Enhancement of RoI in Brain Tumor Images Using

Integer Wavelet Transform and Discrete Cosine Transform

Project report submitted in partial fulfillment of the Requirements for the Award of the
Degree of
BACHELOR OF TECHNOLOGY
In
COMPUTER SCIENCE AND ENGINEERING
By
Ch.Dedeepya 198W1A05D7
G.Akhila 198W1A05E4
P.Jahnavi 198W1A05H3
G.Sanjana 198W1A05H8

Under the Guidance of

Dr.Ch.Rupa

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

V.R SIDDHARTHA ENGINEERING COLLEGE
Autonomous and Approved by AICTE- Twice Accredited by NBA
Affiliated to Jawaharlal Nehru Technological University, Kakinada
Vijayawada-520 007
2022
 V.R.SIDDHARTHA ENGINEERING COLLEGE
(AUTONOMOUS)
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE
This is to certify that the project report entitled Enhancement of RoI in Brain Tumor Images
using Integer Wavelet Transform and Discrete Cosine Transform being submitted by

Ch.Dedeepya 198W1A05D7

G.Akhila 198W1A05E4

P.Jahnavi 198W1A05H3

G.Sanjana 198W1A05H8

in partial fulfillment for the award of the Degree of Bachelor of Technology in Computer

Science and Engineering to the Jawaharlal Nehru Technological University, Kakinada is a record

of bonafide work carried out under my guidance and supervision.

Dr.Ch.Rupa Dr. D. RAJESWARA RAO

M.Tech, Ph.D
Professor Head of the Department

ii
 DECLARATION

I hereby declare that the dissertation entitled “Enhancement of RoI in Brain Tumor Images

using Integer Wavelet Transform and Discrete Cosine Transform” submitted for the B.Tech

Degree is my original work and the dissertation has not formed the basis for the award of any

degree, associateship, fellowship or any other similar titles.

Place: Vijayawada Ch.Dedeepya (198W1A05D7)

Date: G.Akhila (198W1A05E4)

P.Jahnavi (198W1A05H3)

G.Sanjana (198W1A05H8)

iii
 ACKNOWLEDGEMENT

Behind every achievement lies an unfathomable sea of gratitude to those who activated it,
without whom it would ever have come into existence. To them we lay the words of gratitude
imprinted with us.

We would like to thank our respected Principal Dr. A.V. Ratna Prasad and Dr. D. Rajeswara
Rao, Head of the Department, of Computer Science and Engineering for their support throughout
our Project.

It is our sincere obligation to thank our guide, Dr.Ch.Rupa, Professor, Department of Computer
Science and Engineering, for her timely valuable guidance and suggestions for this Project. We
owe our acknowledgments to an equally long list of people who helped us with this Project.
Finally, we wish to thank all the supporting staff who gave us facility in the lab for the
completion of this Project.

Place: Vijayawada

Date:

Ch.Dedeepya(198W1A05D7)
G.Akhila (198W1A05E4)

P.Jahnavi (198W1A05H3)

G.Sanjana (198W1A05H8)

iv
 ABSTRACT

The growth of the Internet has created numerous new opportunities for the creation and
dissemination of digital information. The process of Digital Watermarking embeds the special
fact that it protects the information from unauthorized access. Telemedicine is the process of
transferring medical images through the internet. Medical images can be modified intentionally
or accidentally as the transmission of these may take place through an unsecured network such as
the internet. In order to avoid the wrong diagnosis, the integrity of RoI must be verified in the
received medical image before making any diagnostic decisions. Here the proposed system is a
medical image watermarking technique that embeds the Region of Interest(RoI) into the
respective Region of Non-Interest(RoNI). For enhancing the protection of medical images it is
proposed with Integer Wavelet Transform(IWT) as it has the best coding performance and
Discrete Cosine Transform (DCT) that provides low computational time for embedding,
encryption, decryption as well as extraction of RoI and it ensures the visual quality of an image.
For embedding, it is proposed IWT and for extraction apply DCT on frequency bands. The
proposed methodology protects the medical images against Tampering. It detects the tampered
regions in an image and recovers the original image against malicious modification. As a result,
the digital watermarking technique maintains the security and integrity of an image.

 
Keywords — Watermarking, Integer Wavelet Transform, Discrete Cosine Transform,
Embedding, Extraction, Tampering

v
TABLE OF CONTENTS

vi
1. Introduction

A common practice in telemedicine is the distribution of medical images among distant

locations. To provide clinical healthcare in far-off regions, telemedicine uses information
technologies and telecommunication. It provides access to medical services that are not
accessible in remote areas. Through the use of telemedicine, patients in remote areas can access
treatment from far away specialists, reducing the need to travel to a hospital for a consultation.
Telemedicine enables reliable data transmission, easy patient-medical staff communication, and
the transfer of medical and imaging data from one location to another. Medical images assist
doctors in determining the best diagnostic techniques to use while treating patients. During
transmission, unauthorized individuals could attack or purposefully alter medical images. A
region of interest (RoI) of an image might be altered or manipulated, hence a medical specialist
must verify the integrity of medical images. This checking helps in avoiding wrong diagnosis. In
this situation, watermarking is discovered to be a successful and promising approach.
The watermarking technique can be either visible, like logos, or invisible. Invisible
watermarking involves hiding or embedding the watermark in the cover media so that it is
invisible to the human eye. Any watermarking technique has two fundamental steps: the
embedding and extraction procedures. Robustness, imperceptibility, security, and integrity are
the fundamental requirements for watermarking. A robust approach to watermarking is one that
is highly resistant to attacks. The watermark is imperceptible if it does not distort or affect the
value of the media. The watermarked media must resemble the original media. Medical images
contain one or more important areas. The important areas are called Regions of Interest (RoI)
and the remaining part is called Non-region of interest (RoNI). Before making any diagnostic
decisions the medical practitioner should identify the integrity of the RoI.
ROI functionality is important in medical applications where certain parts of the image are more
important for diagnosis than others. The diagnostically significant information in most medical
images is concentrated in relatively small regions, about 5 to 10% of the total area. These regions
must be encoded at a higher quality than the background in such cases. These regions must be
transmitted first or at a higher priority during image transmission for telemedicine purposes.
The frequency domain watermarking approach for medical images is presented in this
study with the contribution of combining the IWT and DCT transformations. Because DWT
transform is compatible with the Human Visual System, discrete wavelet transform (DWT)

