ArticlePDF Available

Abstract and Figures

The goal of the paper is to provide a practical conceptual framework based on hiding of watermarks embedded within coefficients image disintegrated by contourlet transform, that is characterized by extra sustenance for the potential and actual security of the hiding methods, and strengthen distribution techniques of watermarking inside the cover image; thus this can be done through achieving a kind of merge between those techniques and others techniques of image processing. A case study approach was used to allow the algorithms of the recommended system (non-blind) through concealing the watermarking which is resulted in the possibility of altering the watermarking dimensions with the fixed cover measurements and reciprocally. Another important practical implication is that the quartet tried to divide the techniques into four sections before it has been embedded inside the cover-image then after they have been split up, they distribute them among the fragments of the watermark within the cover-image regarding the quartet try the method. The techniques of using the three suggested algorithms by employing the watermarks cover image of various dimensions displayed that, the correlation factor ratio preceding and succeeding the process of hiding of the cover-image has been exceeded 0.99%. The most striking outcome to emerge from the data is that the result of this research which is in the watermark measured before and after the process depending on the PSNR, SNR, MSE, NC.
Content may be subject to copyright.
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16979
Published by: The Mattingley Publishing Co., Inc.
Hiding Image by Using Contourlet Transform
Diyar Qader Zeebaree1, Adnan Mohsin Abdulazeez2, Omer Mohammed Salih Hassan3
Dilovan Asaad Zebari4, Jwan Najeeb Saeed5
1,4Research Center of Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq
2Presidency of Duhok Polytechnic University, Kurdistan Region, Iraq.
3Electrical & Electronic Engineering Duhok Polytechnic University, Duhok, Kurdistan
5IT Department, Duhok Technical Institute, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq
Article Info
Volume 83
Page Number: 16979 - 16990
Publication Issue:
May - June 2020
Article History
Article Received: 1 May 2020
Revised: 11 May 2020
Accepted: 20 May 2020
Publication: 24 May 2020
Abstract:
The goal of the paper is to provide a practical conceptual framework based
on hiding of watermarks embedded within coefficients image disintegrated
by contourlet transform, that is characterized by extra sustenance for the
potential and actual security of the hiding methods, and strengthen
distribution techniques of watermarking inside the cover image; thus this
can be done through achieving a kind of merge between those techniques
and others techniques of image processing. A case study approach was used
to allow the algorithms of the recommended system (non-blind) through
concealing the watermarking which is resulted in the possibility of altering
the watermarking dimensions with the fixed cover measurements and
reciprocally. Another important practical implication is that the quartet tried
to divide the techniques into four sections before it has been embedded
inside the cover-image then after they have been split up, they distribute
them among the fragments of the watermark within the cover-image
regarding the quartet try the method. The techniques of using the three
suggested algorithms by employing the watermarks cover image of various
dimensions displayed that, the correlation factor ratio preceding and
succeeding the process of hiding of the cover-image has been exceeded
0.99%. The most striking outcome to emerge from the data is that the result
of this research which is in the watermark measured before and after the
process depending on the PSNR, SNR, MSE, NC.
Keywords: Watermarking, hiding information, hiding data, contourlet
transformation
_____________________________________________________________________________________________
I. Introduction
Nowadays, internet communication becomes a
major part of infrastructure [1]. Transmitting the
data across. Internet can be done by concealing a
secret message behind multimedia signals. The
mention message can be decrypted either by
providing the same key utilized for encryption or
by verifying its reality. An example about that,
image watermarking is performed by embedding a
secret message into the original image, to
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16980
Published by: The Mattingley Publishing Co., Inc.
guarantee authentication and verifying of
ownership of the allocated multimedia data [2,3].
Data can be hided and reversed from additional
data to digital images. The original image can be
totally rebuilt after merging the extracted data [4,
5]. Since Internet is an open surrounding, there is
need to provide effective methods of preventing
data from being duplicated or exploited illegally
so, among these procedures the encryption
technology has been inserted and deemed among
the long-established data security technologies.
There is no doubt, that technological developments
made our life easier and speed up everything
around us in this world. The organizations
concerned with researches based on international
standards mentioned that the Internet provides a
large area of relaying private and confidential data
from various scopes such as education, medical
research, medicine and military fields. Since
information leakage, illegal data creation and data
copying, from one to other it’s important to setup
the data security system. Therefore, data security
has been increased [6]. The watermark that use in
digital watermarking technology are invisible for
human, but computer could process. Watermark
can be embedding into the printing design, and thus
the location can be determined by specific key. So,
this will reduce chances for counterfeiters to access
it easily. At the end this will vary application
technology in the digital field, like broadcast
examination, identification, prove ownership,
transaction monitoring, content verification, copy
regulation, device regulation and digital copyright
protection [7].
As for the digital image watermarking procedures
the triumph of the watermarking procedures relies
on how robust it is to various kinds of attacks to
demolish the watermark. It is significant to discern
these attacks for designing stronger and more
robust watermarking methods [8].
A watermark is a data security method, among
other common data security technologies used,
authentication and copyright technique to suffice
its intent, a watermark entails embedding digital
details into multimedia data. The watermark can be
further insulating into two ways depending on how
views it is in the files, for instance visible and
invisible watermarking. Watermarking prevents
the immoral repetition of media files and claims
false ownership [9,10,11].
