden in a host signal, even if

    that signal is subjected to manipulation as degrading as filtering, resampling, cropping, or

    lossy data compression. Other applications of data hiding, such as the inclusion of

    augmentation data, need not be invariant to detection or removal, since these data are there

    for the benefit of both the author and the content consumer. Thus, the techniques used for

    data hiding vary depending on the quantity of data being hidden and the required invariance

    of those data to manipulation. Since no one method is capable of achieving all these goals, a

    class of processes is needed to span the range of possible applications.

  • 7/27/2019 Data Hiding in a binary image Full Report

    11/38

    11

    Relevant Problems

    Steganography for binary images: It is also more challenging to hide secret data in binary

    images because there are only two alternatives to the color of a binary image. The

    modifications done to the image due to the embedding of the secret data can be easily

    observable by the human eye, which gives a strict limit to the hiding capacity of the binary

    image in comparison with the grayscale image.

    The following problems require particular attention:

    Distortion: The distortion introduced must be imperceptibly small for commercial or artistic

    reasons. However, an adversary intending to obliterate may be willing to tolerate certain

    degree of visible artifacts. Therefore, the distortions by embedding and by attack are often

    asymmetric, leading to a wide range of possible point-to-noise ratio.

    Actual noise conditions: An embedding system is generally designed to survive certain

    noise conditions. The embedded data may encounter a variety of legitimate processing

    and malicious attacks, so the actual noise can vary significantly. Targeting conservatively at

    surviving severe noise would lead to the waste of actual payload, while targeting aggressively

    at light noise could result in the corruption of embedded bits. In addition, some bits, such as

    the ownership information and control information, are required to be more robust.

    Uneven distribution of embedding capability: The amount of data that can be embedded

    often vary widely from region to region in image and video. This uneven embedding

    capacity causes serious difficulty to high-rate embedding.

    Problem Statement

    The aim of this project is to implement different algorithms using SVD for hiding data in

    binary images and then finding out which among them is the best approach using a set of

    parameters such as mean, variance, covariance and PSNR value.

  • 7/27/2019 Data Hiding in a binary image Full Report

    12/38

    12

    Overview of proposed solution approach

    I am going to implement the following data hiding algorithms and then will try to find out the

    best among them based on set of parameters.

    Method 1 is based on the one proposed by Bergman and Davidson

    Method 2 is based on the one proposed by Chang et al

    Method 3 is the method proposed by Chung et al

  • 7/27/2019 Data Hiding in a binary image Full Report

    13/38

    13

    Background Study

    Literature Survey

    Summary of Research Paper

    Title of Paper: - Techniques for Data Hiding

    Authors: - W. Bender, D.Gruhl, N.Morimoto and A.Lu

    Year of Publication:- 1996

    Publishing Detail:- It was published in IBM Systems Journal

    Summary:-Several techniques are discussed as possible methods for embedding data in

    host text, image, and audio signals. All of the proposed methods have limitations.

    The goal of achieving protection of large amounts of embedded data against intentional

    attempts at removal may be unobtainable. Automatic detection of geometric and no

    geometric modifications applied to the host signal after data hiding is a key data-hiding

    technology. The optimum tradeoff between bit rate, robustness, and perceiveability

    need to be defined experimentally. The interaction between various data-hiding technologies

    needs to be better understood. While compression of image and audio content continues

    to reduce the necessary bandwidth associated with image and audio content, the need for a

    better contextual description of that content is increasing. Despite its current shortcomings,

    data-hiding technology is important as a carrier of these descriptions.

    Web Link:-www.cs.utsa.edu/~jortiz/.../Techniques%20for%20Data%20Hiding-p.pdf

    Title of Paper: - Steganography Technique based on SVD

    Authors: - Yambem Jina Chanu, Kh. Manglem Singh and Themrichon Tuithung

    Year of Publication:- 2007

    Publishing Detail:- It was published in International Journal of Research in Engineering

    and Technology (IJRET)

    Summary:-The paper proposes an image steganography technique that embeds the secret

    message in the left singular vectors, singular values and right singular vectors of the vectors

    of blocks of the image in such a way that the visual quality of the image is not affected due toembedding of the message. The technique was compared with other two existing methods on

    http://www.cs.utsa.edu/~jortiz/.../Techniques%20for%20Data%20Hiding-p.pdfhttp://www.cs.utsa.edu/~jortiz/.../Techniques%20for%20Data%20Hiding-p.pdfhttp://www.cs.utsa.edu/~jortiz/.../Techniques%20for%20Data%20Hiding-p.pdfhttp://www.cs.utsa.edu/~jortiz/.../Techniques%20for%20Data%20Hiding-p.pdf
  • 7/27/2019 Data Hiding in a binary image Full Report

    14/38

    14

    different color images, and was found that the proposed method is comparatively better than

    the other methods under consideration. The future plan is to test the proposed method under

    different steganalytic attacks.

