IDL - International Digital Library Of Technology & Research Volume 1, Issue 4, Apr 2017
Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017
Image Forgery Detection Using Feature Point Matching and Adaptive Over Segmentation Seema Sultana, Sunanda Dixit Department of Information Sciences, Dayananda Sagar College of Engineering, Bangalore, India Seemasultna17@gmil.com
fabrication
applies the morphological operation to the
location conspire utilizing highlight point
combined locales to create the identified
coordinating and versatile over-division is
fabrication areas. The trial comes about show
worked here. This plan coordinates both
that the proposed duplicate move falsification
square based and key point-based falsification
identification plan can accomplish much better
location strategies. To start with, the proposed
location comes about even under different
Adaptive
calculation
testing conditions contrasted and the current
fragments the host picture into non-covering
cutting edge duplicate move fabrication
and sporadic pieces adaptively. At that point,
discovery strategies.
the component focuses are removed from each
Key words: Adaptive-Over Segmentation,
piece as square elements, and the square
Forgery Region Extraction, Fabrication areas
Abstract: A
duplicate
move
Over-Segmentation
elements are coordinated with each other to
1 Introduction
find the named include focuses, this strategy can around show the presumed fraud districts.
The
To recognize the phony locales all the more
computerized control to even now and moving
precisely, the Forgery Region Extraction
pictures
calculation is exhibited, which replaces the
misdirection,
component focuses with little superpixels as
uprightness. With experts testing the moral
highlight pieces. At that point combines the
limits of truth, it makes a potential loss of
neighboring hinders that have comparable
open trust in computerized media [1]. This
nearby shading highlights into the component
spurs the requirement for location devices that
squares to create the blended areas. At last, it
are straightforward to altering and can tell
IDL - International Digital Library
1|P a g e
presentation
raises
and
moral and
quick
spread
issues
of
advanced
of
truth, picture
Copyright@IDL-2017
IDL - International Digital Library Of Technology & Research Volume 1, Issue 4, Apr 2017
Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017 whether a picture has been altered just by
of data, and the dependability of computerized
investigating the altered picture. Picture
pictures is along these lines turning into an
altering is a computerized craftsmanship
essential issue [4]. As of late, an ever
which
picture
increasing number of scientists have started to
properties and great visual imagination [2].
concentrate on the issue of computerized
One alters pictures for different reasons either
picture altering. Of the current sorts of picture
to appreciate fun of computerized works
altering, a typical control of an advanced
making mind boggling photographs or to
picture is duplicate move falsification, which
deliver false confirmation. Regardless of
is to glue one or a few replicated region(s) of a
whatever the reason for act may be, the
picture into different part(s) of a similar
falsifier ought to utilize a solitary or a blend
picture.
needs
comprehension
of
arrangement of picture handling operations.
Copy-Move Operation
Image Segmentation
Amid the duplicate and move operations, some
Division is the way toward apportioning an
picture preparing techniques, for example,
advanced picture into different portions (sets
revolution, scaling, obscuring, pressure, and
of pixels) [3]. The objective of division is to
clamor expansion are once in a while
streamline
the
connected to make persuading falsifications.
portrayal of a picture into something that is
Since the duplicate and move parts are
more important and simpler to break down.
replicated
Picture division is normally used to find
commotion segment, shading character and
articles and limits (lines, bends, and so on.) in
other essential properties are perfect with the
pictures. All the more correctly, picture
rest of the picture; a portion of the imitation
division is the way toward doling out a mark
recognition strategies that depend on the
to each pixel in a picture to such an extent that
related picture properties are not pertinent for
pixels with a similar name share certain visual
this situation. In earlier years, numerous
qualities.
fabrication location techniques have been
and
additionally
change
proposed
Image Forgery Detection
from
for
a
similar
duplicate
picture,
move
the
imitation
identification. Computerized
picture
fraud
has
been
progressively simple to perform, because of
2 Detection Methods
the advancement of PC innovation and picture
The copy-move forgery detection methods fall
preparing
under two main categories:
programming.
Nonetheless,
advanced pictures are a well-known wellspring IDL - International Digital Library
2|P a g e
Copyright@IDL-2017
IDL - International Digital Library Of Technology & Research Volume 1, Issue 4, Apr 2017
Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017 
Block-based algorithms
strategies, it is a picture blocking strategy

Feature keypoint-based algorithms.
brought
the
Adaptive Over-Segmentation
calculation to separate the host picture into
Block-Based Methods:
non-covering and sporadic pieces adaptively. In the existing block-based methods, the image
At that point, like the key point-based phony
is segmented into overlapping and regular
recognition techniques, the element focuses
image blocks. Then the forgery regions are
are extricated from each picture hinder as
identified by matching blocks of image pixels
square elements as opposed to being removed
or transform coefficients. Some of the bloc-
from the entire host picture as in the
based methods are PCA, DCT, DWT, and
conventional key point-base strategies [7].