The contourlet transform which stands for new
depiction of the two-dimensional digital pictures
which are needed for inspecting grey the cover-
image in order to include frequency the watermark
area, so this endeavor will issue the mentioned
algorithm extra firmness and finally increasing the
concealed potential, while still conserving cover-
image quality and allow extraction of the
watermark having the greatest percentage of
precision.
II. Related Work
Considerable researchers have presented many
works on the topic of data security, especially on
the topic of information hiding. Below are some of
the current work in the field of hiding information
within digital images:
A. Watermark Generation Algorithm
The watermark technique for digital depends on the
angle quantization. The mentioned method works
on the energy ratio connecting two angles
seemingly not too much risky against any
alteration. Digital image watermarking method
gives authentication for undisclosed channel and
imperceptibility [12,13]. In spite of the huge spread
of manipulation of the watermarked, image which
is commonly causes breaking down of
watermarked bits and change them into random bit
streams. Lastly, the quantization of many angles
provided a good filter for digital watermarking. For
angle quantization application, every watermark
bit is embedded in six pairs of actual images. Sets’
dimensions of the DCT of the actual picture, like
(x1, x2 x3, x4, x5 and x6) were picked to
demonstrate a gap in the two-dimensional
coordinate structure. Then, three coordinates of
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16981
Published by: The Mattingley Publishing Co., Inc.
P(x1,x2), Q(x3,x4), and R(x5,x6) are regarded and
calculated based on following Equations as in
(1,2,3) [14].

 
 
 (1)
 
 (2)
 
 (3)
B. Contourlet Properties
The basic idea of contourlet transform is pull
directional information at multiscale resolution.
The contourlet transform can be esteem is a real
sensibility of two-dimensional performance of
images and can achieve degeneration in any
direction at any measure. The contourlet transform
include many wonderful properties, for instance
multiresolution, directionality, localization, and
anisotropy and fix the problem of incomplete idiom
of wavelet transform in directional data [15,16].
Contourlet transform deem as developed or an
altered type of Discrete Wavelet Transform (DWT)
. DWT dissolves an image into four sub-bands low-
low (approximation coefficient), low-high (vertical
details), high-low (horizontal details), and high-
high (diagonal details). Furthermore, contourlet
transform was capable to yield multiple sub bands
as per requirements. This can be taken away by
using Pyramidal Directional filter bank (PDFB)
which includes of Laplacian Pyramidal filter and a
double filter band [17,18].
With regard to contourlet transform theory, there
are several kinds of filter banks, for instance,
quincunx sampling filters and directional filters.
Quincunx sampling filters is gotten on the two-
dimensional spectrum segmentation. The various
frequency response categories will make various
sub-bands. In case of utilizing diamond filter, a
low-pass and high-pass sub-band should be 45o
acquired. But, when we use the fan filter, the
horizontal and vertical sub-bands should be 45o
direction acquired [19,20].
The contourlet transform amulets the reduction of
wavelet. Contourlet transform is a multi-scale and
multi directional framework of discrete picture as
well. In this method, both multi scales and
separated in a serial way so as, the laplacian
pyramid utilized to take the point abruption, which
is followed by a directional filter bank to combine
both points abruption with linear structures
together [21].
C. Data Hiding
The data hiding presented in this section suggests
to hide data which is a technique utilized to hide
data in which the find of hidden data isn’t possible,
data hiding (cover writing) hide the reality that a
secret data is being transmitted. These methods
include steganography, covert channels, copyright
marking, watermarking, visible watermarking and
imperceptible watermarking, the Figure.1 illustrate
various section technologies utilized to conceal
details and these methods and out of the way of
time have taken a major awareness in the domain
of availing data accuracy and privacy.
Cryptography is a method that mix a data such that
no one can know it. While data hiding is a method
that hides the data in a way it cannot be visible. An
invisible data will not appear by using methods that
hide the data doubtfully from the recipient but a
message in encrypted text [22].
Fig 1: Classes of Data Hiding Technologies
II Proposed Method
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16982
Published by: The Mattingley Publishing Co., Inc.
A watermark technique was used to merge the
contribution linking those methods and the
algorithms of treatment of the digital pictures. The
contourlet explain a current illustration of the 2-D
digital images in solving the gray cover image
which is embedded in the watermark. To maintain
the quality of the cover image by providing the
frequency domain an effort to provide the proposed
algorithm with high power and increase hiding
capability. This allows us to get the watermark as
accurately as possible.
A. Covert Chanel
Local authority, criminals and terrorist community
have a reasonable approach to conceal their
transmision secret. Nevertheless, both spy and data
robbery raids are growing with advanced
procedures, which request current data concealing
methods to avoid such raids. Covert Channels are
defined as concealing secret details within rightful
data, utilizing unspecified or unlooked for ways for
concealing the data, pick interest of actual network
agreements to move out the data, like concealing
data within TCP/IP packets, this inspire an
invisible channel and permit concealed data to
avoid Internet supervision without altitude the
doubt [23].