    Web Link:-http://psrcentre.org/images/extraimages/IJRET016061.pdf

    Title of Paper: - Singular Value Decomposition and Principal Component Analysis

    Authors: - Rasmus Elsborg Madsen, Lars Kai Hansen and Ole Winther

    Year of Publication:- 2004

    Publishing Detail:- It was published in Neural Networks for Pattern Recognition Journal

    Summary:- In principal component analysis wend the directions in the data with the most

    variation, i.e. the eigenvectors corresponding to the largest eigenvalues of the covariance

    matrix, and project the data onto these directions. The motivation for doing this is that the

    most second order information are in these directions.1 The choice of the number of

    directions are often guided by trial and error, but principled methods also exist.

    Web Link:-www.imm.dtu.dkpubdbviewsedocdownload.php...imm.pdf

    http://psrcentre.org/images/extraimages/IJRET016061.pdfhttp://psrcentre.org/images/extraimages/IJRET016061.pdfhttp://psrcentre.org/images/extraimages/IJRET016061.pdfhttp://psrcentre.org/images/extraimages/IJRET016061.pdf
  • 7/27/2019 Data Hiding in a binary image Full Report

    15/38

    15

    Integrated Summary

    Applications OF Data Hiding

    Placing data in images is useful in a variety of applications. We highlight below four

    applications that differ in the quantity of data to be embedded and the type of transforms to

    which the data are likely to be subjected.

    First techniques included invisible ink, secret writing using chemicals, templates laid over

    text messages, microdots, changing letter/word/line/paragraph spacing, changing fonts

    Images, video, and audio files provide sufficient redundancy for effective data hiding

    Postscript files, PDF files, and HTML can also be used for non-robust data hiding to a limited

    extent Executable files, provide very little space for data hiding Fonts

    Need Of Data Hiding

    Covert communication using images (secret message is hidden in a carrier image)

    Ownership of digital images, authentication, copyright, Data integrity, fraud detection, self-

    correcting images Traitor-tracing (fingerprinting video-tapes) Adding captions to images,additional information, such as subtitles, to video, embedding subtitles or audio tracks to

    video (video-in-video) Intelligent browsers, automatic copyright information, viewing a

    movie in a given rated version Copy control (secondary protection for DVD)

  • 7/27/2019 Data Hiding in a binary image Full Report

    16/38

    16

    Properties Of Data Hiding

    Robustness

    The ability to extract hidden information after common image processing operations: linear

    and nonlinear filters, lossy compression, contrast adjustment, recoloring, resampling, scaling,

    rotation, noise adding, cropping, printing / copying / scanning, D/A and A/D conversion,

    pixel permutation in small neighborhood, color quantization (as in palette images), skipping

    rows / columns, adding rows / columns, frame swapping, frame averaging (temporal

    averaging), etc.

    Un-Detectability

    Impossibility to prove the presence of a hidden message. This concept is inherently tied to thestatistical model of the carrier image. The ability to detect the presence does not

    automatically imply the ability to read the hidden message. Undetectability should not be

    mistaken for invisibility a concept related to human perception.

    Invisibility

    Perceptual transparency. This concept is based on the properties of the human visual system

    or the human audio system.

    Security

    The embedded information cannot be removed beyond reliable detection by targeted attacks

    based on a full knowledge of the embedding algorithm and the detector(except a secret key),

    and the knowledge of at least one carrier with hidden message.

    Steganography v/s Digital Watermarking

    In digital watermarking, the focus is on ensuring that nobody can remove or alter the content

    of the watermarked data, even though it might be plainly obvious that it exists.

    Steganography on the other hand, focuses on making it extremely difficult to tell that a secret

    message exists at all. If an unauthorized third party is able to say with high confidence that a

    file contains a secret message, then steganography has failed.

