International Journal of Engineering Trends and Technology (IJETT) – Volume 31 Number 1- January 2016
Secrecy Data Transferring Using Genetic Operation and
Perform Image Mosaic in an Image Processing
Kovilapu Jagadheesh Babu1, Konni Srinivasa Rao2
1
Final M.Tech Student, 2Asst.professor
1,2
Dept of CSE, Sarada Institute of Science, Technology and Management (SISTAM), Srikakulam,
Andhra Pradesh
Abstract: Images are considered as one of the most
important medium of conveying information, in the
field of computer vision, by understanding images
the information extracted from them can be used for
other tasks. Image mosaic is the process of
partitioning a digital image into multiple segments.
Image denoising is done before the mosaic to avoid
the selection of falsely object for mosaic to segment
the image into multiple parts without loss of
information. The goal of mosaic is to change the
representation of an image into more meaningful
and easier to analyse. Image mosaic is basically
used to locate the objects and boundaries (lines,
curves, etc.) in images. Mosaic technique can be
classified into different types namely, Region Based,
Edge Based, Threshold Based etc. In this paper we
are proposed mainly three concepts for performing
generation of secret key, secrecy of transferring data
and also perform image mosaic process. By
implementing diffie Hellman key exchange protocol
we can generate shared key between the users. In
this paper we are using an encryption technique
using genetic operation for converting plain format
data into unknown format. After converting data into
cipher format we can put into image by using least
significant bit technique. After completion of data to
be hidden into image and perform mosaic technique
for segment image. In this paper we are using region
based technique for performing image mosaic
process. By implementing those concepts we can
provide more security of transferring data and also
improve the efficiency of network.
Keywords: Image mosaic, Security, cryptography,
Key Exchange Protocol, least significant bit
technique.
I. INTRODUCTION
Image Mosaicing technology is becoming more
and more popular in the fields of image processing,
computer graphics, computer vision and multimedia.
It is widely used in daily life by stitching pictures
into panoramas or a large picture which can display
the whole scenes vividly. For example, it can be
used in virtual travel on the internet, building virtual
environments in games and processing personal
pictures. In Image Mosaicing is firstly divided into
ISSN: 2231-5381
(usually equal sized) rectangular sections, each of
which is replaced with another photograph that
matches the target photo. When viewed at low
magnifications, the individual pixels appear as the
primary image, while close examination reveals that
the image is in fact made up of many hundreds or
thousands of smaller images. In image mosaicing
two input images are taken and this images are fused
to form a single large image. This merged single
image is the output mosaiced image.The first step in
Image Mosaicing is feature extraction. In feature
extraction, features are detected in both input images.
Image registration refers to the geometric alignment
of a set of images.
The different sets of data may consist of two or
more digital images taken of a single scene from
different sensors at different time or from different
viewpoints. In image registration the geometric
correspondence between the images is established so
that they may be transformed, compared and
analyzed in a common reference frame. This is of
practical importance in many fields, including
remote sensing, computer vision, medical imaging.
Registration methods can be loosely divided into the
following classes: algorithms that use image pixel
values directly, e.g., correlation
methods
[1];algorithms that use the frequency domain, e.g.,
Fast Fourier transform based (FFT-based) methods
[2];algorithms that use low level features such as
edges and corners, e.g., Feature based methods
[4];and algorithms that use high-level features such
as identified parts of image objects, relations
between image features, for e.g., Graph-theoretic
methods[3].The next step, following registration, is
image warping which includes correcting distorted
images and it can also be used for creative purposes.
The images are placed appropriately on the bigger
canvas using registration transformations to get the
output mosaiced image. The quality of the mosaiced
image and the time efficiency of the algorithm used
are given most importance in image mosaicing.
Before performing image mosaic we can stored
data into image. The storing data into image the
sender will perform encryption of data using genetic
operation. By performing encryption process the
sender will convert data into unknown format. After
converting data the sender will stored data into
http://www.ijettjournal.org
Page 45
International Journal of Engineering Trends and Technology (IJETT) – Volume 31 Number 1- January 2016
image using least significant bit technique. In this
paper we are using another concepts for generation
of shared key by using Diffe Hellmankey exchange
protocol. Using that key the sender will encrypt the
transferring message using encryption process using
genetic operation. After encryption the sender will
put data into image and perform mosaic of image
using region based technique. The sender will send
those parts to specified receiver and the receiver will
perform the reverse process. By performing reverse
of process we can get original data and original
image. The remaining concepts of this paper are as
follows. Section 2 is to specify related work of our
proposed system. Section 3 implementation
procedure of our proposed system. Section 4 is
conclusion of our proposed system. Section 5 is
reference of can be specify in this paper.
II.