B. Steganography
It is the technique and science of hide data such
that that no one other than the transitter and
receiver concerned can doubt the actuality of the
data, a type of secrecy utilizing obscurity. Hidden
data may appear differently: image, press article,
shopping list. Steganography includes the hidding
of data. In digital steganography, electronic links
may consist of steganographic coding within the
transfer layer, for instance a document record,
picture record, program or agreements. Media files,
due to their greater capacity, are better relayed
using steganographic technique. For instance, a
transmitter might begin with an unhurt picture
record and set the pigment of every percent pixel to
agree to a data in the alphabet. The distinction is so
perfect that anyone who is not sectionicularly
searching has no chance of perceiving the
alteration [24].
C. Copyright
Copyright security has become an seriouse topic
for executive applications. Classical methods
consistes the use of encryption, watermarking, or
data hiding for the security of the copyright or
property of multimedia content, copyright security,
also known as content security, copy protection,
and copy limitation, is any effort intended to hinder
reproduction of software, movies, music, and other
media, specifically for copyright grounds [25].
D. Watermark
There are two broad categories of watermark:
visible and invisible. These two main types must be
contemplated when creating a digital
watermarking algorithm.Figure 2. Emphasizes the
importance of balancing strength and capacity
while respecting other requirements when creating
a watermark algorithm [26]. Increasing the amount
of data leads to distortion in the quality of the cover
and reduces the robustness in case of any attacks.
[27]. Therefore, optimal solidity of data can be
selected when embedding to obtain better
concealment [28]. Draw attention to the size of the
cover utilized to embed the watermark larger than
the watermark size [29].
Fig. 2: The fundamental of the watermarking [26]
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16983
Published by: The Mattingley Publishing Co., Inc.
III Watermark Categories
Watermark is divided into four categories [27]:
1. text: means adding watermark to the text.
2. Picture: means appending watermark to the
image constituents.
3. Movies:means attaching a watermark to
movie records that control these programs.
Skitching: means attaching a watermark to two or
3-dimensional illustrations
A. Visual Watermark
The observable watermark is one of the digital
watermark that entails embedding the watermark
of the data is embedded into the casing in a visual
way that is observable by the naked eye. Thus, the
watermark of the cover is completely different
from the original mark after the process is fully
embeded. This is the most important and generality
popular method to securite your digital multimedia
data, so we need to take some action to annul
propagation images and videos that can be
permanently utilized in unlawful acts to handle
the media in question [30]. There are some
qualifying properties in the visible watermark.
- The watermark is included within the wide
band or significant range of the cover image to
restrain it from being eliminated.
- The watermark is clearly included
exclusive of blocking the significant sectioniculars
of the cover picture.
- It is difficult to take off specifics as this
necessitaes for huge attempts and inflated cost
allocation.
- The methods of the visual watermark
should be done beautifully with minimal attempt
and people intrusion.
B. Unvisual Watermark
This is can be hidden in digital contents in a
technique enable as to be known distinctly
[31,32,33].
IV The Algorithm
Hiding of the watermark usually is performed by
means of contourlet transform since this technique
has the ability to hide the soft edges of the image.
Human being vision is often less sensitives than
edges to prevent the access to confidential
information. The grey watermark has been hidden
in the directional bands specifically those
containing higher frequencies to the cover-image.
Several research have been conducted on the
algorithms for several categories of watermark
grey images and the cover-image with various
dimensions. To confirm the accurecy of the
watermark embeding in the cover image before and
beside hiding the watermark that many scarcely
pedicted through the repetetive scale
A. Embedding
Analysis the cover-image and watermark.Set up
the cover image coefficient of the watermark using
the contourlet transform coefficient and then
establish the measurements of the contourlet
transform factors of the cover image. Update the
pixel value according to equation (4) and then
renew the structure using the inverse contourlet
transform to get a section of the watermark image.
  (4)
Encryption of the secret key used in the embedding
procedure, settled on by the two sections through
relaying using a contourlet transform coefficient.
Regrouping the watermark image sections.
B. Extraction Watermark
The following point show how to extract the
confidential data from sections of a watermark at
the section of the receiver.
- Set up the cover-image by splitting it into 4
sections.
- Extract the unknown key and decrypt it in
agreement to the embedding by utilizing the
contourlet transform coefficients.
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16984
Published by: The Mattingley Publishing Co., Inc.
- Processing the section of a cover-image and
the watermark utilizing the contourlet transforms
with similar number of the evaluation scale in the
embedding phase.
- Take out the contourlet transform factor of
the secret picture of the section watermark utilizing
Equation (5), steps 2, 3 and 4 are replicated with
respect to the quantity of the coefficients
embedded.
  (5)
- Collect the contourlet transform
coefficients that are take out from the watermark,
and from the implementation of the inverse
contourlet transform that section is recreated.
- The procedures above are replicated to take
out the residual sections of the watermark picture.
Preceding move is the phase of combination the
four derived sections of the watermark to get the
whole watermark, on top of grouping the recover
the cover-image.
C. Measurement Efficiency of
Watermark Algorithm
To estimate the effective implementation of the
algorithm with the aim of including the watermark,
there is a need to study some metrics related to the
implementation and effectiveness of the algorithm.
There are many metrics, and the focus of this
research has been on a set of metrics that confirm,
they are active in reducing the strength of the
algorithms used, based on a large issue of
researches published. Below are the metrics that
were based on this paper.
 
 

 (6)
 
 (7)

  

 (8)
  


  


 (9)
V. Results and Desscusion
All code is written in (matlab15a) to apply the
contourlet transform from start to end of the
project.