  • 7/27/2019 Data Hiding in a binary image Full Report

    17/38

    17

    Steganography v/s Cryptography

    Cryptography does not attempt to hide the fact that a message exists. Instead, it merely

    obscures the integrity of the information so that it does not make sense to anyone but thecreator and the recipient. The adversary will be able to see that a message exists, and the

    inverse process of cryptanalysis involves trying to turn the meaningless information into its

    original form.

    The "secrecy" of the embedded data is essential in this area. Historically, steganography have

    been approached in this area. Steganography provides us with:

    (A) Potential capability to hide the existence of confidential data

    (B) Hardness of detecting the hidden (i.e., embedded) data

    (C) Strengthening of the secrecy of the encrypted data

    Details of empirical study (Field survey, Experimental studies)

    Data hiding represents a class of processes used to embed data, such as copyright

    information, into various forms of media such as image, audio, or text with a minimum

    amount of perceivable degradation to the host signal; i.e., the embedded data should be

    invisible and inaudible to a human observer.

    Data hiding, while similar to compression, is distinct from encryption. Its goal is not to

    restrict or regulate access to the host signal, but rather to ensure that embedded data remain

    inviolate and recoverable.

    Two important uses of data hiding in digital media are to provide proof of the copyright, and

    assurance of content integrity. Therefore, the data should stay hidden in a host signal, even if

    that signal is subjected to manipulation as degrading as filtering, resampling, cropping, or

    lossy data compression. Other applications of data hiding, such as the inclusion of

    augmentation data, need not be invariant to detection or removal, since these data are therefor the benefit of both the author and the content consumer. Thus, the techniques used for

  • 7/27/2019 Data Hiding in a binary image Full Report

    18/38

    18

    data hiding vary depending on the quantity of data being hidden and the required invariance

    of those data to manipulation. Since no one method is capable of achieving all these goals, a

    class of processes is needed to span the range of possible applications.

    The technical challenges of data hiding are formidable. Any holes to fill with data in a host

    signal, either statistical or perceptual, are likely targets for removal by lossy signal

    compression. The key to successful data hiding is the finding of holes that are not suitable for

    exploitation by compression algorithms. A further challenge is to fill these holes with data in

    a way that remains invariant to a large class of host signal transformations.

    Feature tagging. Another application of data hiding is tagging the location of features within

    an image. Using data hiding it is possible for an editor (or machine) to encode descriptive

    information, such as the location and identification of features of interest, directly into

    specific regions of an image. This enables retrieval of the descriptive information wherever

    the image goes. Since the embedded information is spatially located in the image, it is not

    removed unless the feature of interest is removed. It also translates, scales, and rotates exactly

    as the feature of interest does.

    Each application of data hiding requires a different level of resistance to modification and a

    different embedded data rate. These form the theoretical data-hiding problem space. There is

    an inherent trade-off between bandwidth and robustness, or the degree to which the data

    are immune to attack or transformations that occur to the host signal through normal usage,

    e.g., compression, resampling, etc. The more data to be hidden, e.g., a caption for a

    photograph, the less secure the encoding. The less data to be hidden, e.g., a watermark, the

    more secure the encoding.

  • 7/27/2019 Data Hiding in a binary image Full Report

    19/38

    19

    Analysis, Design and Modeling

    Requirement Specifications

    Computer (Desktop, Laptop)

    Windows/Linux/Mac OS

    Microsoft Visual C++

    Compiler

    Functional requirements

    For the project to work we need Matlab to be installed in the system other than that a working

    pc/laptop with windows/mac/linux installed.

    The user will need to select an image to work on. Then the system will pop out histogram of

    original image and steganography image along with window of original image and

    steganography image.

    Then go check out the original image and steganography images mean, PSNR value,

    correlation we will have to go the output tab. There we will get all our details.

    Input: A binary image

    Output: A steganography image (image with data hidden)

    Non Functional requirements

    Performance Requirements

    Performance requirements define acceptable response times for system functionality.

    The load time should not be longer.

    The data hiding should be done in a matter of seconds.

    Safety Requirements

    It is completely safe to use but keep it in mind that the data is not fully secure others too can

    extract it. So be careful

    Security Requirements

    As the data can be retrieved by other people too as the techniques are not 100% secure so

    while dealing with sensitive data you have to be more careful

    Efficient: The product is completely efficient.

