copy move forgery detection on digital images primer researchissue4/paper1.pdf · international...

International Scientific Global Journal in Engineering Science and Applied Research

(ISGJESAR) ISSN: 2456 - 1894

Vol. 3 Issue 3

May 2018

V o l 2 I s s u e 3 | w w w . I s g j e s a r . c o m

ABSTRACT

In today’s advanced age the reliable towards picture is twisting a direct result of malicious

forgery images. The issues identified with the security have prompted the examination

center towards tampering detection. As the source image also, the objective locales are from

a similar picture so that copy move forgery is very effective in image manipulation due to its

same properties such as temperature, color, noise and illumination conditions. In this

article, we added preliminary research methods (existing algorithms). We used hybrid

approaches of existing algorithms. The performance is evaluated in terms of normally used

parameters precision and recall with improved results. Thus the proposed CMFD can

manage all the image processing operations. We added single image forensics analysis

method also. Finally made a comparative analysis based on some clustering algorithms and

its applications, drawbacks, digital forensics tool analysis.

Keywords: copy move forgery, block-based, feature extraction, matching, tampering

Copy Move Forgery Detection on Digital Images –

Primer Research

Arun Anoop M1, PhD Scholar, S.Poonkuntran

2, Professor & Head

1,2Department of Computer Science, Velammal College of Engineering and Technology, Viraganoor, Madurai, India



Vol. 3 Issue 3

May 2018


1. INTRODUCTION

Digital images forgeries happening because of lack of security between client and server. In medical field, medical

image manipulation occurred, is that the security less communication channel between hospital and patient(s). If any

manipulation of data may life threaten patient’s health. But in nowadays many illegal manipulations in images and videos we can

see. Digital image are used in some of the medical, court. Copy move forgery (CMF) is one of the particular form of image

tampering where a piece (interested potion) of the image is copy-pasted on other piece of the same image. Digital image forgery,

were because free available image editing tools like Adobe photoshop , GIMP etc.[30]. Cut a piece of leaves and pasted it to hide

any of the object is Copy Move Forgery. Musaed Alhussein mentioned to include feature selection algorithms to reduce the

number of features. Also, in future, authors will investigate the effect of other types of color components such as luminance and

Chroma, or hue and saturation, in image forgery detection [61]. Vincent Christlein et. al., develop a joint forensic toolbox

performs on manipulated images [62]. V.Suresh et. al., mentioned in future authors will concentrate to detect spliced images [63].

Meenal Shandilya mentioned in future author will add identification of other forms of geometric attacks, relevant to copy-move

forgery, such as reflection, as well as other image region transforms, such as gray level interpolation [64]. Anushree U. Tembe et.

al., mentioned to find tampered regions with other type of geometric transformations in future [65]. Rani Susan Oommen et. al.,

use a different measure instead of SSIM to localize forged regions to get efficient detection. Authors mentioned SSIM is not a

good measure to compare regions [66]. R.C. Pandey et. al., mentioned in future their work will detect splicing in human body and

face, to concentrate social networking sites using different image features [67].

II. RELATED WORKS Anil Dada Warbhe et. al., concluded the main drawback of block-based approaches. Authors mentioned that the

detection procedure of copy-move forgery took high computation time. Authors concluded that in block-based approach, the

image needs to be divided into the number of blocks and each block is processed for feature extraction and matching. Hence

authors best choice is key-point based approach for copy-paste forgery detection in large size images over block based approach

[51]. Yongzhen Ke et. al., mentioned Image recognition accuracy, common sense knowledge and refinement of logic reasoning

rule was not high enough. And they concluded that improving accuracy will be their future work [52]. Xunyu Pan et. al.,

robustness of the proposed algorithm with regards to several imaging conditions. And authors future work will Combine the

current detection method with other noise based features to increase the detection performance [53]. P M Panchal et. al.,

mentioned future work will be in video registration [54]. SITI FADZLUN MD SALLEH et. al., mentioned future works may

explore in color images, or high resolution images. And also future works should consider multilayer processing [55]. Geethu N

Nadh et. al., mentioned authors will think about to add security enhancements in future [56]. Nishmitha M.R et. al., mentioned to

add DWT to detect image forgery in future [57]. Seung-Jin Ryu et. al., mentioned to concentrates on establishing an appropriate

data structure[58]. Keerthi Priya et. al., mentioned their work can be implemented in real applications. Also, authors have an idea

to combine with other mechanisms like image segmentation and neural learning [59]. Hansoo Kim et. al., mentioned to include

implementations and verifications of several detection schemes of digital image forgeries [60].