SVD [5]. Key-point based algorithms: An alternative to the block-based methods, keypoint-based forgery detection methods are proposed, where image keypoints are extracted and matched over the whole image to resist some image transformations while identifying duplicated regions. Scale-Invariant Feature Transform (SIFT) is applied to host images to extract feature points, which are then match to one another. When the value of the shift vector exceeded
Fig 1: Framework for copy-move forgery detection
the threshold, the sets of corresponding SIFT
scheme
feature points are defined as the forgery
The Adaptive Over-Segmentation calculation,
region. Speeded Up Robust Features (SURF)
which is like when the extent of the host
is also applied to extract image feature instead
pictures builds, the coordinating calculation of
of SIFT [6].
the covering pieces will be considerably more
3 Proposed System
costly. To address these issues, the Adaptive Over-division technique was proposed, which
This plan incorporates both the conventional
can portion the host picture into non-covering
square based phony location strategies and key
areas of sporadic shape as picture pieces a
point-based imitation recognition techniques.
short time later, the imitation locales can be
Like
square
based
phony
IDL - International Digital Library
identification 3|P a g e
Copyright@IDL-2017
IDL - International Digital Library Of Technology & Research Volume 1, Issue 4, Apr 2017
Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017 recognized
non-
After the host picture is sectioned into picture
unpredictabledistricts.
squares, piece components are separated from
Divisiontechnique, the non-covering division
the picture squares (IB). The conventional
can
piece
covering
by and
diminish
contrasted
coordinating
and
the
those
computational
the
covering
costs
blocking;
based
techniques
falsification
extricated
identification
elements
of
an
moreover, as a rule, the sporadic and
indistinguishable length from the square
significant areas can speak to the fraud district
elements or specifically utilized the pixels of
superior to the consistent squares.
the picture obstruct as the square components. Notwithstanding, these components reflect mostly the substance of the picture pieces, forgetting the area data. Additionally, these components are not impervious to different picture changes. Along these lines, in this venture, the component focuses are extricated from each picture hinder as square elements and the element focuses ought to be powerful to different twists, for example, picture
Fig 2: Flowchart of Adaptive-Over-Segmentation
scaling, revolution, and JPEG pressure.
4 Results In addition to the plain copy-move forgery, have tested proposed scheme when the copied regions are distorted by various attacks [8]. In this case, the forged images are generated by using each of the 48 images in the dataset, and the copied regions are attacked by geometric distortions that include scaling and rotation and common signal processing such as JPEG compression.
Fig 3: Flowchart of Block Feature Matching Algorithm
IDL - International Digital Library
4|P a g e
Copyright@IDL-2017
IDL - International Digital Library Of Technology & Research Volume 1, Issue 4, Apr 2017
Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017
Fig 5: SIFT Feature Detected Points
Fig 4: Input Image
Fig 6: SURF Feature Detected Points
IDL - International Digital Library
5|P a g e
Copyright@IDL-2017
IDL - International Digital Library Of Technology & Research Volume 1, Issue 4, Apr 2017
Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017 Fig 7: Matched Points
Future work could focus on applying the proposed forgery detection scheme based on adaptive over-segmentation and feature-point matching on other types of forgery, such as splicing or other types of media, for example, video and audio.
References [1] J. Fridrich, D. Soukal, and J. Lukáš, “Detection of copy–move forgery in digital images,” in Proc.
Digit.
Forensic Res.
Workshop, Cleveland, OH, Aug. 2003. [2] X. B. Kang and S. M. Wei, “Identifying tampered
regions
using
singular
value
decomposition in digital image forensics,” in Proc. Int. pp. 926–930, Dec. 2008. Fig 8: Forgery Detected
[3] S. Bayram, H. T. Sencar,“An efficient and
5 Conclusion
robust method for copy–move forgery,” in
Computerized falsification pictures made with duplicate move operations are trying to
Proc. IEEE Int. Conf. Acoust., Speech, Signal Process (ICASSP), pp. 1053–1056, Apr. 2009.
identify. A novel duplicate move phony
[4] S. J. Ryu, M. J. Lee, and H. K. Lee,
recognition conspire utilizing versatile over-
“Detection of copy-rotate-move forgery using
division and highlight point coordinating is
Zernike moments,” in Information Hiding.
proposed. The Adaptive Over-Segmentation
Berlin, Germany: Springer-Verlag, pp. 51–65,
calculation is proposed to portion the host
2010.
picture into non-covering and sporadic squares
[5] S. Bravo-Solorio and A. K. Nandi,
adaptively as indicated by the given host
"Exposing duplicated regions affected by
pictures, utilizing this approach, for each
reflection, rotation and scaling," in Acoustics,
picture, a fitting piece introductory size to
Speech and Signal Processing (ICASSP), 2011
improve the precision of the fabrication
IEEE International Conference on pp. 1880-
discovery results can be resolved and, in the
1883, 2011.
meantime, lessen the computational costs.
IDL - International Digital Library
6|P a g e
Copyright@IDL-2017
IDL - International Digital Library Of Technology & Research Volume 1, Issue 4, Apr 2017
Available at: www.dbpublications.org
International e-Journal For Technology And Research-2017 [6] X. Y. Pan and S. Lyu, "Region Duplication
Forensics and Security, IEEE Transactions on,
Detection Using Image Feature Matching,"
vol. 7, pp. 1018-1028, 2012.
Ieee Transactions on Information Forensics and Security, vol. 5, pp. 857-867, Dec 2010.
[8] B. Shiva Kumar and L. D. S. S. Baboo, "Detection of region duplication forgery in
[7] P. Kakar and N. Sudha, "Exposing Post
digital
processed
International Journal of Computer Science
Copy–Paste
Forgeries
through
Transform-Invariant Features," Information
IDL - International Digital Library
images
using
SURF,"
IJCSI
Issues, vol. 8, 2011.
7|P a g e
Copyright@IDL-2017