A. Energy
The aim of this algorithm splitting the quaternary
was included to enhance the solidity of the hiding
on top of what it supplies, the ability to embed a
watermark with dimensions near to the size of the
cover image. This was achieved by splitting the
watermark. This algorithm guide to outcome that
may be overtake the outcomes of the other
algorithms in embedding and retrieving the
watermark. As shown in figure (3) is the model of
the watermark “Flower.png” using the first section
of the algorithm to embed the watermark with
measurements (128x128) after splitting it into four
sections with a dimension of 64 x 64.
Fig. 3: Include the secrete image” flower” in the
cover image’s
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16985
Published by: The Mattingley Publishing Co., Inc.
Table (1): Show the Outcome of Embedding Watermark Algorithm using Contourlet Transformation and
Energy for the First Section of Algorithm
Whereas (table1) evidence the outcomes of the
watermark. As shown in the (table 2) we can
illustrate the outcomes of take out the watermark
With its four sections “Flower.png” from the
sections of the cover-image “Lena.png” and (table
3) shows the outcomes of retrieve the cover-image.
Cover
Image
Cover
image’s
size
Watermar
k
Waterma
rks size
Coefficients
Different parameter outcomes of efficiency of the
watermark image
Lena-
image
1024×1
024
Flower-
sections
128×128
MSE
PSNR
NC
SNR
Section
1
512×51
2
Section1
64×64
{1,1}
0.000004
99.941003
1.000000
94.023212
{1,2}
0.000000
121.93014
0
1.000000
116.012349
{1,3}
0.000000
122.88413
0
1.000000
116.966339
Section
2
512×51
2
Section2
64×64
{1,1}
0.000016
94.451115
1.000000
86.393365
{1,2}
0.000000
120.17884
6
1.000000
112.121096
{1,3}
0.000000
121.84108
6
1.000000
113.783336
{1,1}
0.000023
92.884560
1.000000
88.069917
Section
3
512×51
2
Section3
64×64
{1,2}
0.000000
119.69961
1
1.000000
114.884967
{1,3}
0.000000
120.77052
6
1.000000
115.955882
{1,1}
0.000005
99.423635
1.000000
94.881229
Section
4
512×51
2
Section4
64×64
{1,2}
0.000000
120.08528
3
1.000000
115.542877
{1,3}
0.000000
121.33681
5
1.000000
116.794408
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16986
Published by: The Mattingley Publishing Co., Inc.
Table (2): The Outcomes of Extracting Watermark Embedding Algorithm using Contourlet Transformation
and Energy Algorithm the First Section
Table (3): The Outcomes of Recover Watermark Embedding Algorithm using the Contourlet
Transformation and Energy Algorithm the First Section
Cover
Image
Cover
Image size
Wate
rmar
k
Size of
the
waterma
rk
Conto
-urlet
coeffic
-ients
Different Parameters Amount for Efficiency
Performance of the Recover Cover-Image
Lena
1024×1024
Sectio
n from
Flower
128×128
MSE
PSNR
NC
SNR
Section
1
512×512
Secti
on1
64×64
{1,1}
0.000000
123.307609
1.000000
117.389818
{1,2}
0.000000
134.462805
1.000000
127.934411
{1,3}
0.000000
134.276372
1.000000
128.358581
Section
2
512×512
Secti
on2
64×64
{1,1}
0.000000
120.553064
1.000000
112.495314
{1,2}
0.000000
131.358427
1.000000
123.300677
{1,3}
0.000000
132.902178
1.000000
124.844428
Section
3
512×512
Secti
on3
64×64
{1,1}
0.000000
118.351484
1.000000
113.536840
{1,2}
0.000000
131.034658
1.000000
126.220014
{1,3}
0.000000
132.138745
1.000000
127.324101
Section
4
512×512
Secti
on4
64×64
{1,1}
0.000000
123.576100
1.000000
119.033694
{1,2}
0.000000
131.449627
1.000000
126.907221
{1,3}
0.000000
132.375643
1.000000
127.833237
Image
Cover
Image size
Cover
Watermark
Size of the
watermark
Different Parameter Outcomes for Efficiency of
Extracted Watermark
Lena
1024×1024
Earth
128×128
MSE
PSNR
NC
SNR
Section1
512×512
Section1
64×64
73.922108
27.673523
0.994689
18.355091
Section2
512×512
Section2
64×64
97.138451
27.944790
0.991037
21.655048
Section3
512×512
Section3
64×64
168.158146
24.977378
0.992986
21.079227
Section4
512×512
Section4
64×64
82.885288
27.820186
0.990559
17.900146
After of collecting the four sections
105.525998
27.585107
0.993735
20.368837
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16987
Published by: The Mattingley Publishing Co., Inc.
Table (4): Illustrate the Outcomes of other Researches [32].
Tested Image (Cover)
Method
Measure
Baboon
Barbara
Boat
Couple
Elaine
Lena
Peppers
37
37
37
37
46
47
37
CTL.[1]
PSNR
84.1548
…….