III. PROBLEM DEFINITION Main problem is lack of security between client and server. Most important problem is authenticity. Seven main

problems in `image forgery field` are adding or removing interested portions, resize, unusual color modification, cut someone’s

head and paste it into someone’s body, presenting false evidence in court, unavailability of original photos for experiment(Text

forgery in images), availability of freely available image editing tools(like GIMP, Adobe Photoshop etc.). Main drawback is a

person who have well knowledge in manipulation, he or she can change normal image to abnormal and abnormal to normal. This

will increase the crime rates. A small bit change can identify by image forgery detection approach.

IV. PROPOSED SYSTEM The research work of the paper is to identify the tampered portion of the image. The proposed work comprises of three

main steps(ii-iv): (i) pre-processing, (ii) Block Tiling, (iii) Feature Extraction, (iv) Block Matching and (v) Block reconstruction.

In proposed system (Multiple Feature-Extraction Approach) is implemented based on three existing algorithms. Finally it is

compared with two key point based methods SIFT and CSURF and proved MFE approach is the best solution to find image

forgery detections. And we used fusion approaches for evaluation process (both key point and block-based).



Vol. 3 Issue 3

May 2018


Fig. 1: MFE Approach (Block diagram of the proposed work)

Pre-ProcessingOriginal

Image

.

.

.

.

.

.

.

.

.

.

.

.

Weber Local DescriptorFeature

Extraction

Lexicographic Sorting

Tampered

Localization

Block

Matching

Forged

Image

Feature

Matching

EuclidianDistance

Block

Division

Hue Histograms

Zernike Moments

Fig. 2: 3FE Hybrid Approach(Block diagram of the proposed work{ZM+WLD+HH)



Vol. 3 Issue 3

May 2018


Pre-ProcessingOriginal

Image

.

.

.

.

.

.

.

.

.

.

.

.

HOG and GLCMFeature

Extraction

Lexicographic Sorting

Tampered

Localization

Block

Matching

Forged

Image

Feature

Matching

EuclidianDistance

Block

Division

Fig. 3: 2FE Hybrid Approach (Block diagram of the proposed work{HOG+GLCM)

a. Input Data Base

The information images gathered from various website pages is considered as database for the proposed system.

b. Preprocessing

Read the original image from the database.

After that the original RGB image is converted into Gray scale image using standard color space conversion.

In color image processing, no need any type of conversion.

Gray conversion can identify more accurate features from corners.

The standard equation from RGB to Gray conversion is,

BGRI g 114.0587.0229.0 (1)

In the above equation, R, G and B are red, green and blue components.

c. Block Tiling

After pre-processing, the picture is separated into small squares.

d. Feature Extraction

The extraction of relevant information that represent the characteristics features of the image.

Feature vector’s size will depend on the block size.

After that the features of the blocks are extracted using Zernike Moment, Weber Local descriptor and Hue Histogram for

first approach.

For second extract features based on Hog and GLCM algorithm.

V. RESULTS AND DISCUSSION The proposed work is implemented in the MATLAB 2014a software with a database of images. In this work, the image is taken

from the Columbia university dataset [26].

A) Comparative analysis:

Papers are compared based on drawbacks (1-28, 39) and investigations(29-39) by author(s).



Vol. 3 Issue 3

May 2018


Sl.No: Paper Title Drawbacks(1-28,39) and Investigations(29-38)

1 [68] Xudong Zhao et. al., mentioned in future authors will study about Higher order features integrated

with dimensionality reduction method [68].

2 [69] Anupama K. Abraham et. al., mentioned in future authors will concentrate to detect the Copy-

move forgery in videos with minimal time [69].

3 [70]

Pradyumna Deshpande et. al., mentioned that in future, authors will add DWT can be used to

increase the speed-up , find new method for rotation invariant forgery detection techniques. And

will work in Video forgery detection [70].

4 [71] Jaseela S et. al., in future, authors will concentrate in splicing and detect tampering in video

forgery [71].

5 [72] Weihai Li et. al., mentioned to improve the BAG (block artifact grid) marking algorithm to

achieve clearer grid map and reduce computation load. And also to design a machine judging

algorithm to check the alignment of BAG [72].

6 [73] Pin Zhang et. al., mentioned that authors will concentrate to work with weakness of their proposed

work [73].

7 [74] Hareesh Ravi et. al., mentioned in future, authors will perform the localization of tampering in a

video. In that localization can be in terms of GOP, frames or as small as a macro-block [74].

8 [75] Gawtham Srinivasan R et. al., mentioned in future authors will research about to detect forgery

with DWT and also authors concentrate to add overlapping sub blocks concept [75].

9 [76] Priya Singh et. al., will add correlation method and to produce better result with more than one

forged region in the image [76].

