Sunteți pe pagina 1din 11

R. V.

COLLEGE OF ENGINEERING, BENGALURU-59


(Autonomous Institution Affiliated to VTU, Belagavi)

Medical Image Forgery Detection


MINOR PROJECT REPORT

Submitted by

MANJUNATH YADAV S 1RV16EC087

RAVI A C 1RV16EC422

Under the guidance of

Mrs. Nethravathi K A
Assistant Professor
R.V. College of Engineering, Bengaluru-59.

In partial fulfillment for the award of degree


of
Bachelor of
Engineering
in
Electronics and Communication
Engineering 2019-20
R. V. COLLEGE OF ENGINEERING, BENGALURU-59
(Autonomous Institution Affiliated to VTU, Belagavi)

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

CERTIFICATE

Certified that the minor project work titled “Medical Image Forgery Detection” is carried out by
Manjunath Yadav S (1RV16EC087) and Ravi A C (1RV16EC422) who are bonafide students
of R.V College of Engineering, Bengaluru, in partial fulfilment for the award of degree of Bachelor
of Engineering in Electronics and Communication of the Visvesvaraya Technological
University, Belagavi during the year 2019-2020. It is certified that all corrections/suggestions
indicated for the Internal Assessment have been incorporated in the report deposited in the
departmental library. The minor project report has been approved as it satisfies the academic
requirements in respect of minor project work prescribed by the institution for the said degree.

Signature of Guide Signature of Head of the Department


(Mrs. Nethravathi K A) (Dr. K S Geetha)

External Viva
Name of Examiners Signature with date

II
R.VCOLLEGE OF ENGINEERING, BENGALURU - 560059
(Autonomous Institution Affiliated to VTU, Belagavi)

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

DECLARATION

We, Manjunath Yadav S (1RV16EC087) and Ravi A C (1RV16EC422) students of seventh


semester B.E., Department of Electronics and Communication Engineering, R V College of
Engineering, Bengaluru, hereby declare that the minor project titled ‘Medical Image Forgery
Detection’ has been carried out by us and submitted in partial fulfillment for the award of degree
of Bachelor of Engineering in Electronics and Communication Engineering during the year
2019-2020.

Further we declare that the content of the dissertation has not been submitted previously by
anybody for the award of any degree or diploma to any other university.

Place: Bengaluru

Date: 18/11/2019

Name Signature of the student

1. Manjunath Yadav S
2. Ravi A C

III
ACKNOWLEDGEMENT

We are indebted to our guide, Mrs. Nethravathi K A, Assistant Professor, Department of


Electronics and Communication Engineering for her wholehearted support, suggestions and
invaluable advice throughout our minor project work and also helped in the preparation of this
thesis.

We also express our gratitude to our panel members Dr. Saraswathi K, Associate Professor,
Department of Electronics and Communication Engineering and Dr. Usharani, Associate
Professor, Department of Electronics and Communication Engineering for their valuable
comments and suggestions.

Our sincere thanks to Dr. K S Geetha, Professor and Head, Department of Electronics and
Communication Engineering, RVCE for her support and encouragement.

We express sincere gratitude to our beloved Principal Dr. K. N. Subramanya for his appreciation
towards this minor project work.

We thank all the Project Coordinators Dr.Veenadevi S V Associate Professor, Mr. Subramanya
K N Assistant Professor and Mr.Nagaraj Bhat Assistant Professor of Electronics and
Communication Engineering Department, RVCE for their help.

We thank all the teaching staff and technical staff of Electronics and Communication
Engineering department, RVCE for their help.

Lastly, we take this opportunity to thank our family members who provided all the backup support
throughout the minor project work.

IV
ABSTRACT

Medical images have been used as one of the objects to diagnose the patient. A digitally
formatted medical image is easier to be stored and distributed but also easier to be modified for all
the illegal purposes. As health is a sensitive issue, it should be taken care for security and caution.
This project proposes a new medical image forgery detection system for the healthcare framework to
verify the images related to health-care. The existing watermarking scheme is used to perform tamper
detection in the region of interest .In this project Discrete Cosine Transform algorithm and Prewitt
Detection technique are used to get better results.

In this project the scanned and forged images are converted into gray image to perform
watermarking and forgery detection. The converted gray image should be a noise free image which
is done by dilation process to remove the unwanted noise. Then the image is segmented into blocks
to find DCT of each block .The watermark is then added to the corresponding DCT block to obtain
watermarked image. It is compared with forged image to know the given image is forged or not using
edge detection process. The forgery detection is used to find out whether any modification has been
done upon the medical image or not. The algorithm required for this process is simulated using
MATLAB 2014a.

