International Journal of Communication and Computer Technologies

Volume 04 No. 9 Issue: 02 March 2016

ISSN NUMBER : 2278-9723

High Speed Image Searching For Human Gait Feature

Selection
Ganga Devi,2Reena,3Priya,4Yuvarani,UG Students, AVS College of Technology,
5
M.Kavitha, Assistant Professor, AVS College of Technology,
6
A.Surendar, Assistant Professor, KSR College of Engineering.

AbstractIn this paper, a new patch distribution

feature (i.e., referred to as Gabor-PDF) is used for human
gait recognition. We represent each gait energy image
(GEI) as a set of local augmented Gabor features, which
concatenate the Gabor features extracted from different
scales and different orientations. A global Gaussian
mixture model (GMM) (i.e., referred to as the universal
back- ground model) with the local augmented Gabor
features from all the gallery GEIs; then, each gallery or
probe GEI is further expressed as the normalized
parameters of an image-specific GMM adapted from the
global GMM. Observing that one video is naturally
represented as a group of GEIs, also a new classification
method
called
locality-constrained
group
sparse
representation (LGSR) to classify each probe video by
minimizing the weighted l1,2 mixed-norm-regularized
reconstruction error with respect to the gallery videos. In
contrast to the standard group sparse representation
method that is a special case of LGSR, the group sparsity
and local smooth sparsity constraints are both enforced in
LGSR. The same LGSR algorithm is used for both color
images and for content based image retrieval (CBIR).
Index TermsHuman gait recognition, LGSR, CBIR.

1. INTRODUCTION
Computer vision is a field that includes
methods for acquiring, processing, analyzing, and
understanding images. A theme in the development
of this field has been to duplicate the abilities of
human vision by electronically perceiving and
understanding an image. Computer vision has also
been described as the enterprise of automating and
integrating a wide range of processes and
representations for vision perception. The Gait
analysis and recognition is one of the important
field in computer vision.
1.1 HUMAN IDENTIFICATION
Authentication from an information security
point-of-view is the process of confirming the
identity of a human being. Biometric authentication
uses one of several different biometric features to
determine a persons identity. Some of the most
frequently used features today are fingerprints,
face, voice and iris.

It is the first type of biometrics came into form

in 1890, created by an anthropologist named
Alphonse Bertillon. The method consisted of
identifying people by taking various body
measurements like a persons height, arm length,
length and breadth of the head, the length of
different fingers, the length of forearms, etc. using
calipers. However, the methodology was unreliable
as non-unique measurements allowed multiple
people to have same results, decreasing the
accuracy and hence is no longer used.
Finger print recognition or authentication
refers to the automated method of verifying a
match between two human fingerprints for
identifying and verifying their identity. A problem
confronting fingerprint matching is the lack of
reliable algorithms for extracting minutiae. Existing
algorithms result in spurious minutiae because of
an inability to cope with anomalies introduced by
factors such as scars, over-inking, and sweat. For
this reason human intervention is generally needed
in order to check that the fingerprint classification
is correct.
A face recognition system is a computer
application used for automatically identifying a
person from a digital image or digital video frame.
One way to do this is by comparing selected facial
features from the image and facial database. One of
the main problems that must be overcome in face
recognition systems is to remove redundant
sampling
to
reduce
the
dimensionality.
Sophisticated preprocessing techniques are required
to attain the best results.
The term voice recognition refers to finding
the identity of "who" is speaking, rather than what
they are saying. Recognizing the speaker can
simplify the task of translating speech in systems
that have been trained on specific person's voices or
it can be used to authenticate or verify the identity
of a speaker as part of a security process. The main
problem being acoustic features can be Misspoken
or misread phrases, the human voice's tremendous