RELATED WORK
In medical imaging, the large panoramic images
can help doctors to conduct comprehensive and
visual observation on the focus and the surrounding
parts, image mosaicking technology has become a
research hot spot in the domain of medical image
processing. The purpose is to make several images
located in different space positions match and
mosaic a complete new image. Retinal images are
used to diagnose and monitor the progress of
diseases, including diabetic retinopathy which is one
of the leading causes of blindness, age-related
mascular degeneration, and glaucoma [4]. However,
the angle of a retinal photograph is only 30 to 60
degrees. Two or more retinal photographs are
needed to capture a general view of entire retina.
Building a mosaic image from a sequence of partial
views is a powerful means of obtaining a complete,
nonredundant view of a scene. Another application
in which mosaics are used is ophthalmology[5]. A
seamless mosaic formed from multiple fundus
camera images aids in diagnosis, provides a means
for monitoring the progress of diseases, and may be
used as a spatial map during surgical treatment. This
section discusses some of the literature present in the
retinal image mosaicing.
Can et.al [6] describes a robust hierarchical
algorithm for fully-automatic registration of a pair of
images of the curved human retina photographed by
a fundus microscope. Accurate registration is
essential for mosaic synthesis, change detection, and
design of computer-aided instrumentation. Central to
the algorithm is a 12-parameter interimage
transformation derived by modeling the retina as a
rigid quadratic surface with unknown parameters,
imaged by an uncalibrated weak perspective camera.
The parameters of this model are estimated by
matching vascular landmarks extracted by an
algorithm that recursively traces the blood vessel
ISSN: 2231-5381
structure. The parameter estimation technique,
which could be generalized to other applications, is a
hierarchy of models and methods: an initial match
set is pruned based on a zeroth order transformation
estimated as the peak of a similarity-weighted
histogram; a first order, affine transformation is
estimated using the reduced match set and leastmedian of squares; and the final, second order, 12parameter transformation is estimated using an
Mestimator initialized from the first order estimate.
This hierarchy makes the algorithm robust to
unmatchable image features and mismatches
between features caused by large interframe
motions. Before final convergence of the Mestimator, feature positions are refined and the
correspondence set is enhanced using normalized
sum-of-squared differences matching of regions
deformed by the emerging transformation. Can et.al
proposed, an extension of the above algorithm[7] is
discussed. Two novel methods are introduced in this
paper.
The first is a linear, non-iterative method
for jointly estimating the transformations of all
images onto the mosaic. This employs constraints
derived from pairwise matching between the nonmosaic image frames. It allows the transformations
to be estimated for images that do not overlap the
mosaic anchor frame, and results in mutually
consistent transformations for all images. This
means the mosaics can cover a much broader area of
the retinal surface, even though the transformation
model is not closed under composition. This
capability is particularly valuable for mosaicing the
retinal periphery in the context of diseases such as
AIDS/CMV. The second is a method to improve the
accuracy of the pairwise matches as well as the joint
estimation by refining the feature locations and by
adding new features based on the transformation
estimates themselves. The physician can now choose
any image as the anchor image, and need not worry
about identifying a single image that will overlap all
others.
III.PROPOSED SYSTEM
Image mosaic is generally enhancing the
granular information in images for viewers and
offering improved input for different automated
image processing techniques. The primary aim of
segmenting an image is to enhance quality and
suitability for presenting the image for a specific
given task in front of an observer. Clustering or
mosaic is a process of partitioning of color or grey
scale image into various set of segments. The major
benefit of Image mosaic is to provide a convenient
way of image representation and analysis. In this
process, whole image is distributed and categorized
in to different group of image sectors. These sectors
consist of similar image level on a pixel basis. Thus,
http://www.ijettjournal.org
Page 46
International Journal of Engineering Trends and Technology (IJETT) – Volume 31 Number 1- January 2016
displaying same level pixels prominent and making
the image outlines brighter which can be used for
further analysis. Application of image mosaic is vast
and could be used in many fields. It enhances clarity
in the algorithms and innovating new methods of
analysis is interested region and supports better
object recognition. There are number of various
image mosaic algorithms which are currently used
and applied for different purposes. In this paper we
are also proposed other concept for transferring data
into image. Before performing image mosaic process
the sender will perform encryption process for data
and that cipher formatted data put into image. After
that the sender will use the region based image
mosaic technique we can segment image into
number of parts. The sender will send those parts to
specified receiver and receiver will receive parts will
generate single image. After generating single image
the receiver will get data from the image and decrypt
cipher format data. So that the receiver completes
decryption process it will get original data and
original image. By implementing those concepts we
can propose four concepts in this papers i.e. shared
key generation, data encryption and decryption
process, least significant bit and region based image
mosaic technique. In this paper the first concept is
generation of shred key by using Diffe Hellmankey
exchange protocol. The implementation procedure of
Diffe Hellmanis as follows.
After generating shared key those keys are same for
both users. By using that shared key the sender will
encrypt transferring message. The encryption
process genetic operation technique is as follows.