10 [77] Amrit Hanuman et. al., will investigate resampling factors, techniques to improve rotation

detection, optimal peak detection strategies, adaptable block size algorithm using JPEG

compressed Tampered images and different input image color spaces [77].

11 [78]

Ashima Gupta et. al., will take work to find optimize the data structures to gain additional query

performance and further improve accuracy [78].

12 [79] Joshi Chintal J et. al., mentioned to extend their work on videos where search for duplicated

blocks has to perform on multiple image frames [79].

13 [80] Prinkle Rani et. al., mentioned in future authors will minimize the processing time to detect the

forgery in the images to few seconds or even microseconds [80].

14 [81]. Harpreet Kaur et. al., mentioned in future authors will add more tests will be performed on

pictures with greater quantity of testing samples. And also authors will investigate comparison of

different color spaces in image forgery detection [81].

15 [1] Er. Saiqa Khan et. al., extended to work on videos where search for duplicated blocks has to

perform on multiple image frames[1].

16 [2] B.L.Shivakumar et. al., they will deal with problem such as rotation and Gaussian noise[2].

17 [3] Salam A. Thajeel et. al., will deal to detect and extract duplicated regions with higher accuracy and

robustness[3].

18 [4] Vivek Kumar Singh et. al., may deal to detect Gaussian blurring and AWGN[4].

19 [5] Feng Liu et. al., will deal with the detection of multiple copy move forgery and localisation in

future[5].

20 [6] Vidhi P. Raval may deal with Gaussian blurring may be in future[6].

21 [7] Zhang Ting et.al. , deal to improve the robustness against low quality factors of JPEG compression

and assure authenticity in future[7].

22 [8] Irene Amerini et. al., may deal with the proposal of new algorithms in the same area and

investigate for authenticity proving strategy[8].

23 [9] Vincent Christlein et. al., deal with a rigorous evaluation on the impact of noise and the scale

invariance of SATS in future[9].

24 [10] Yanping Huang et.al., may deal with rotation and scaling in future[10].



Vol. 3 Issue 3

May 2018


25 [11] Ghulam Muhammad et. al., may investigate more about DyWT and may propose new methods to

find authenticity[11].

26 [12] Yuenan Li will investigate more with LSH based similar patch detection scheme than

lexicographic sorting[12].

27 [13] Hieu Cuong Nguyen et. al., my deal with Gaussian noise and scaling[13].

28 [14] Seniha Ketenci et. al., may deal with rotation, scaling and other similar operations analysis in

future[14].

29 [15] M. Ali Qureshi et. al., surveyed different forging detection techniques with a focus on copy and

move approaches[15].

30 [16] Mohsen Zandi, Ahmad Mahmoudi-Aznaveh et. al., proposed a method and analysed with various

kinds of attacks such as rotation, AWGN, JPEG compression and blurring[16].

31 [17] Lu Liu et. al., demonstrated the efficiency of their method on different forgeries and quantify its

robustness and sensitivity[17].

32 [18] Jen-Chun Lee et. al., mentioned they improving detection in regions with rotation and scaling

adjustment over large areas[18].

33 [19] Hao-Chiang Hsu et. al., proposed method can achieve high correct rate, estimated rotation angle

and scaling factor[19].

34 [20] Davide Cozzolino et. al., proposed technique to be at least as accurate, robust, and much faster,

than state-of-the-art dense-field references[20].

35 [21] Ye Zhu et. al., mentioned that their algorithm was effective for geometric transformation, such as

scaling and rotation, Gaussian blur, Gaussian white noise and JPEG recompression[21].

36 [22] WU YunJie et. al., demonstrated the robustness and effectiveness[22].

37 [23] Mohd Dilshad Ansari et. al., discussed about pixel-based techniques for image forgery detection,

mainly copy-move and splicing techniques[23].

38 [24] Ewerton Silva et. al., their proposed image forgery detection based on voting process among all

detection maps[24].

39 [25] Jian Li et. al., in future they all will try to improve the detection speed of the proposed scheme by

means of parallel programming[25].

B) Result Analysis

The step by step analysis part of the proposed forgery detection is mentioned below with single original image shown in figure 8.

(c)CoMoFoD dataset

Fig 8: Original Images



Vol. 3 Issue 3

May 2018


Fig 9: Grayscale Images

Fig 10: Forged Images (angle=Left 90)

(c)CoMoFoD dataset

Fig 11: Authenticity of Images (Forgery detected area)

Fig 12: Authenticity of Images (Multiple Forgery detected area)

C) Evaluation Metrics

The performance evaluation of the proposed work is evaluated in terms of the following:-

100PrPP

p

FT

Tecision (16)

100ReNP

p

FT

Tcall (17)



Vol. 3 Issue 3

May 2018


Table 1: Performance metrics comparison for forgery detection

Techniques Precision Recall PSNR

SampleImage1 58 98 18.890

SampleImage2 55 97 12.666

SampleImage3 99 96.8 21.193

Table 2: Performance metrics comparison for forgery detection (Used fusion of image forgery detection techniques for

evaluation process)

Techniques Precision Recall PSNR

SIFT [27] 88.4 79.2 11.4280

CSURF [28] 91.1 85.4 14.76

3FE-methods with Lexi.sort and Eu.dist.