84.4969
84.2884
……
83.542
1
83.0052
DWT and
SVD [18]
52.4855
……
52
……
……
53
……
APAP-
MIPOEE
Applying a
filling
border in a
set of
angles -
MSB6[15]
48.2793
48.2276
……
48.4922
……
48.409
4
48.2294
Non-Blind
CTL [1]
107.7354
51
108.3099
34
101.8727
80
108.8727
80
91.56067
8
107.30
9568
96.8727
80
Proposed
method\3rd
0.000251
77
0.000262
1
0.000232
7
0.000244
14
0.000253
31
0.0002
8992
0.00032
806
APAP-
MIPOEE
Applying a
filling
border in a
set of
angles -
MSB6[17]
MSE
0.000001
0.000001
0.000004
0.000001
0.000033
0.0000
01
0.00001
1
Proposed
method\3rd
57.07
……
……
……
……
59.695
58.976
APAP-
MIPOEE
Applying a
filling
border in a
set of
SNR
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16988
Published by: The Mattingley Publishing Co., Inc.
angles -
MSB6[17]
101.4802
48
99.54147
1
95.52683
7
102.9794
08
80.90189
7
101.50
6316
88.0749
93
Proposed
method\3rd
0.921
0.972
0.922
0.981
0.970
0.973
0.965
CTL.[33]
NC
1.000000
1.000000
1.000000
1.000000
1.000000
1.0000
00
1.00000
0
Proposed
method\3rd
Employ the section of the cover-image and the
hidden picture in constructing the concealing
system to perform noise reduction in the recovered
hidden picture and the extracted cover-image and
then illustrated over the estimates of PSNR and
SNR on top of the rise in the grade of estimation
connecting the source picture and the extracted one
as can be seen via the estimates of NC.
VI. Conclusion
The characteristic of information dissemination in
the contourlet transform coefficients outcomes in
absolute secrecy of the information requirement
become concealed, where the cover-image that
contains a hidden watermark very near to the actual
picture and caused difficulty to the viewer to
realize that when it subsists at the interior of the
cover-image. This work proposed algorithm
embedding utilizing the Contourlet Transformation
and Energy secret data within cover image
coefficients. Furthermore, contourlet transform
coefficient and energy are utilized depending on
the concept on quadric division tree in order to hide
data. Proposed algorithms are evaluated depending
on PSNR, MSE, SNR, and NC where showed that
in my proposed algorithm is the best one.
VII. References
[1]. Q. Su, G. Wang, G. Lv, X. Zhang, G. Deng, and B. Chen,
“A novel blind color image watermarking based on
Contourlet transform and Hessenberg
decomposition,” Multimed. Tools Appl., vol. 76, no. 6,
pp. 87818801, 2017.
[2]. M. Amini, H. Sadreazami, M. O. Ahmad, and M. N. S.
Swamy, “A Channel-dependent Statistical Watermark
Detector for Color Images,” IEEE Trans. Multimed.,
vol. PP, no. c, p. 1, 2018.
[3]. D. Q. Zeebaree, H. Haron, and A. M. Abdulazeez, "Gene
selection and classification of microarray data using
convolutional neural network," in 2018 International
Conference on Advanced Science and Engineering
(ICOASE), 2018, pp. 145-150: IEEE.
[4]. B. Yin, F. Chen, H. He, and S. Yan, "Separable reversible
data hiding in encrypted image with classification
permutation," in 2017 IEEE Third International
Conference on Multimedia Big Data (BigMM), 2017,
pp. 201-204: IEEE.
[5]. V. Ananthaneni and U. R. Nelakuditi, "Hybrid digital
image watermarking using contourlet transform (CT),
DCT and SVD," International Journal of Image
Processing (IJIP), vol. 11, no. 3, p. 85, 2017.
[6]. I. Phutane and S. Nalbalwar, "A new method for secret
image transmission via secret fragment visible mosaic
image," in 2016 International Conference on
Electrical, Electronics, and Optimization Techniques
(ICEEOT), 2016, pp. 2418-2423: IEEE.
[7]. W. Zhang, J. Meng, and C. Ma, "Research progress of
applying digital watermarking technology for
printing," in 2018 Chinese Control And Decision
Conference (CCDC), 2018, pp. 4479-4482: IEEE.
[8]. S. Kumar and A. Dutta, "A study on robustness of block
entropy based digital image watermarking techniques
with respect to various attacks," in 2016 IEEE
International Conference on Recent Trends in
Electronics, Information & Communication
Technology (RTEICT), 2016, pp. 1802-1806: IEEE.
[9]. I. J. Kadhim, P. Premaratne, P. J. Vial, and B. Halloran,
"Comprehensive survey of image steganography:
Techniques, Evaluations, and trends in future
research," Neurocomputing, vol. 335, pp. 299-326,
2019.
[10]. A. M. A. Brifcani and J. N. Al-Bamerny, "Image
compression analysis using multistage vector
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16989
Published by: The Mattingley Publishing Co., Inc.
quantization based on discrete wavelet transform," in
2010 International Conference on Methods and
Models in Computer Science (ICM2CS-2010), 2010,
pp. 46-53: IEEE.
[11]. D. A. Zebari, H. Haron, D. Q. Zeebaree, and A. M.
Zain, "A Simultaneous Approach for Compression
and Encryption Techniques Using Deoxyribonucleic
Acid," in 2019 13th International Conference on
Software, Knowledge, Information Management and
Applications (SKIMA), 2019, pp. 1-6: IEEE.