vii
watermarking techniques offer great imperceptibility (HVS). The implication is that the human
eye is less sensitive to changes in the image(the inserted watermark). The advantages of IWT
watermarking can better take advantage of the DWT characteristics. IWT only works with
integers, which makes it much faster. Using IWT the image can be reconstructed without any
loss. Frequency Domain watermarking methods are more robust than spatial domain
watermarking methods. Against compression and image processing, DCT watermarking
techniques are highly robust.

It is also a fast transformation. Therefore, the usage of IWT and DCT for watermarking medical
images is feasible. To achieve appropriate imperceptibility and robustness results, this
combination is used.

1.1 Problem Statement

 Segmentation of RoI in MRI images(Brain), and recovering the original content if tampering
occurs.

1.2 Scope

 The project is based on the digital watermarking technique for authentication of DICOM
images(MRI) using Integer Wavelet Transform and Discrete Cosine Transform. The
proposed method in this case uses transform domain watermarking. 

1.3 Objective

 To analyze existing methods of watermarking and pin down the loopholes with the current
mechanisms.

 To design and develop a secure watermarking system for the privacy preservation of
medical images using IWT and DCT.

 To develop a system that recovers the original content of medical images if tampered.

 To test the simulation time and Peak signal to noise ratio(PSNR) that ensures the quality of
an image

viii
Fifth Page

The sixth page may include the Acknowledgement

Sixth Page

The seventh page should contain an abstract of the Project. The candidate may emphasize here
his contributions.

Seventh and Eight Page

In this page, a table of contents, list of tables, list of figures, and photographs and notation must
be provided.

Important Note:

 All the above pages are to be numbered in Roman numerals of lower case. Ex.
i,ii,iii,iv,…

 The document pages must be numbered using numbers i.e. 1,2,3……

Arrangement of Chapters depending upon the project

The following is suggested format for arranging the project report matter into various chapters:
1. Introduction

ix
 This chapter must describe the introduction, Problem statement, scope and
objective of your project.
2. Literature Survey/Existing System
3. Software Requirement Analysis
 Functional requirements definitions
 Nonfunctional requirements definitions
4. Software Design
The design part must include the following items
 DFDs in case of Database projects
 UML diagrams. This UML diagrams must include the following
Class Diagrams
Interaction diagrams-Sequence and Collaboration diagrams
Object Diagrams
Usecase diagrams
 Control Flow diagrams
 Database Design
For database projects, the report must include the following items.
E-R Diagrams
5. Proposed System
 Define the modules and their functionalities
6. Coding
Consist of coding or code outline for various files
Explain each class with functionality and methods with input and output
parameters.
For Database projects, the report consisting of
o Tables – explaining all fields and their data types
o Stored procedures (PL/SQL)
7. Testing
Various test cases (two or three) for black box and white box testing
8. Output Screens / Results
Should include all user interfaces and output screens.
9. Conclusion and Further Work
11. References
12. Appendices (if any).

Arrangement of Paragraph in a Chapter:

 Each paragraph in a chapter should be properly numbered for example, 2.1, 2.2 etc.,
where first digit represents the Chapter Number and second digit the paragrahph number.
There is no need to indicate the number for the first paragraph in a chapter.
 Sub-paragraphs, if any indicated as 1.1.1, 1.1.2 etc. i.e. first digit representing the
chapter, the second representing the paragraph and third representing the sub-paragraph.
 Don’t underline the headings or subheadings or side heading. Instead use the bold
letters.

x
Photographs/Figures and Tables

 The figures, photographs and tables occuring in a chapter may be serially numbered as
Fig. 1.1, 1.2 etc., where the first digit represents the chapter, the second digit represents
Figure number.
 The photographs may be represented as Photo 1.1, 1.2 etc., the first digit representing
chapter and the second digit represents Photograph number.
 The tables may be represented as Table 1.1, 1.2 etc., the first digit representing chapter
and the second digit represents table number.
Graphs

The graph should clearyly indicate the points, which are used for drawing the curve or curves.
All the letters in the graphs should be written with stencils.

References:
 The following format used for writing the References.
Author Name, “Title of the book or paper”, Publisher name, Volume, year.

Example: Berry, Jason, Jonathan Foose, and Tad Jones. “Up from the Cradle of Jazz: New
Orleans Music Since World War II”, Athens: U of Georgia P, 1986.

(An article in a journal) Booth, Wayne C. "Kenneth Burke's Way of Knowing." Critical Inquiry, 1-22,
1974.

xi