Volume 04 No.9 Issue: 02

International Journal of Communication and Computer Technologies

Page 4051
www.ijccts.org

International Journal of Communication and Computer Technologies

Volume 04 No. 9 Issue: 02 March 2016
ISSN NUMBER : 2278-9723

variability, due to colds, aging, and simple

tiredness. It can be captured surreptitiously by a
third party and replayed.
Iris recognition is an automated method
of biometric identification that uses mathematical
pattern-recognition techniques on video images of
the irides of an individual's eyes, whose complex
random patterns are unique and can be seen from
some distance.
Retina Recognition technology uses
infrared scanning and compares images of the
blood vessels in the back of the eye, the choroidal
vasculature. The eyes inherent isolation and
protection from the external environment as an
internal organ of the body is a benefit. No two
retinas are the same, even in identical twins. Retina
scan is used in high-end security applications like
military installations and power plants.
DNA recognition employs Deoxyribo
Nucleic Acid, which is the one-dimensional
ultimate unique code for ones individuality.
Identify information from every cell in the body in
a digital form. It is not yet fully automated, not fast
and expensive. Theoretical limitation is that
Identical twins have the same DNA.
Gait analysis is the systematic study of animal
locomotion, more specific as a study of human
motion, using the eye and the brain of observers,
augmented by instrumentation for measuring body
movements, body mechanics, and the activity of the
muscles. Gait analysis is used to assess, plan, and
treat individuals with conditions affecting their
ability to walk. Unlike other biometric features
such as iris, faces, palm and fingerprint, the
advantages of gait include: 1) gait can be collected
in a non-contactable, non-invasive, and hidden
manner; 2) gait is the only perceptible biometric at
a distance.
Advances in data storage and image acquisition
technologies have enabled the creation of large
image datasets. In order to deal with these data, it is
necessary to develop appropriate information
systems to efficiently manage these collections In
Content-Based Image Retrieval (CBIR) systems
image processing algorithms (usually automatic)
are used to extract feature vectors that represent

image properties such as color, texture, and shape.

In this approach, it is possible to retrieve images
similar to one chosen by the user (query-byexample). One of the main advantages of this
approach is the possibility of an automatic retrieval
process, contrasting to the effort needed to annotate
images.

2. LITERATURE SURVEY
Biometrics research is a hot topic because of
the demanding requirements for automatic human
authentication and authorization in computer
systems. Gait recognition is a subfield of
biometrics which depends upon the walking style
of the human individual. It has the advantage (over
other biometrics) of being unobtrusive and distance
recognition.
Psychological research says that human can
identify persons by locomotion from other patterns,
based on genders, direction of motion and weight
carrying condition. The baseline algorithm
considers some covariates such as viewing angle,
shoe type, walking surface, carrying condition and
time [12]. Some problems such as shadow removal,
moving background, walking surface, clothing etc
cannot be removed using the baseline algorithm.
The Gait recognition is divided into two
categories as model free approach and model based
approach. Model free approach does not follow any
model scheme. It is based on body shape. Model
based approach is based on static parameters (e.g.,
size ratio of different body parts) and dynamic
parameters (e.g., stride length and speed) [2]. The
shadow effect in images is removed by finding the
quadrant in which shadow falls and sampling the
intensity and categorize the colour characteristics
[2]. Still moving background, walking surface,
clothing problem cannot be removed. A Gaitrecognition technique that recovers static body and
stride parameters of subjects as they walk is
presented. A simplest neighboring algorithm is
proposed for analyzing the joint trajectory on time
analysis for dynamic parameters [3]. Gait
recognition using only the trajectories of lower
body joint angles projected into the walking plane.
A simple method given by Collins et al uses 2D
silhouettes extraction for human gait to avoid
clothing colour and texture problem. Gait cycle
analysis serves two important functions. First, it