Encryption Process using genetic operation:
In this module the sender will encrypt the
transferring message using genetic operation
technique. The implementation of encryption
process is as follows.
Step 1: Consider the message to be encrypted as
‗THIS‘.
Step 2: Calculate the numeric value of the first
alphabet (the position in which it reside in the
alphabetic sequence). The numeric value of ‗T‘ is
20.
Step 3: Convert 20 to binary. Binary of 20 is 10100
Step 4: Select a default (any randomly generated)
chromosome as the second parent for crossover. I
have taken the default chromosome as 11111,
Step 5: A crossover point is randomly selected and
crossover is performed. Here the crossover point is
selected as 2. The crossover is performed as follows:
Parent 1
Diffe Hellman Key Exchange Protocol:
In this module the sender and receiver will
generate same shred key for encryption and
decryption of transferring message. The generation
of shared key is as follows.
10100
Parent 2
11111
COP = 2
1.
2.
3.
4.
5.
6.
7.
The sender and receiver will agree to use
modulus P and base G.
The sender will choose private key a and
calculate public key by using following
formula.
Public key= Ga mod P
After generating public the sender will send
that public key to receiver.
The receiver will retrieve public key and
choose private key.
Using that private the receiver will generate
public by using same formula and send that
public to sender.
The sender will retrieve receiver public key
and generate shared key by using following
formula.
Shared key= receiver publica mod P
The receiver also generate shared key by
using following formula.
Shared key= sender publickeya mod P
ISSN: 2231-5381
New Child 1 0 1 1 1
Step 6: Two values are obtained from the above
step. New child – 10111 Left out value – 11100 (this
value is used during decryption). Decimal
representation of the left out value is 28.
Step 7: A mutation point is randomly selected and
mutation is performed to invert any particular bit of
the chromosome. Here the mutation point is selected
as 4
10111
10101
Step 8: Now T is represented as ‗10101‘. Convert
this binary value to decimal, which is ‗21‘. Convert
the number to alphabet. The alphabet corresponding
to 21 is ‗U‘. Thus ‗T‘ will be replaced by ‗U‘.
Note: If any decimal value crosses 26, then we can
repeat the alphabets and can represent the alphabets
http://www.ijettjournal.org
Page 47
International Journal of Engineering Trends and Technology (IJETT) – Volume 31 Number 1- January 2016
with a ‗*‘. For example if the decimal value btained
is 28, then we can represent it in alphabets as B*.
During encryption, for every word the default
chromosome, crossover point and the mutation point
varies. The cipher text corresponding to ‗THIS‘ is
{U28,M24,M25,U27}. For decryption the cipher
text along with 3124 is send to the receiver, where
31 is the decimal representation of the second parent
(11111), 3 is the crossover point and 4 is the
mutation point.
After completion of encryption process the
sender will convert cipher format data into binary
format. By taking the cipher formatted binary the
sender will put into image by using least significant
bit technique. The implementation procedure of least
significant bit technique is as follows.
Least significant bit technique:
In this module the sender will take binary
formatted data of cipher data and image pixel values.
The sender will take transferring image and convert
into binary format. After conversion of binary the
sender will take cipher format binary data and put
into binary pixel value of least significant bit. The
sender will take that stored binary pixel values and
again generate data hide image.
28 – 11100
Step 2: From 3124, it‘s known that ‗4‘ is the
mutation point,
so invert the fourth bit in U.
U
10101
Bit inverted
10111
Step 3: Decrypt the crossover operation. From 3124,
it‘s known that crossover point is ‗2‘.
10111
28(value associated with U)
1100
Pair the similar shaded bits.
10100
11111
Step 4: Convert both the binary values to decimal.
10100 - 20
11111 – 31
The alphabetic value corresponding to 20 is ‗T‘.
This is the first letter of the plain text. From ‗3124‘
it‘s already known that ‗31‘ is the default parent.
The value obtained from reverse crossover matches
with the value of default parent in 3124‘, thus
providing verification
The receiver will get original plain formatted data
and also get original image without loss of color.
Region based image mosaic technique:
In this module the sender will segment data hide
image into number of parts by using region based
image mosaic technique. In this technique we are
segment image using region based. In this paper we
are taking some amount of pixel will be consider in a
region and split that region into one segment. After
that take another part from previous region of some
pixel values and next region of original image.
Likewise we can segment image into specified parts
and those segment will be send to receiver.
The receiver will receive parts from the sender
and generate single image by applying reverse of
process of region based image mosaic technique.
The completion of generating data hide image the
receiver will convert image into binary format. After
converting image into binary format the receiver will
get all binary formatted cipher data from the image.
The receiver will get all binary formatted cipher data
and convert into plain format by using decryption
process using genetic operation. The implementation
of decryption process is as follows.