HYBRID Proposed

100 96.8 22.3193

2FE-methods with Lexi.sort and Eu.dist.

HYBRID Proposed

97 94.2 19.42

Table 3: Comparative analysis of clustering algorithm and its applications

Sl.

Number

Clustering algorithms Applications

1 K-means clustering 1. Leaf disease detection[33]

2. Data mining

3. Image Forgery Detection

[38]

4. Wireless Sensor Networks

5. Biometrics

6. Biomedical Engineering

7. Facial Image Extraction[41]

8. Machine Learning

9. Finger Knuckle print authentication

[36]

10. Iris segmentation

[34]

2 C-means or Fuzzy clustering 1. Iris segmentation[34]

2. Indoor Fingerprint Localization[40]

3. Passwords sharing prevention[35]

4. Mobile phone fraud detection[42]

3 Hierarchical clustering Ear localization[39]

4 Trajectory localization User authentication[37]

Table 4: Attacks we identified in single images (Text forgery in images)

Data poisoning attack Attack with some interested portion adding forgery.

Cut paste attack Cut a region and pasting approach.

Brightening attack Brightness updating attack.

Insertion of handwritten signature Adding forged signature into an image for manipulation crime.

Removal of watermark Using breaking tools to remove the watermarks.

Meta data removal attack Take the properties of image to delete all meta data informations.

GPS tag removal attack Depend on online sites to remove GPS tags.

EXIF tag removal attack With the help of freely available tools to remove the EXIF tags.

Metadata modifying and updating attack With the help of freely available websites to modify meta data and updating

attack.



Vol. 3 Issue 3

May 2018


Table 5: Comparative analysis of Digital Image (forensics tools, uses)

Jeffry’s Image metadata

viewer[83].

Can’t identify MS Paint used forgeries.

Online tool for viewing metadata embedded within images, such as camera setting used when taking

a photographs, date and location[83].

Metapicz web Meta data viewing tool.

EXIFTool by Phil

Harvey[84].

ExifTool is a free and open-source software program for reading, writing, and manipulating image,

audio, video, and PDF metadata [82]. Other methods to remove EXIf are [84].

FTK forensics tool Forensics solution.

Hex editor[86]. A hex editor is a type of computer program that allows for manipulation of the fundamental binary

data that constitutes a computer file[86].

Imageforensics[87]. Image forensics analysis[87].

Fotoforensics[88]. Image forensics analysis[88].

Verexif[89]. View and remove EXIF[89]

Error Level Analysis [85]

VI. CONCLUSION

Thus the paper solved the problem of image authenticity using the proposed copy move forgery detection. Best one approach in

our experimental evaluation is 3FE Hybrid approach. MFE approach 1 and 2 will work only if we have 2images (original and

forged). For single image forgery detection, we analysed some existing forgery detection tools. Three feature extraction

combination is the best one in our preliminary approach. In future, we will apply clue removal attacks also before post processing

stage. In our next work, we will deal with the same to test for robustness, accuracy tests against attacks like AWGN, Gaussian

Blur, Gaussian Noise, rotation (Clues removal attack once normal image processing attacks finished).

REFERENCES

[1] Khan, Er Saiqa, and Er Arun Kulkarni. "An efficient method for detection of copy-move forgery using discrete wavelet

transform." International Journal on Computer Science and Engineering, Vol. 2, No. 5, pp. 1801, 2010.

[2] Shivakumar, B. L., and S. Santhosh Baboo. "Automated forensic method for copy-move forgery detection based on Harris

interest points and SIFT descriptors." International Journal of Computer Applications, Vol. 27, No. 3, pp. 9-17, 2011.

[3] Thajeel, Salam A., and G. Bin Sulong. "State of the art of copy-move forgery detection techniques: a review." International

Journal of Computer Science Issues, Vol. 10, No .6, pp. 174-183, 2013.

[4] Singh, Vivek Kumar, and R. C. Tripathi. "Fast and efficient region duplication detection in digital images using sub-

blocking method." international journal of advanced science and technology, Vol. 35, No. 1, pp. 93-102, 2011.

[5] Liu, Feng, and Hao Feng. "An efficient algorithm for image copy-move forgery detection based on DWT and SVD."