[12]. A. M. A. Brifcani and W. M. A. Brifcani, "Stego-based-
crypto technique for high security applications,"
International Journal of Computer Theory and
Engineering, vol. 2, no. 6, p. 835, 2010.
[13]. D. A. Zebari, H. Haron, S. R. Zeebaree, and D. Q.
Zeebaree, "Multi-Level of DNA Encryption
Technique Based on DNA Arithmetic and Biological
Operations," in 2018 International Conference on
Advanced Science and Engineering (ICOASE), 2018,
pp. 312-317: IEEE.
[14]. A. Najih, S. Al-Haddad, A. R. Ramli, S. Hashim, and
M. A. Nematollahi, "Digital image watermarking
based on angle quantization in discrete contourlet
transform," Journal of King Saud University-
Computer and Information Sciences, vol. 29, no. 3, pp.
288-294, 2017.
[15]. Y. Zhang and Y. Sun, "An image watermarking method
based on visual saliency and contourlet transform,"
Optik, vol. 186, pp. 379-389, 2019.
[16]. D. Q. Zeebaree, H. Haron, A. M. Abdulazeez, and S. R.
Zeebaree, "Combination of K-means clustering with
Genetic Algorithm: A review," International Journal
of Applied Engineering Research, vol. 12, no. 24, pp.
14238-14245, 2017.
[17]. M. Kalita and S. Majumder, “A new steganographic
method using Contourlet Transform,” 2016 Int. Conf.
Signal Process. Commun. ICSC 2016, pp. 274278,
2016.
[18]. “Advanced Image Steganography Technique using
DWT and SVD with High PSNR,” vol. 7, no. 5, pp.
1223412236, 2017.
[19]. J. Zhu, H. Zhang, and X. Li, “INFORMATION
HIDING BASED ON GRAY [1] J. Zhu, H. Zhang,
and X. Li, ‘INFORMATION HIDING BASED ON
GRAY RELATION AND CONTOURLET
TRANSFORM,’ pp. 179–184, 2017.RELATION
AND CONTOURLET TRANSFORM,” pp. 179–184,
2017.
[20]. D. A. Zebari, H. Haron, S. R. Zeebaree, and D. Q.
Zeebaree, "Enhance the Mammogram Images for Both
Segmentation and Feature Extraction Using Wavelet
Transform," in 2019 International Conference on
Advanced Science and Engineering (ICOASE), 2019,
pp. 100-105: IEEE.
[21]. O. M. S. Hassan, A. M. Abdulazeez, and V. M.
TİRYAKİ, "Gait-based human gender classification
using lifting 5/3 wavelet and principal component
analysis," in 2018 International Conference on
Advanced Science and Engineering (ICOASE), 2018,
pp. 173-178: IEEE.
[22]. N. Menon and V. Vaithiyanathan, “A survey on image
steganography,” Proc. 2017 IEEE Int. Conf. Technol.
Adv. Power Energy Explor. Energy Solut. an Intell.
Power Grid, TAP Energy 2017, pp. 15, 2018.
[23]. M. Khader, A. Hadi, and A. Hudaib, "Covert
communication using port knocking," in 2016
Cybersecurity and Cyberforensics Conference (CCC),
2016, pp. 22-27: IEEE.
[24]. S. Jangid and S. Sharma, “High PSNR based video
steganography by MLC(multi-level clustering)
algorithm,” Proc. 2017 Int. Conf. Intell. Comput.
Control Syst. ICICCS 2017, vol. 2018-Janua, pp. 589
594, 2018.
[25]. H. C. Huang, J. Lin, and Y. Y. Lu, “Visual Secret
Sharing for Copyright Protection and Authentication
of Color Images,” Proc. - 2015 3rd Int. Conf. Robot.
Vis. Signal Process. RVSP 2015, pp. 151154, 2016.
[26]. A. Yershov and P. Rusakov, “Universal
Stegoconstructor in Context of Intellectual Property
Protection,” pp. 131–136, 2010.
[27]. S. Tyagi and H. V. Singh, “Digital Watermarking
Techniques for Security Applications,” 2016 Int.
Conf. Emerg. Trends Electr. Electron. Sustain. Energy
Syst., pp. 379382, 2016.
[28]. M. Sathik, “An Improved Invisible Watermarking
Technique for Image Authentication An Improved
Invisible Watermarking Technique for Image
Authentication,” no. January, 2015.
[29]. R. Patel and U. Shrawankar, “SECURITY ISSUES IN
SPEECH WATERMARKING FOR,” no. April 2013,
2014.
[30]. M. Keyvanpour, “Classification and Evaluation of
Watermarking,” pp. 7–9, 2017.
[31]. A. B. Kahng et al., “Watermarking Techniques for
Intellectual Property Protection,” pp. 776–781, 1998.
[32]. L. Chen and J. Zhao, “Contourlet-based image and
video watermarking robust to geometric attacks and
compressions,” Multimed. Tools Appl., vol. 77, no. 6,
pp. 71877204, 2018.
[32]. I. M. Zeebaree, D. Q. Zeebaree, and Z. A. Ayoub,
"FACE RECOGNITION USING STATISTICAL
FEATURE EXTRACTION AND NEURAL."
May - June 2020
ISSN: 0193-4120 Page No. 16979 - 16990
16990
Published by: The Mattingley Publishing Co., Inc.