Volume 04 No.9 Issue: 02

International Journal of Communication and Computer Technologies

Page 4052
www.ijccts.org

International Journal of Communication and Computer Technologies

Volume 04 No. 9 Issue: 02 March 2016
ISSN NUMBER : 2278-9723

determines the frequency and phase of each

observed gait sequence, allowing us to perform
dynamic time warping to align sequences before
matching. Secondly, it provides data reduction by
summarizing the sequence with a small number of
prototypical key frames [4]. Several temporal
alignment techniques (e.g., the simple temporal
correlation, Fourier analysis dynamic time
wrapping and Hidden Markov Models (HMMs))
have been proposed to exploit the dynamic
information [4]. The drawback being it is sensitive
to view point dependency.
To address the problem of the lack of training
templates, a novel approach for human recognition
by combining statistical gait features from real and
synthetic templates [16]. It directly compute the
real templates from training silhouette sequences,
and generate the synthetic templates from training
sequences by simulating silhouette distortion. A
statistical approach for learning effective features
from real and synthetic templates was proposed.
Mismatch in identifying male and female
individuals are seen in this method. Spatiotemporal gait representation called gait energy
images [GEI] is proposed by Han et al uses
principal component analysis for dimensional
reduction, [5]. This leads to appearance based
approach which has better performance than model
based approach. In the common approaches that
only employ the silhouette shape similarity, the
binary silhouettes over one Gait cycle are averaged
such that each gait video containing a number of
Gait cycles is represented by a set of gray-level
average silhouette images [i.e., gait energy images
(GEIs)] [5]. Chen, Yunhong [5] proposed a new
method for gender recognition via gait silhouettes.
For this they used radon transform and Relevant
Component Analysis (RCA). Radon Transform is
applied to obtain gait templates and RCA is
employed on the radon transformed templates to
get a maximum likelihood estimation of the within
class covariance matrix. They calculated
Mahalanobis distances and measured gender
dissimilarity in recognition. The Nearest Neighbor
(NN) classifier is adopted to determine whether a
sample in the Probe Set is male or female [14]. The
classical dimension-reduction techniques Principal
Component Analysis
(PCA) and Linear
Discriminant Analysis (LDA) [5], [6] have also
been applied to acquire an efficient and

discriminant representation before formally

conducting classification, in which each GEI is
represented as a lengthy vector in the highdimensional space. The purpose of PCA training is
to obtain several principal components to
rerepresent the original gait features from a highdimensional measurement space to a lowdimensional eigenspace. In General tensor
discriminant analysis the averaged gait image is
decomposed by Gabor filter to give a new
representation, which is suitable for recognition.
[6].
By representing each GEI as a set of local
Gabor features, Huang et al. [7] have recently
proposed an image-to-class distance for human gait
recognition by directly calculating the distance
from one probe GEI to all the gallery images
belonging to a certain class. To improve the
scalability, researchers aim at obtaining nonlinear
feature representations that work better with linear
classifiers. In particular, Yang et al proposed a
metod where sparse coding (SC) was used instead
of VQ to obtain nonlinear codes. dimensional
signals [8]. While these successes in classical
signal processing applications are inspiring, in
computer vision. However, the reference samples
are treated as independent data points in the above
SR-based methods. When the reference samples
and the query samples are organized as groups,
group sparse representation (GSR)-based methods
[8].
The drawback being the regularization is not
smooth and computationally expensive. Yu et al.
empirically observed that SC results tend to be
local nonzero coefficients are often assigned to
bases nearby to the encoded data. They suggested a
modification to SC, called Local Coordinate
Coding (LCC), which explicitly encourages the
coding to be local, and theoretically pointed out
that under certain assumptions locality is more
essential than sparsity, for successful nonlinear
function learning using the obtained codes. Modern
databases now a days having the contents in the
form of images and so there is a need for such a
system which can retrieve similar image on the
basis of content-based search capabilities. These
phenomena led to the implementation of many
content-based image retrieval systems (CBIR).
However, there are many problems faced in
designing such a retrieval system. The most basic