International Journal of Security and Its Applications, Vol. 8, No. 5, pp. 377-390, 2014.

[6] Raval, Vidhi P. "Analysis and Detection of Image Forgery Methodologies."International Journal of Scientific Research and

Development, Vol. 1, No. 9, 2013.

[7] Zhang, Ting, and Rang-ding Wang. "Copy-move forgery detection based on SVD in digital image." Image and Signal

Processing, 2009. CISP'09. 2nd International Congress on. IEEE, 2009.

[8] Amerini, Irene, Lamberto Ballan, Roberto Caldelli, Alberto Del Bimbo, Luca Del Tongo, and Giuseppe Serra. "Copy-move

forgery detection and localization by means of robust clustering with J-Linkage." Signal Processing: Image Communication,

Vol. 28, No. 6, pp. 659-669, 2013.

[9] Christlein, Vincent, Christian Riess, and Elli Angelopoulou. "On rotation invariance in copy-move forgery detection." 2010

IEEE International Workshop on Information Forensics and Security. IEEE, 2010.

[10] Huang, Yanping, Wei Lu, Wei Sun, and Dongyang Long. "Improved DCT-based detection of copy-move forgery in

images." Forensic science international, Vol. 206, No. 1, pp. 178-184, 2011.

[11] Muhammad, Ghulam, et al. "Blind copy move image forgery detection using dyadic undecimated wavelet transform." 2011

17th International Conference on Digital Signal Processing (DSP). IEEE, 2011.

[12] Li, Yuenan. "Image copy-move forgery detection based on polar cosine transform and approximate nearest neighbor

searching." Forensic science international, Vol. 224, No. 1 (2013): 59-67.

[13] Nguyen, Hieu Cuong, and Stefan Katzenbeisser. "Detection of copy-move forgery in digital images using radon

transformation and phase correlation."Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), 2012

Eighth International Conference on. IEEE, 2012.

[14] Ketenci, Seniha, and Guzin Ulutas. "Copy-move forgery detection in images via 2D-Fourier transform."

Telecommunications and Signal Processing (TSP), 2013 36th International Conference on. IEEE, 2013.

[15] Qureshi, M. Ali, and M. Deriche. "A review on copy move image forgery detection techniques." Systems, Signals &

Devices (SSD), 2014 11th International Multi-Conference on. IEEE, 2014.



Vol. 3 Issue 3

May 2018


[16] Zandi, Mohsen, Ahmad Mahmoudi-Aznaveh, and Azadeh Mansouri. "Adaptive matching for copy-move Forgery

detection." 2014 IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, 2014.

[17] Liu, Lu, Rongrong Ni, Yao Zhao, and Siran Li. "Improved SIFT-Based Copy-Move Detection Using BFSN Clustering and

CFA Features." In Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), 2014 Tenth International

Conference on, pp. 626-629, 2014.

[18] Lee, Jen-Chun, Chien-Ping Chang, and Wei-Kuei Chen. "Detection of copy–move image forgery using histogram of

orientated gradients." Information Sciences, Vol. 321, No. 1, pp. 250-262, 2015.

[19] Hsu, Hao-Chiang, and Min-Shi Wang. "Detection of copy-move forgery image using Gabor descriptor." Anti-counterfeiting,

Security, and Identification. IEEE, 2012.

[20] Cozzolino, Davide, Giovanni Poggi, and Luisa Verdoliva. "Efficient dense-field copy–move forgery detection." IEEE

Transactions on Information Forensics and Security, Vol. 10, No. 11, pp. 2284-2297, 2015.

[21] Zhu, Ye, Xuanjing Shen, and Haipeng Chen. "Copy-move forgery detection based on scaled ORB." Multimedia Tools and

Applications, Vol. 75, No. 6, pp. 3221-3233.

[22] Wu, YunJie, Yu Deng, HaiBin Duan, and LinNa Zhou. "Dual tree complex wavelet transform approach to copy-rotate-move

forgery detection." Science China Information Sciences, Vol. 57, No. 1, pp. 1-12, 2014.

[23] Ansari, Mohd Dilshad, S. P. Ghrera, and Vipin Tyagi. "Pixel-based image forgery detection: a review." IETE Journal of

education, Vol. 55, No. 1, pp. 40-46, 2014.

[24] Silva, Ewerton, Tiago Carvalho, Anselmo Ferreira, and Anderson Rocha. "Going deeper into copy-move forgery detection:

Exploring image telltales via multi-scale analysis and voting processes." Journal of Visual Communication and Image

Representation, Vol. 29, No. 1, pp. 16-32, 2015.

[25] Li, Jian, Xiaolong Li, Bin Yang, and Xingming Sun. "Segmentation-based image copy-move forgery detection scheme."

