Content uploaded by Mohanad Fadhil Jwaid
Author content
All content in this area was uploaded by Mohanad Fadhil Jwaid on Feb 20, 2019
Content may be subject to copyright.
Image forgery detection based on SIFT 1
Maharashtra Institute of Technology, Pune
Image forgery detection based on SIFT technique
Under the guidance of
Prof. Trupti N. Baraskar
MIT, Pune
Mohanad F. Jwaid
Roll No. : 606013
M.E., I.T.
MIT, Pune
14-06-
2017
Image forgery detection based on SIFT 2
Content :
•
•
•
•
•
• 14-06-
2017
Image forgery detection based on SIFT 3
Introduction :
!"#$%
" &
'"
%
()*
%
+
14-06-
2017
Image forgery detection based on SIFT 4
Cont.…
,-.,-
14-06-
2017
Image forgery detection based on SIFT 5
Literature Survey
Image forgery
detection
Active approach Passive approach
TamperingDigital watermarking
splicing
Copy move
14-06-
2017
Image forgery detection based on SIFT 6
Cont...
N. Title Advantage Disadvantage
1 Digital Image forgery
detection using SIFT
feature
IEEE,2015
Reduce the require time to
detect forgery.
Less accuracy as
compare to other system.
2 Copy Move Forgery
Detection
using SIFT and
GMM
IEEE,2015
This system use the
Gaussian Mixture Model to
identify the image forgery.
The system is time
consuming.
3 Reflective SIFT for
Improving the
Detection of Copy-
Move Image Forgery
IEEE,2016
This system uses the new
technique is mirror-
reflection invariant feature
transform (MRIFT)
Less Accuracy as
compare to other system.
14-06-
2017
Image forgery detection based on SIFT 7
Cont.…
NO
.
Title Advantage Disadvantage
4 Image Forgery
Detection based on
SIFT and k-means
IEEE,2015
This system uses the k-
means++ technique to
identify the image
forgery or duplication.
The similarity is less as
compare to others
system.
5 Copy-Move
Forgery Detection
in Digital Images
Using Affine-SIFT
IEEE,2016
This is system is uses the
affine scale invariant
feature transform
(ASIFT)
Forgery detection
performance is low than
proposed method.
14-06-
2017
Image forgery detection based on SIFT 8
SIFT technique
Input image
Pre-processing
Key-point based Block based
Feature extraction
Matching
Filtering
Result
14-06-
2017
Image forgery detection based on SIFT 9
Pre-processing
/0, #/#0-
1,
14-06-
2017
RGB Y
CbCr
Image forgery detection based on SIFT 10
2)
14-06-
2017
Image forgery detection based on SIFT 11
3
4- 53
6Convolving image with Gaussian kernel repeatedly to get more and more
blurred version of the image
6Calculating the difference image (DoG) as approximation to Laplacian of
Gaussian (LoG)
14-06-
2017
Image forgery detection based on SIFT 12
Cont.…
7-53
3
%
14-06-
2017
Image forgery detection based on SIFT 13
$
') 3
3 % .
'"
3%
14-06-
2017
Image forgery detection based on SIFT 14
%'
3
'# " ')#
)'#" !%
14-06-
2017
Image forgery detection based on SIFT 15
Applications
%
%
%
%
%
$%
8%
14-06-
2017
Image forgery detection based on SIFT 16
Conclusion
"%
",-%
9')
%
%
14-06-
2017
Image forgery detection based on SIFT 17
References
922%$#(
*"
,-7:4;%
!1 2#($
/$$*;!<5
,!<.!5-7:4;%
="=$#(
)$*
>!"'7:4?%
50'#0</&<#(
')@@*52&
<&#'7:4;%
9$ #()$
<)*A7:4?#4B)4;%7:4?#
'<##
14-06-
2017
Image forgery detection based on SIFT 18
Thank You…
14-06-
2017