  • 7/27/2019 Data Hiding in a binary image Full Report

    20/38

    20

    Overall architecture with component description and dependency

    details

  • 7/27/2019 Data Hiding in a binary image Full Report

    21/38

    21

    Design Documentation

    Use Case Diagram

  • 7/27/2019 Data Hiding in a binary image Full Report

    22/38

    22

    Class Diagram/ Control Flow Diagram

  • 7/27/2019 Data Hiding in a binary image Full Report

    23/38

    23

    Sequence Diagram/ Activity Diagram

  • 7/27/2019 Data Hiding in a binary image Full Report

    24/38

    24

    Algorithms

    Method 1: Algorithm by Bergman and Davidson

    Embedding Algorithm

    1. Compute the normal singular value decomposition, , of each block of A.

    2.Transform into :

    (a) Set certain components =.||, where=message [1 -1]

    (b) Choose remaining components to ensure that is still

    orthogonal.

    3.Compute=.

    4. Round the entries in .

    Resulting matrix, will be a block of the stego-image.

    Extraction Algorithm

    denotes the stego image and is applied to retrieve the hidden message.

    1. Compute the U~S~VT~of .

    2. Extract payload bits from the signs of the entries in the triangular portion of

    ~:=~/|~|

  • 7/27/2019 Data Hiding in a binary image Full Report

    25/38

    25

    Method 2: Algorithm by Chang et al

    Embedding Algorithm

    Input: Block , where =,1,,3,,161

    =binary secret message

    Output:A stego image

    Perform SVD on the block , generating the corresponding , Sand matrices.

    If W(, j)==1

    4= 23,if 3>(23)

    0, otherwise.

    and 2=2+, where is threshold.

    Perform inverse SVD.

    Repeat these steps until all secret message have been embedded.

    Combine all stego blocks.

    Extracting Algorithm

    Input: Stego block , where =,1,,3,,161

    Output: The extracted hidden message

    Perform SVD on each blocks of image

    10 0 0

    3. Let SWK= 0 20 0

    0 0 30

    0 0 0 4

    The extracted hidden message is given by

    EW(,)= 1,if 23>/2.

    0, Otherwise.

    Repeat the above steps until all hidden message bits are extracted.

    Combine all stego blocks to form the stego image .

  • 7/27/2019 Data Hiding in a binary image Full Report

    26/38

    26

    Method 3: Algorithm by Chung et al

    Embedding Algorithm

    Input: Block , where =,1,,3,,161, binary secret message

    Output: A stego image

    Perform SVD on the block of 44 size

    If W(,j) = = 1

    Modify 2,1and 3,1are modified to satisfy the condition|2,1| |3,1| .

    Otherwise the condition

    |3,1||2,1| >

    must be held.

    Perform inverse SVD.

    Repeat the above steps until all binary pixels of the secret message have been

    embedded. Combine all stego blocks to form the stego.

    Extracting Algorithm

    Input: Stego block , where =,1,,3,,161

    Output: The extracted hidden message

    Perform SVD on the block generating the corresponding , and

    matrices.

    The extracted hidden message is given by

    1, if |2,1| |3,1|

    EW(,)= 0, otherwise

    Repeat the above steps until all hidden message bits are extracted

  • 7/27/2019 Data Hiding in a binary image Full Report

    27/38

    27

    Risk Analysis and Mitigation Plan

    Risk

    Id

    Risk

    Description

    Risk

    AreaProb Impact RE

    (P*I)

    Risk

    forM Plan

    M Plan C

    Plan

    1

    Matlab needsspecificHardwareRequirementspeople having oldcomputers mightnot be able to run italso it is a paidsoftware

    Hardware Low High Medium No __ __

    2Sometimes thecode might notfunction properlydue to the image

    type

    Software Medium High High Yes

    Specificallyinformingthe userthat onlyimages of

    certaindimensionthat toobinaryimages willwork

    __

    3

    Not all users mightbe able to work itout properly

    Software Low Medium Low Yes

    A proper

    SRS willbe providedso that

    users canlearn how

    to properlyoperate thesoftware

    If the user

    still needshelp evenafter

    readingSRS then

    online helpcan beprovidedwhere anybody could

    askquestions

    andanybodycould

    answerthem

  • 7/27/2019 Data Hiding in a binary image Full Report

    28/38

    28

    Implementation and Testing

    Implementation details and issues

    I have been able to complete the method 2 and method 3 by Chung et al and Chang et al

    respectively. The above two algorithms use SVD to hide data in the image.