IEEE Transactions on Information Forensics and Security, Vol. 10, No. 3, pp. 507-518, 2015.

[26] Ng TT, Chang SF, Hsu J, Pepeljugoski M. “Columbia photographic images and photorealistic computer graphics dataset.”

ADVENT, Columbia University, Technical Report. 2005.

[27] Amerini I, Ballan L, Caldelli R, Del Bimbo A, Serra G. “A sift-based forensic method for copy–move attack detection and

transformation recovery.” IEEE Transactions on Information Forensics and Security, vol. 6, No. 3, pp. 1099-110, Sep 2011.

[28] Bo X, Junwen W, Guangjie L, Yuewei D. Image copy-move forgery detection based on SURF. In2010 International

Conference on Multimedia Information Networking and Security 2010 Nov 4 (pp. 889-892). IEEE.

[29] V. Christlein, C. Riess, J. Jordan, C. Riess, and E. Angelopoulou, “An evaluation of popular copy-move forgery detection

approaches,” IEEE Transactions on Information Forensics and Security, vol. 7, no. 6, pp. 1841–1854, 2012.

[30] Arun Anoop M, ``Review on Image forgery and its detection,`` ICIIECS 2015,IEEE

[31] Arun Anoop M, Poonkuntran S, ``Certain investigation on Biomedical impression and Image Forgery Detection,``

International Journal of Biomedical Engineering and Technology (Inderscience.)

[32] Arun Anoop M, Poonkuntran S, `À Brief study on “Multimedia Security” In Research``, ISBN-13:978-93-86258-63-2,

FIRST EDITION,JULY 2017,VSRD Academic Publishing.

[33] Mr. Jagan Bihari Padhy*, Devarsiti Dillip Kumar**, Ladi Manish*** and Lavanya Choudhry****, ``Leaf Disease Detection

Using K-Means Clustering And Fuzzy Logic Classifier ,`` IJESTA,Volume 02, No. 5, May 2016

[34] S.Jayalakshmi1, M.Sundaresan2, `À Study of Iris Segmentation Methods using Fuzzy C-Means and K-Means Clustering

Algorithm,`` International Journal of Computer Applications (0975 – 8887), Volume 85 – No 11, January 2014,pp 1-5

[35] Salvador Mandujano, Rogelio Soto,``PREVENTING PASSWORD SHARING: USER AUTHENTICATION VIA FUZZY

C-MEANS CLUSTERING APPLIED TO KEYSTROKE PROFILES,``citeseer, doi=10.1.1.60.9251

[36] A. MUTHUKUMAR1** AND S. KANNAN 2,``K-MEANS BASED MULTIMODAL BIOMETRIC AUTHENTICATION

USING FINGERPRINT AND FINGER KNUCKLE PRINT WITH FEATURE LEVEL FUSION``,IJST, Transactions of

Electrical Engineering, Vol. 37, No. E2, pp 133-145

[37] Hazarath Munaga*1,J.V.R.Murthy1,and N. B. Venkateswarlu2, `Ènhanced User Authentication through Trajectory

Clustering ,`Ìnternational Journal of Recent Trends in Engineering , ACEEE

[38] Ghassem Alikhajeh1, Abdolreza Mirzaei1, Mehran Safayani1, and Meysam Ghaffari2,`` Duplicate matching and estimating

features for detection of copy-move images forgery,`ÀRXIV, Jan2017,pp 1-12.

[39] Surya Prakash, Umarani Jayaraman and Phalguni Gupta,`` Ear Localization using Hierarchical Clustering,`` Proceedings of

SPIE International Defence, Security and Sensing conference (Biometric Technology for Human Identification VI),

Orlando, Florida, April 2009.

[40] Hao Zhou ; Nguyen Ngoc V an,`` Indoor Fingerprint Localization Based on Fuzzy C-Means Clustering,`` Measuring T

echnology and Mechatronics Automation (ICMTMA), 2014 Sixth International Conference, China.

[41] Yousef Farhang, `` Face Extraction from Image based on K-Means Clustering Algorithms,`` (IJACSA) International Journal

of Advanced Computer Science and Applications, Vol. 8, No. 9, 2017

[42] Sharmila Subudhi, Suvasini Panigrahi, ``Detection of Mobile Phone Fraud Using Possibilistic fuzzy C-Means Clustering

and Hidden Markov Model,`` International Journal of Synthetic Emotions, Vol,issue2,Jul-dec2016

[43] Michael V. Boland,2Mia K. Markey,1and Robert F. Murphy1*, `Àutomated Recognition of Patterns Characteristic of

Subcellular Structures in Fluorescence Microscopy Images,`` 1998 Wiley-Liss, Inc., RECOGNITION OF CELLULAR

LOCALIZATION PATTERNS, pp366-375.