Volume 04 No.9 Issue: 02

International Journal of Communication and Computer Technologies

Page 4053
www.ijccts.org

International Journal of Communication and Computer Technologies

Volume 04 No. 9 Issue: 02 March 2016
ISSN NUMBER : 2278-9723

issue is how to measure the similarity in terms of

content.Any one of the following approaches can
be adopted to solve the problem (1) Take the global
image properties or (2) Take the object level
semantics into account. A New approach for image
retrieval technique called Coefficient of correlation
is proposed to improve retrieval performance, [10]
and reduce the extraction search times. The
techniques are tested both generally for multicomponent images and particularly for isolated
color and texture. Finally, matching is performed
between the test image and the object image and
quality of matching is measured. Histogram [16] is
one of the simplest image features. Despite being
invariant to translation and rotation about viewing
axis, lack of inclusion of spatial information is its
major drawback. In a different way of
incorporating spatial information into the colour
histogram, colour coherence vectors (CCV) [16],
was proposed. Each histogram bin is partitioned
into two types, i.e., coherent, if it belongs to a large
uniformly-colored region, or incoherent, if it does
not. Due to its additional spatial information, it has
been shown that CCV provides better retrieval
results
than
the
histograms.
To obtain a Wabor filter bank with orientations and
S scales, the twodimensional wabor function is dila
ted and rotated appropriately by setting the paramet
ers of the Wabor function [15]. Various techniques
based on generalized Hough transform and Fourier
descriptors have been reported in the literature for
shape and object boundary detection. A review of
methods for shape comparison has been reported
in. Active contour model called snake has been
used in [12] for interactive interpretation, where
user imposed constraint forces guide the snake to
feature of interest. Many variations based on active
contour methods have been found in literature. The
boundary detection precision of active contour
based methods is generally sensitive to seed-points
or seed-contours, if not provided properly, snakes
may not converge to true object boundaries. Many
relevance feedback techniques have been proposed
in literature to bridge the semantic gap by
specifying positive and negative feed backs given
by the user for refinement of results. A relevance
feedback based interactive image retrieval approach
to address issues of semantic-gap and subjectivity
of human perception of visual contents was
introduced
in
which
showed
significant

improvement in the results [13]. Dong xu et al [11]

recently proposed Marginal Fisher Analysis (MFA)
for human gait recognition, first present a direct
application of MFA, then inspired by recent
advances in matrix and tensor-based dimensionality
reduction algorithms, present matrix-based MFA
for directly handling 2-D input in the form of graylevel averaged images. For CBIR, it deal with the
relevance feedback problem by extending MFA to
marginal biased analysis, in which within-class
compactness is characterized only by the distances
between each positive sample and its neighboring
positive samples [11]. A new patch distribution
feature (PDF) (i.e., referred to as Gabor-PDF) for
human gait recognition. This represent each gait
energy image (GEI) as a set of local augmented
Gabor features, which concatenate the Gabor
features extracted from different scales and
different orientations together with the XY
coordinates. In contrast to the existing PDF (i.e.,
referred to as Discrete Cosine Transform PDF
(DCT-PDF)] for face recognition, in which each
face image is represented as a set of DCT features
extracted from the local patches, newly proposed
Gabor-PDF can achieve much better performance
for human gait recognition [1]. Dong xu et al
propose a new classification method called localityconstrained group sparse representation (LGSR) to
classify each probe video by minimizing the
weighted
l1,2
mixed-norm-regularized
reconstruction error with respect to the gallery
videos.
3. PROPOSED SYSTEM
In existing system the algorithm is not used
for colour images and also for retrieval of data. In
the proposed system the gait images for both colour
and grey level are obtained from the silhouette
images. The norm equalization are done using
LGSR algorithm. The same algorithm is used for
CBIR process in order to retrieval the required gait
image.
In this paper Gait features are extracted and
searched in the CBIR database for getting the
Matched Gait images using LGSR .This proposal
not only work for GEI images but also for natural
human images. The accuracy is improved by using
Gabor PDF. In this paper silhouettes images are
obtained for both colour and GEI images,
segmented and features are extracted and