    SVD includes :

    Matrix A of size m n

    factoring the matrix (A) into three part USVT

    where

    Orthogonal matrices:

    U : Left singular vector

    V : Right singular vector

    S: is a diagonal matrix

    While implementing the algorithms there were some issues coming with calculating PSNR

    value. I tried to calculate it by using different methods and was finally able to get it right.I am implementing the algorithms to work on binary images but for experimental purposes I

    tried these algorithms on colored images and there came out matrix mismatch then I tried

    converting the colored images in greyscale then in black & white then the results were

    favorable. So my project can handle both colored as well as binary images, only we have to

    convert the colored image at run time. Finally I was able to implement 2/3 algorithms due to

    shortage of time. The results of the algorithm came out to be favorable and I was able to

    come to a conclusion.

  • 7/27/2019 Data Hiding in a binary image Full Report

    29/38

    29

    Testing

    Testing Plan

    Type of TestWill Test Be

    Comments/Explanations Software ComponentPerformed?

    Requirements Testing Yes

    Without proper requirementfulfillments the project will not beable to run. Majority of errors are

    associated with not being able tocomplete the requirements.

    Testing will beperformed onwhether the systemis having the properoperating system

    with matlab installedor not

    Unit Yes

    Unit testing needs to be done aseven if a small module isnt workingthe way it is supposed to then thewhole product is doomed

    There are 3algorithms being

    used each will betested to see whetherthe output is comingout to be what weaccepted or not

    Integration No

    There is no need to do integrationtesting as the modules are separatethere is no integration between them ______

    Performance Yes

    To check whether my product ismeeting the performancerequirement as performance is themajor core of any product it can

    Whether the

    algorithms are

    providing result

    within a stipulatedtime

  • 7/27/2019 Data Hiding in a binary image Full Report

    30/38

    30

    build and destroy products

    Stress Yes

    Stress testing is an important

    criteria which helps us in

    knowing what all can our

    product handle

    All the algorithmswill be tested withdifferent types ofimages to see whatall can our producthandle

    Compliance No

    Because it is related with whetherIT standard are followed or notwhich is not applicable here

    _______

    ____

    _______

    Security Yes

    To check whether our data is

    secure or not

    We will try to

    decrypt the

    message using

    other algorithms

    Load NoBecause we are using a single

    image at a time so there is noneed to do load test _______

    Volume NoWe are only dealing with one

    image at a time. So need for

    volume test. ____

    ____

  • 7/27/2019 Data Hiding in a binary image Full Report

    31/38

    31

    Test Schedule

    Activity Start Date Completion

    Date

    Hours Comments

    Requirement

    Testing

    06/12/2013 06/12/2013 1 System tested

    for availability

    of matlab

    Unit Testing 07/12/2013 07/12/2013 4 The output

    coming is

    favorable

    Performance

    Testing

    08/12/2013 08/12/2013 3 Time to get the

    embedded image

    is very low

    hence very good

    Stress Test 09/12/2013 09/12/2013 5 The results were

    favorable

    Security Test 10/12/2013 10/12/2013 7 The system if

    almost secure

  • 7/27/2019 Data Hiding in a binary image Full Report

    32/38

    32

    Test EnvironmentSoftware Items

    OS:

    Min Requirement:Windows XP x64 Edition Service Pack 2

    Disk Space:

    1 GB for MATLAB only,34 GB for a typical installation

    Hardware Items

    Ram:1024 MB(At least 2048 MB recommended)

    Processor :Any Intel or AMD x86 processor supporting SSE2 instruction set

    -PROVIDE A DESCRIPTION OF THE TEST PLATFORMS

  • 7/27/2019 Data Hiding in a binary image Full Report

    33/38

    33

    Component decomposition and types of testing required

    S.No. Components Type of Testing Reqd. Technique for Writing Test cases

    1 Matlab(algorithms) Requirement White Box Testing

    2 Matlab

    (algorithms)

    Unit White Box Testing

    3 Matlab

    (algorithms)

    Performance Black Box Testing

    4 Matlab

    (algorithms)

    Stress Black Box Testing

    RequirementWhite Box Testing

    Id 1:

    Checking to see whether the system is meeting the minimum requirement

    UnitWhite Box Testing

    Id 2:

    All the 2/3 algorithms will be checked to see that there is no discrepancy coming out in any

    result.