Vol. 3 Issue 3

May 2018


[44] Michael Vorobyov,``Shape Classification Using Zernike Moments, ``Available: https://www.slideserve.com/rivka/shape-

classification-using-zernike-moments

[45] Jie Chen,Shiguang Shan, Chu He, Guoying Zhao,Matti Pietikainen, Xilin Chen, Wen Gao,``WLD: A Robust Local Image

Descriptor,``IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 32, NO. 9,

SEPTEMBER 2010, pp 1705-1720

[46] Zernike Moments, Available: http://murphylab.web.cmu.edu/

publications/boland/boland_node25.html

[47] HOG, Available: https://www.learnopencv.com/histogram-of-oriented-gradients/

[48] Nishmitha M.R and Aravind Naik,” COMPARISON OF THREE TECHNIQUES OF IMAGE FORGERY DETECTION,”

International Journal of Emerging Technology in Computer Science & Electronics (IJETCSE) , Volume 14 Issue 2 –APRIL

2015

[49] Meera Mary Isaac, Dr. M. Wilscy,” A Key point based Copy-Move Forgery Detection using HOG features,”IEEE,2016.

[50] GLCM, Available: https://www.ucalgary.ca/mhallbey/glcm1 [51] Anil Dada Warbhe, R. V. Dharaskar, V. M. Thakare,” A Survey on Keypoint Based Copy-Paste Forgery Detection

Techniques”, International Conference on Information Security & Privacy (ICISP2015), 11-12 December 2015, Nagpur, INDIA(ScienceDirect, Procedia Computer Science 78 ( 2016 ) 61 – 67).

[52] Yongzhen Ke, Weidong Min, Fan Qin, Junjun Shang," Image Forgery Detection Based on Semantics", International Journal of Hybrid Information tehcnology,vol.7, No.1 (2014),pp. 109-124

[53] Xunyu Pan. Xing Zhang, Siwei Lyu, " Exposing Image Forgery with Blind Noise Estimation", MM&Sec’11, ACM, September 29–30, 2011, Buffalo, New York, USA.

[54] P M Panchal, S R Panchal, S K Shah,” A Comparison of SIFT and SURF”, International Journal of Innovative Research in Computer and Communication Engineering,Vol. 1, Issue 2, April 2013

[55] SITI FADZLUN MD SALLEH, MOHD FOAD ROHANI, MOHD AIZAINI MAAROF,”COPY-MOVE FORGERY DETECTION: A SURVEY ON TIME COMPLEXITY ISSUES AND SOLUTIONS”, Journal of Theoretical and Applied Information Technology 15

th June 2017. Vol.95. No 11.

[56] Geethu N Nadh, Sreelatha S.H,” Contrast Enhancement Detection on Digital Images - A Survey”, International Journal Of Engineering And Computer Science ISSN:2319-7242 , Volume 4 Issue 7 July 2015, Page No. 13465-13467.

[57] Nishmitha M.R and Aravind Naik,”COMPARISON OF THREE TECHNIQUES OF IMAGE FORGERY DETECTION”, International Journal of Emerging Technology in Computer Science & Electronics (IJETCSE),ISSN: 0976-1353 Volume 14 Issue 2 –APRIL 2015.

[58] Seung-Jin Ryu, Min-Jeong Lee, and Heung-Kyu Lee,” Detection of Copy-Rotate-Move Forgery Using Zernike Moments”, LNCS 6387, pp. 51–65, 2010

[59] Keerthi Priya, Vishnukanth Karwa P,” A Novel Image Localization Method for Image Forgery”,IJIRCCE, Vol. 5, Issue 5, May 2017

[60] Hansoo Kim and Joong Lee,” An Implementation and Pragmatic Analysis of the Digital Image Forgery Detection Schemes”, International Journal of Future Computer and Communication, Vol. 4, No. 5, October 2015

[61] Musaed Alhussein,” Image Tampering Detection Based on Local Texture Descriptor and Extreme Learning Machine”, 2016 UKSim-AMSS 18th International Conference on Computer Modelling and Simulation.

[62] Vincent Christlein, Christian Riess, ,Johannes Jordan, Corinna Riess, and Elli Angelopoulou,” An Evaluation of Popular Copy-Move Forgery Detection Approaches”,IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,26 Nov 2012.

[63] V.Suresh, T.Primya, G. Kanagaraj,” Efficient Detection Technique for Image Forgery”, International Journal of Imaging Science and Pattern Recognition Volume 1 Issue 1,2017.

[64] Meenal Shandilya, Ruchira Naskar, “ Detection of Geometric Transformations in Copy-Move Forgery of Digital Images”, Master Thesis, NIT,Rourkela,June 2015.