[33]. V. Ananthaneni, “Hybrid Digital Image Watermarking
using Contourlet Transform ( CT ), DCT and SVD,”
vol. 2, no. 11, pp. 8593, 2017.
[34]. D. M. Abdulqader, A. M. Abdulazeez, and D. Q.
Zeebaree, "Machine Learning Supervised Algorithms
of Gene Selection: A Review," Machine Learning, vol.
62, no. 03, 2020.
... The size of the input has been minimized to the end layers. Through sequential layers, and features are extracted from the low-level to the high-level [18].  Convolutional layer: This layer-based CNN technique deals with convoluting each image as input with kernels (filters). ...
... A series of architectures of deep neural networks such as CNN's, Recurrent Neural Networks (RNNs), and Deep Neural Networks (DNNs) have been studied to help identify face emotions [30]. This system uses an end-to-end model to train a deep network structure with millions of parameters that automatically learn accurate features from massive data without the hand-made features [14], [40]. The in-depth features or activations may input conventional classification schemes [34], [37], [41]. ...
Article
Full-text available
Facial emotional processing is one of the most important activities in effective calculations, engagement with people and computers, machine vision, video game testing, and consumer research. Facial expressions are a form of nonverbal communication, as they reveal a person's inner feelings and emotions. Extensive attention to Facial Expression Recognition (FER) has recently been received as facial expressions are considered. As the fastest communication medium of any kind of information. Facial expression recognition gives a better understanding of a person's thoughts or views and analyzes them with the currently trending deep learning methods. Accuracy rate sharply compared to traditional state-of-the-art systems. This article provides a brief overview of the different FER fields of application and publicly accessible databases used in FER and studies the latest and current reviews in FER using Convolution Neural Network (CNN) algorithms. Finally, it is observed that everyone reached good results, especially in terms of accuracy, with different rates, and using different data sets, which impacts the results.
... Hilbert's wavelet change, which compares to the fanciful parts of the three-square, and the genuine four-wave wavelet Waves comprising of fourfold investigation signal. It can be caught on as an optimized genuine wavelet and advancement of complex wavelet, which has inexact consistency in change, copious stage data, restricted recurrence, etc. whereas keeping up the capacity to localize the time of the routine wavelet recurrence and channel plan utilizing Hilbert change a match of the two-fold tree structure, which Simple to realize [52], [53], [54], [55]. The proficiency of a watermarking strategy lies for the most part in its capacity to satisfy three prerequisites: strength, security and intangibility ...
Article
Wavelet transform (WT) for image processing is one of the most popular methods in the frequency domain, the information of images could be represented as a group based on this method. The aim of this paper is to provide a wide-ranging review of the survey found able on wavelet-based image processing applications approaches. This paper reviews the newly published works on applying waves to image processing depending on the analysis of multiple solutions. the wavelet transformation reviewed in detail including wavelet function, integrated wavelet transformation, discrete wavelet transformation, rapid wavelet transformation, DWT properties, and DWT advantages. After reviewing the basics of wavelet transformation theory, various applications of wavelet are reviewed and multi-solution analysis, including image compression, image reduction, image optimization, and image watermark. In addition, we present the concept and theory of quadruple waves for the future progress of wavelet transform applications and quadruple solubility applications. The main contribution of this paper will be beneficial for scholars to execute effective image processing applications approaches.
... The hidden particulars to be embedded can be some words, writer ‗s serial digits, organization logo, photos containing exceptional influence. These secret details are embedded in digital information (images, audio, and video) to uphold the security, data authentication, identification of possessor and copyright defense [9][10][11][12][13]. The image that is required to be embedded is called a watermark image and the image which carries the watermark is called host or original image. ...
Article
Full-text available
This paper proposes a watermarking method for grayscale images, in which lifting wavelet transform and singular value decomposition are exploited based on multi-objective artificial bee colony optimization to produce a robust watermarking method. Furthermore, for increasing security encryption of the watermark is done prior to the embedding operation. In the proposed scheme, the actual image is altered to four sub-band over three levels of lifting wavelet transform then the singular value of the watermark image is embedded to the singular value of LH sub-band of the transformed original image. In the embedding operation, multiple scaling factors are utilized on behalf of the single scaling element to get the maximum probable robustness without changing watermark lucidity. Multi-objective artificial bee colony optimization is utilized for the determination of the optimal values for multiple scaling components, which are examined against various types of attacks. For making the proposed scheme more secure, the watermark is encrypted chaotically by logistic chaotic encryption before embedding it to the host (original) image. The experimental results show excellent imperceptibility and good resiliency against a wide range of image processing attacks. Keywords: Encryption Image watermarking Lifting wavelet transform Multi-objective artificial bee colony optimization Multiple scaling factor SVD This is an open access article under the CC BY-SA license.
Article
Full-text available
Digital picture watermarking is employed to stay secret the proprietary info as a watermark within a digital image, to spot the possession. This method has relevancy to any or all pictures. Separate trigonometric function transform (DCT) is employed before inserting the watermark within the host image. The host picture is isolated into 8×8 non-covering hinders preceding DCT application, and therefore the watermark bit is inserted by dynamic distinction between DCT coefficients of contiguous squares. Arnold transform is employed even so disorderly encoding to feature 2-fold block safeguard to the watermark. 3 distinctive variations of the planned calculation are tried and stone-broke down. The reenactment results demonstrate that the planned set up is powerful to the overwhelming majority of the image making ready tasks like JPEG pressure, honing, trimming, middle separating, and so on. To approve the proficiency of the planned technique, the recreation results are contrasted and sure condition of-workmanship systems. The examination results represent that the planned set up performs higher as so much as power, security and imperceptivity. Given the advantages of the planned set up, it alright could also be used in applications like e-social insurance and telemedicine to smartly hide out electronic eudemonia records in therapeutic footage.