Volume 04 No.9 Issue: 02

International Journal of Communication and Computer Technologies

Page 4054
www.ijccts.org

International Journal of Communication and Computer Technologies

Volume 04 No. 9 Issue: 02 March 2016
ISSN NUMBER : 2278-9723

classification is done to get a higher ranking in

which it get matched for getting the matched
images. Gait Energy Image (GEI) is the sum of
images of the walking silhouette divided by the
number of images. GEI is a useful representation
with superior selective power and strength against
segmental errors. The GEI that are

Figure : Gait cycle

Figure: Block Diagram
got from a video that has been converted into
frames or already in frame format are taken and
edge detection and thersholding are applied in order
to get the segmented image with good boundary.
The edging technique can be any one of the edging
format as a result it should give a clear and fine
edge detected image from the given input image.
The matched gait images are given to large
database in order to retrieve them and can be used
for analysis. As shown in the block diagram
whenever a probe video is entered for extraction it
is compared with the gallery video.
Once the features are matched the matched gait
images that are obtained are given to CBIR
database in which the input image is compares with
the database images and similarity is obtained.
Once a match if found the image is retrieved and
displayed. The most important data for gait analysis
is its gait cycles. From that individual gait images
called the silhouette images for colour and GEI
images are got. This is done by edge detection .The
obtained images are analysed using its Gait cycle
includes from start of walking position to ending of
the walking position(it may be jumping, running
etc) including the height, hand swings, leg
movement, carrying condition, stride length and
view angles of the gait images. This gives the
segmented images.

The segmentation involves getting the

outline of the image from a given video by using
different static and dynamic parameter and
identifying the gait from the video set. This makes
the extraction easier and classification in an
accurate way for gaits. After classification the
position or ranking in terms of its value are
obtained for the gait image. These positions or
ranks are compared and when a match happens it
stops searching the further sets of gait in the videos.
The ranking may depend upon scale and orientation
of the gait images.
3.1. GABOR FEATURE EXTRACTION
The Gabor wavelet feature has been
demonstrated to be an effective feature for human
gait recognition a tensor subspace learning method
by representing the Gabor-filtered GEIs as higher
order tensors directly calculated the image-to-class
distance for human gait recognition by representing
each GEI as a set of Gabor features. A new PDF
(i.e., referred to as Gabor-PDF) to characterize the
distribution of Gabor features extracted from each
GEI.
3.2. LGSR CLASSIFIER
Most existing human gait recognition
methods employ the simplistic nearest neighbor
classifier for classification. Inspired by the recent
success of SR-based methods for various computervision applications, a new classification method
called LGSR for human gait recognition is given.
The pioneering work to classify face images by
minimizing the l1 norm-regularized reconstruction
error, in which it seeks an SR for only a single test

Volume 04 No.9 Issue: 02

International Journal of Communication and Computer Technologies

Page 4055
www.ijccts.org

International Journal of Communication and Computer Technologies

Volume 04 No. 9 Issue: 02 March 2016
ISSN NUMBER : 2278-9723

image. In the context of human gait recognition, we

need to classify each probe video with multiple
GEIs. To utilize effectively the intrinsic group
information from multiple GEIs within each video,
we treat each probe/gallery video as one group of
GEIs and propose a new classification method
called LGSR. In contrast to the standard GSR
method that is a special case of LGSR, Enforcing
both the group sparsity and local smooth sparsity
constraints in LGSR by minimizing the weighted
mixed l1,2 norm-regularized reconstruction error.
Once we obtain the optimal reconstruction
coefficient, we can use two classification methods
based on different criteria to classify the probe
video. The LGSR algorithm is given by
2
1
yj - X sj + l sj
2
1
2
2
1
LLC : s j* = argsj min y j - X s j + l d j Q s j
2
2

displays the result with high accuracy. The time

taken for searching the image is greatly reduced by
using this algorithm. The accuracy is improved by
Gabor PDF. A very few detail is enough to do this
action.
4.