[65] Anushree U. Tembe, Supriya S. Thombre,” Copy-Paste Forgery Detection in Digital Image Forensic”, IJSRSET | Volume 3 | Issue 2,2017

[66] Rani Susan Oommen and Dr. Jayamohan M,” A HYBRID COPY-MOVE FORGERY DETECTION TECHNIQUE USING REGIONAL SIMILARITY INDICES”, International Journal of Computer Science & Information Technology (IJCSIT) Vol 7, No 4, August 2015

[67] R.C. Pandey, S. K. Singh, and K. K. Shukla,” A FULLY AUTOMATED BLIND AND PASSIVE FORENSIC METHOD FOR IMAGE SPLICING DETECTION”, I J C T A, 9(41) 2016, pp. 899-908

[68] Xudong Zhao, Shilin Wang, Shenghong Li and Jianhua Li,” Passive Detection of Image Splicing using Conditional Co-occurrence Probability Matrix”, APSIPA ASC 2011 Xi’an.

[69] Anupama K. Abraham, Rosna P. Haroon,” An Improved Hashing Method for the Detection of Image Forgery”, IOSR-JCE, Volume 16, Issue 5, Ver. III (Sep – Oct. 2014), PP 13-19

[70] Pradyumna Deshpande , Prashasti Kanikar,” Pixel Based Digital Image Forgery Detection Techniques”, IJERA, Vol. 2, Issue 3, May-Jun 2012, pp. 539-543

[71] Jaseela S, Mrs.Nishadha S. G.,” Copy Move Image Forgery Detection Using SURF Feature Point Extraction”, International Journal Of Scientific & Engineering Research, Volume 7, Issue 7, July-2016

[72] Weihai Li, Yuan Yuan and Nenghai Yu,” DETECTING COPY-PASTE FORGERY OF JPEG IMAGE VIA BLOCK ARTIFACT GRID EXTRACTION”.

[73] Pin Zhang, Xiangwei Kong, Detecting Image Tampering Using Feature Fusion”, 2009 International Conference on Availability, Reliability and Security, 2009 IEEE

[74] Hareesh Ravi, A.V. Subramanyam, Gaurav Gupta, B. Avinash Kumar,” COMPRESSION NOISE BASED VIDEO FORGERY DETECTION”.



Vol. 3 Issue 3

May 2018


[75] Gawtham Srinivasan R, Lokhesh K ,” Image Encryption and DWT Based Copy-move Image Forgery Detection”, International Journal of Computer Applications Technology and Research Volume 6–Issue 1, 66-69, 2017

[76] Priya Singh, Ms. Shalini Sharma Goel,” Correlation Based Image Tampering Detection”, (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 7 (2) , 2016, 990-995

[77] Amrit Hanuman, Azim Abdool, Akash Pooransingh, Aniel Maharajh, “A Novel Approach To Detection and Evaluation of Resampled Tampered Images”, International Journal of Image Processing (IJIP), Volume (9) : Issue (4) : 2015

[78] Ashima Gupta, Nisheeth Saxena, S.K Vasistha,” Detecting Copy move Forgery using DCT”, International Journal of Scientific and Research Publications, Volume 3, Issue 5, May 2013

[79] Joshi Chintal J, Prof. Shailendra K Mishra,” Investigating the Possibility of Recognizing the Forgery by Using Spatial & Transform Domain”, International Journal of Advance Research in Computer Science and Management Studies Volume 3, Issue 5, May 2015.

[80] Prinkle Rani, Er. Jyoti Rani,” Copy-Move Forgery Attack Detection using Enhanced SIFT”, IJERT,Vol. 4 Issue 10, October-2015.

[81] Harpreet Kaur, Kamaljit Kaur,” Image Forgery Detection Using Steerable Pyramid Transform and LAB Color Space”, International Journal of Advanced Research in Computer Science and Software Engineering, Volume 5, Issue 8, August 2015.

[82] EXIFTool, Available: https://www.sno.phy.queensu.ca/~phil/exiftool/

[83] Jeffrey’s Image metadata viewer, Available: http://exif.regex.info/exif.cgi

[84] EXIF removal, Available: https://www.makeuseof.com/tag/3-ways-to-remove-exif-metadata-from-photos-and-why-you-might-want-to/

[85] ELA, Available: https://fotoforensics.com/tutorial-ela.php

[86] Hex editor, Available: https://en.wikipedia.org/wiki/Hex_editor

[87] Image forensiscs, available: http://www.imageforensic.org/

[88] Foto forensics, Available: https://fotoforensics.com/

[89] Verexif , Available: https://www.verexif.com/

copy move forgery detection on digital images primer researchissue4/paper1.pdf · international...

Documents