Conference Paper
Full-text available
Abstract—This study describes a representation of gait appearance for the purpose of person identification and classification. The gait representation is based on wavelet 5/3 lifting scheme simple features such as features extracted from video silhouettes of human walking motion. Regardless of its effortlessness, this may lead us to say that, the resulting feature vector contains enough information to perform well on human identification and gender classification tasks. We found out the recognition behaviors of different methods to total features over time functions under different recognition tasks. In addition to that, we provide results of gender classification based on our gait appearance features using a (C4.5 algorithm). So, the result of classification rate for CASIA - B gait databases is 97.98% and the result of recognition rate for OU-ISIR gait Database Large Population Dataset is 97.5%, these results have been obtained from gender classification data. Gait database demonstrates that the proposed method achieves better recognition performance than the most existing methods in the literature, and particularly under certain walking variations. Keywords—Gait Recognition, Lifting 5/3, C4.5 Algorithm, Principal Component Analysis (PCA)
Conference Paper
Breast cancer (BC) is a main killer disease for women and men. It can be cured and controlled only if it is detected at its early detection. BC initial identification can be realized by the help of computer support identification approaches. From the detailed study on previous researches, it is found that, there is no system producing high accuracy because of one or more reasons. Absence of effective preprocessing is the discussed reason that obstructs the detection accuracy of Computer-aided diagnosis (CAD) method. Noise removal and contrast enhancement are the two types of preprocessing. There is no system performs the preprocessing on mammogram image. This work is an attempt to develop an enhanced preprocessing method for CAD of breast cancer by incorporating suitable noise reduction and contrast enhancement methods in the conventional CAD system. Contrast enhancement after noise reduction double enhances the mammogram image and the proposed methods MSE value for the mammogram image mdb072 has been 1.44% reduced. Reduction in MSE increases the PSNR to 0.16%. Many mammogram images have been tested and the result shows that, increase in contrast, decrease in mean square error and increase in peak signal to noise ratio when comparing to existing methods
Article
For the purpose of enhancing the imperceptibility and the robustness of watermark, a new image watermarking method based on visual saliency and contourlet transform is proposed. In this algorithm, salient object detection and contourlet transform are operated separately on host image. After dividing the transformed low-pass sub-band into nonoverlapping blocks, the saliency values and the energy distribution of the block determine the quantization step-size of each block together. The logarithmic quantization index modulation is modified so as to gain the robustness against the amplitude scaling attack. Then, in each low-pass sub-band block, the maximum singular value is chosen to embed watermark bits using the modified logarithmic quantization index modulation (MLQIM). The watermarked image is obtained after carrying out the inverse contourlet transform. The results of experiments demonstrate that the presented algorithm possesses satisfactory imperceptibility and is superior to other common algorithms in terms of the robustness against various attacks.
Conference Paper
Abstract— Gene expression profiles could be generated in large quantities by utilizing microarray techniques. Currently, the task of diagnosing diseases relies on gene expression data. One of the techniques which helps in this task is by utilizing deep learning algorithms. Such algorithms are effective in the identification and classification of informative genes. These genes may subsequently be used in predicting testing samples’ classes. In cancer identification, the microarray data typically possesses minimal samples number with a huge feature collection size which are hailing from gene expression data. Lately, applications of deep learning algorithms are gaining much attention to solve various challenges in artificial intelligence field. In the present study, we investigated a deep learning algorithm based on the convolutional neural network (CNN), for classification of microarray data. In comparison to similar techniques such as Vector Machine Recursive Feature Elimination and improved Random Forest (mSVM-RFE-iRF and varSeIRF), CNN showed that not all the data have superior performance. Most of experimental results on cancer datasets indicated that CNN is superior in terms of accuracy and minimizing gene in classifying cancer comparing with hybrid mSVM-RFE-iRF. Keywords: Deep Learning; Convolutional Neural Network (CNN); Microarray Cancer Data; Classification;
Article
Storing and communicating secret and/or private information has become part of our daily life whether it is for our employment or personal well-being. Therefore, secure storage and transmission of the secret information have received the undivided attention of many researchers. The techniques for hiding confidential data in inconspicuous digital media such as video, audio, and image are collectively termed as Steganography. Among various media types used, the popularity and availability of digital images are high and in this research work and hence, our focus is on implementing digital image steganography. The main challenge in designing a steganographic system is to maintain a fair trade-off between robustness, security, imperceptibility and higher bit embedding rate. This research article provides a thorough review of existing types of image steganography and the recent contributions in each category in multiple modalities. The article also provides a complete overview of image steganography including general operation, requirements, different aspects, different types and their performance evaluations. Different performance analysis measures for evaluating steganographic system are also discussed here. Moreover, we also discuss the strategy to select different cover media for different applications and a few state-of-the-art steganalysis systems.