The results show that the DCT watermarking algorithm modifies the image where the quality
of the watermarked image is of no decline relative to the original and the watermark is invisible. The
Prewitt algorithm provides two masks for detecting edges in horizontal and vertical directions. The
comparison result of watermarked and forged image shows that the images are not matched and the
matching percentage below the threshold indicates the image is forged with an accuracy of 80- 90%.

The image forgery detection system is able to perform forgery detection on different images
that include medical images, copy move forged images. Further development is needed to make this
watermarking scheme is fully reversible using developed descriptors like Dense Scale Invariant
Feature Transform (DSIFT), Fitting Function Rotation Invariant Descriptor (FFRID) and Segment
Gradient Orientation Histogram (SGOH) in the applications of object detection.

V
ACRONYMS

1. ANMS - Adaptive Non-Maximal Suppression

2. ANN - Approximate Nearest Neighbour

3. AWGN - Additive White Gaussian Noise

4. BoWImage - Bag of Words Image

5. BRIEF - Binary Robust Independent Elementary Features

6. CHT - Circular Harmonic Transforms

7. CMF - Copy-Move Forgery

8. CMFD - Copy-Move Forgery Detection

9. CRMF - Copy-Rotate-Move Forgery

10. DCT - Discrete Cosine Transform

11. DLT - Direct Linear Transformation

12. DSIFT - Dense Scale-Invariant Feature Transform

13. DWT - Discrete Wavelet Transform

14. FAST - Features from Accelerated Segment Test

15. FFRID - Fitting Function Rotation Invariant Descriptor

16. FLANN - Fast Library for Approximate Nearest Neighbours

17. HOG - Histogram of Oriented Gradients

18. HOGM - Histogram of Oriented Gabor Magnitude

19. HSV - Hue, Saturation, Value

20. PNG - Portable Network Graphics

21. RGB Red, Green, Blue

22. SGOH - Segment Gradient Orientation Histogram

VI
TABLE OF CONTENTS

PAGE NO
Abstract V

Acronyms VI

List of Figures X

Chapter 1
1. Introduction to Image Forgery Detection

1.1 Literature Survey 3


1.2 Motivation 8
1.3 Objectives of the project 9
1.4 Methodology 9
1.5 Organization of Report 9

Chapter 2
2. Fundamentals of Digital Watermarking 11

2.1 Digital Watermarking 11


2.2 Types of Digital Watermarks 12
2.3 Characteristics of Digital Watermarks 13

Chapter 3

3. Image Forgery and Detection Techniques 16

3.1 Type of Image Forgery 16


3.1.1 Cloning 16
3.1.2 Splicing 16
3.1.3 Retouching 17
3.1.4 Morphing 17

VII
3.1.5 Enhancing 18
3.1.6 Computer Generating 18

3.2 Image Forensic Tools 19


3.3 Forgery Detection Techniques 19
3.3.1 Block Based Techniques 19
19
3.3.2 DCT-based methods
19
3.3.3 Statistical-based methods 20

3.3.4 Transformation-based methods 20


20
3.3.5 Moments-based methods
20
3.3.6 Histogram-based methods

Chapter 4
4. Implementation of Image Forgery Detection System 22

4.1.1 Convert a Colored Image into Gray Image 22


4.1.2 Dilate an Image 24
4.1.3 Horizontal and Vertical Edge Processing of an Image 25
4.1.4 DCT-Based Image Watermarking 28
4.1.5 Forgery Detection Using Prewitt Edge Detection 28

Chapter 5
5. Results and Discussion 31

5.1 DCT image watermarking 31


5.2 Detection and Image Matching 32

Chapter 6
6. Conclusion and Future scope 36
6.1 Conclusion 36

VIII
. 6.2 Future scope 36
6.3 Learning Outcomes 37

References 38

IX
LIST OF FIGUERS

Figure No. List of Figure Page No.

3.1 An example of copy-move forgery where the original image 20


And the tampered Image

3.2 Examples of image splicing, all the images in the top row are authentic 21
And those in the lower row are spliced

3.3 An example of image retouching/repairing 21

3.4 Example of a sequence of morphed images: a human face is slowly 22


Changed into that of an alien doll

3.5 The image enhanced to alter the color, contrast, and blur of the 22
Background cars

3.6 A computer generated model 23

3.7 Test image and its circular shift 24

4.1 Flowchart for an implantation of Image forgery Detection 27

4.2 Color image 28

4.3 Gray image 28

4.4 Dilated image 29

4.5 Horizontal edge processing 30

4.6 Vertical edge processing 31

4.7 Gray image to be watermarked 32

4.8 watermark image 32

4.9 Watermarked Image where watermark is embedded to the original image 33

4.10 Output after horizontal and vertical edge detection using Prewitt Operator 35

5.1 Original images and watermarked images (post-processing) 37

X
5.2 Comparing watermarked image and non-watermarked image 39

5.3 Comparison of watermarked image and original image 40

XI

S-ar putea să vă placă și