Decryption process using Genetic Operation:
Step 1: Take the first letter U28. Convert both U
(decimal
value 21) and 28 to binary.
U - 10101
ISSN: 2231-5381
IV. CONCLUSIONS
This paper presents an efficient technique for
performing image mosaic and also provides privacy
of transferring data into image. Before performing
image mosaic process the sender will enter
transferring and convert into unknown format by
using cryptography technique. In this paper we are
using encryption and decryption of data using
genetic operation to be convert data into unknown
format. After completion encryption process the
sender will stored cipher format data into image
using least significant bit technique. The completion
data hiding into image the sender will perform image
segment process by using region based image
mosaic technique. After completion of image
mosaic the sender will send those parts to specified
receiver. The receiver will receive those parts and
combine parts will generate single image. The
receiver will take data hide image and convert into
binary format. After converting binary format the
receive will get cipher formatted binary data from
the image. The receive will get data form image and
get plain format data using decryption process using
genetic operation technique. After getting original
data the receiver will get data and also get original
image. By implementing those concepts we can
improve more efficiency and provide privacy of
transferring message.
http://www.ijettjournal.org
Page 48
International Journal of Engineering Trends and Technology (IJETT) – Volume 31 Number 1- January 2016
V. REFERENCES
[1]. D. I. Barnea; and H. F. Silverman,”A class of
algorithms for fast digital registration,” IEEE Trans.
Comput, vol.C-21, pp.179-186, 1972.
[2]. C. D. Kuglin and D .C. Hines,” The phase
correlation image alignment method”,in Proc. IEEE
Int. Conf. Cybernet. Society, New York, NY, pp
163-165, 1975.
[3]. Lisa G. Brown. A survey of image registration
techniques. ACM Computing Surveys, 24(4); pp
325-376, December 1992.
[4]. J. B. A. Maintz and M. A. Viergever, “A survey
of medical image registration,”Med. Image Anal.,
vol. 2, no. 1, 1998, pp. 1–36
[5]. A Can, C.V.Stewart, B.Roysam, H.L.
Tanenbaum, “A Feature-Based Technique for Joint,
Linear Estimation of High-Order Image-to-Mosaic
Transformations: Application to Mosaicing the
Curved Human Retina”, IEEE Conference on
Computer Vision and Pattern Recognition, vol. 2,
pp: 585 - 591 , 2000
[6] Ali Can, Charles V. Stewart, Badrinath Roysam,
“A Feature-Based, Robust, Hierarchical Algorithm
for Registering Pairs of Images of the Curved
Human Retina”, IEEE Transactions on Pattern
Analysis and Machine Intelligence, vol.24, No.3,
pp.347-364,Maech 2002.
[12] M. Huang, W. Yu, and D. Zhu, “An improved
image segmentation algorithm based on the Otsu
method,” in Proc. 13th ACIS Int. Conf Softw. Eng.,
Artif. Intell., Netw. Parallel Distrib. Comput., Aug.
2012, pp. 135–139.
BIOGRAPHIES:
Kovilapu
Jagadheesh
Babu is student in M.Tech
(SE) in Sarada Institute of
Science Technology and
Management, Srikakulam,
Andhra Pradesh. He has
received
his
M.C.A
PGRRCDE,
Osmania
University,
Hyderabad,
and
Telengana.
His
interesting
areas
are
network security, image processing and web
technologies.
Konni SrinivasaRao is
working as an Assistant
Professor
in
Sarada
Institute
of
Science,
Technology
and
Management, Srikakulam,
Andhra
Pradesh.
He
received his M.Tech (cse)
from Pragati engineering
college,Kakinada,
East
Godavari,Andhra Pradesh.
His research areas include Network Security and
Computer Networks
[7]. S. Battiato, G. Di Blasi, G. M. Farinella and G.
Gallo, “A Survey of Digital Mosaic Techniques”,
Eurographics Italian Chapter Conference ,pp. 129135,2006.
[8]. Inampudi,R.B.,” Image mosaicing” in
International Conference on Geoscience and Remote
Sensing Symposium Proceedings,vol.5,pp 23632365,1998
[9]. Battiato, G. Di Blasi, G. M. Farinella, and G.
Gallo, “Digital mosaic framework: An overview,”
Eurograph.—Comput. Graph. Forum , vol.26, no. 4,
pp. 794–812, Dec. 2007.
[10]. C. H. Bindu and K. S. Prasad, “An efficient
medical image segmentation using conventional
OTSU method,” Int. J. Adv. Sci. Technol., vol. 38,
pp. 67–74, Jan. 2012.
[11]. M. Spann and R. Wilson, “A quad-tree
approach to image segmentation which combines
statistical and spatial information,” Pattern
Recognit., vol. 18, nos. 3–4, pp. 257–269, 1985.
ISSN: 2231-5381
http://www.ijettjournal.org
Page 49