    Performance

    Id 3: Various set of images are used to check whether the steganography images are coming

    out in justifiable time or not.

    Stress

    Id 4: Images of different type like binary and coloured images are used to check whether the

    system can handle them or not

    Security

    Id 5: Other algorithms are used to try to retrieve the message embedded by some other

    algorithm to find out whether the system is secure or not

  • 7/27/2019 Data Hiding in a binary image Full Report

    34/38

    34

    Test Case ID Input Expected Output Pass/Fail1 Code Some outcome Pass

    2 Binary Image Steganography Image Pass

    3 Binary Image Fast Result Pass (Within a minute)

    4 Colored & Binary Image Steganography Image Pass

    5 Steganography Image Failure to decrypt message Pass

    Limitation of the Solution

    We can only use images of dimension 256*256

    The system is not totally secure as after finding out which algorithm has

    been used the embedded information can be retrieved easily

    There is no graphical user interface

    The image to be worked upon needs to be hard coded

    The project will not be able to work on coloured images without

    converting them to greyscale then to black & white.

    You can only embed data in binary form

  • 7/27/2019 Data Hiding in a binary image Full Report

    35/38

    35

    Finding and Conclusion

    Findings

    I tested my algorithm on these images

    The method 2 is showing higher PSNR value then method1. The mean, variance and

    correlation value are coming to be almost close

  • 7/27/2019 Data Hiding in a binary image Full Report

    36/38

    36

    Conclusion

    I have tried to implement image steganography technique that embeds the secret message in

    the left singular vectors, singular values and right singular vectors of the vectors of blocks of

    the image in such a way that the visual quality of the image is not affected due to embedding

    of the message. The technique was compared between method proposed by Chang et al and

    Chung et al on different color as well as binary images, and was found that the method 2 is

    comparatively better than the other method under consideration.

    Future Work

    The future plan is to come up with a much better technique for data hiding and also to test the

    different methods under different steganalytic attacks

  • 7/27/2019 Data Hiding in a binary image Full Report

    37/38

    37

    Appendix

    Project Plan

    Phase Description of Work Start and End Dates

    Phase One Project Proposal Week 1

    Phase Two Setting up environment Week 1

    Phase Three Understanding the Various Methods Week 28

    Phase Four Implementation of the various methods Week 9-10

    Phase Five Differentiating between different methods Week 10-12

    Phase Six Coming up with a conclusion Week 12-13

  • 7/27/2019 Data Hiding in a binary image Full Report

    38/38

    References

    [1] F. Petticolas, Information hiding techniques for steganography and digital watermarking, Stefen

    Katzenbeisser, Artech house books, ISBN 158053-035-4, Dec. 1999.

    [2]C. Bergman and J. Davidson, Unitary embedding for data hiding with the SVD, Security, Steganography, and

    Watermarking of

    Multimedia Contents VII, SPIE, vol. 5681, San Jose, Jan., 2005.

    [3] M. Y. Wu and J. H. Lee. A Novel Data Embedding Method for Two-Color Facsimile Images. In

    Proceedings of International Symposium on Multimedia Information Processing, Chung-Li, Taiwan, R.O.C,

    December 1998

    [4] F. Petitcolas, R. Anderson and M. Kuhn Information Hiding, A Survey Proceedings of the IEEE, special

    issue on protection of multimedia content, July 1999.

    [5] W. Bender, D. Gruhl, N. Morimoto, and A. Lu, Techniques for data hiding,IBM Systems Journal, Vol. 35,No. 3 and 4, pp. 313-336, 1996.

    [6] C-C. Chang, C-C. Lin and Y-S. Hu, An SVD oriented watermark embedding scheme with high qualities for

    the restored images, IJICIC, vol. 3, no. 3, pp. 609-620, June 2007

    [7] M.M. Hadhoud and A.A. Shallan, An efficient SVD image steganographic approach, IEEE ICCES, pp. 257-

    262, 14-16, December 2009.