RESULT AND DISCUSSION

The system is tested and implemented using

MATLAB software. By using the software source
code was developed and input was got and the gait
image was obtained which is further given for
processing for the retrieval of the images in the
CBIR database by using the LGSR algorithm.

SR : s j* = argsj min

2
2

Figure : Loading of the gait video.

Figure : Gait classifications

3.3 CBIR BLOCK

Once the features are matched in the feature
matching comparator the gait image is obtained and
given to the control unit. The control unit is nothing
but our CBIR systems. In this unit the gait image to
be searched is given to the CBIR database. Once
the image is given it starts searching the required
matched images corresponding to the query image.
The same LGSR algorithm is used to retrieve the
image. When match occurs it stops the search and

Figure : Gait not matched

Volume 04 No.9 Issue: 02

International Journal of Communication and Computer Technologies

Page 4056
www.ijccts.org

International Journal of Communication and Computer Technologies

Volume 04 No. 9 Issue: 02 March 2016
ISSN NUMBER : 2278-9723
[6] D. Tao, X. Li, X. Wu, and S. Maybank, General
tensor discriminant analysis and gabor features for gait
recognition, IEEE Trans. Pattern Anal. Mach. Intell.,
vol. 29, no. 10, pp. 17001715, Oct. 2007.
[7] Y. Huang, D. Xu, and T. J. Cham, Face and human
gait recognition using image-to-class distance, IEEE

Figure : Matched and Retrieved Gait

5.

CONCLUSION
ENHANCEMENT

AND

FUTURE

Reduced details requirement which refers by

having small requirement of the gait feature it is
possible to get the gait of the person. Distance
recognition in which there is the possibility that
gait feature can be got by distance recognition. In
future this can be developed into powerful
Biometric systems for the recognition of the
persons in controlled environments. It can be
integrated into the internet for searching and
retrieving of images /videos which can be used in
much application. This work can be extended for
the gait analysis of animals also.

REFERENCES
[1] Dong Xu, Yi Huang, Zinan Zeng, and Xinxing Xu,
human gait recognition using patch distribution feature
and locality-constrained group sparse representation,
IEEE transactions on image processing.,vol.21, no. 1,
PP. 316-326, January 2012.
[2] A.F.Bobick and A. Y. Johnson, Gait recognition
using static activity specific parameters, in Proc. IEEE
Conf. Comput. Vis. Pattern Recog., 2001, pp. 423430.
[3] R.Tanawongsuwan and A. Bobick, Gait recognition
from time-normalized joint-angle trajectories in the
walking plane, in Proc. IEEE Conf. Comput. Vis.
Pattern Recog., 2001, pp. 726731.
[4] R T. Collins, R. Gross, and J. Shi, Silhouette-based
human identification from body shape and gait, in
Proc. IEEE Int. Conf. Autom. Face Gesture Recog.,
2002, pp. 351356.
[5] J.Han and B. Bhanu, Individual recognition using
gait energy image, IEEE Trans. Pattern Anal. Mach.
Intell., vol. 28, no. 2, pp. 316332, Feb. 2006.

Trans. Circuits Syst. Video Technol., vol. 20, no. 3,

pp. 431438, Mar. 2010.
[8] J. Wright, Y. Ma, J. Mairal, G. Sapiro, T. S.
Huang, and S. Yan, Sparse representation for
computer vision and pattern recognition, Proc.
IEEE, vol. 98, no. 6, pp. 10311044, Jun. 2010.
[9] J.Wang, J. Yang, K. Yu, F. Lv, T. Huang, and
Y. Gong, Locality constrained linear coding for
image classification, in Proc. IEEE Int. Conf.
Comput. Vis. Pattern Recog., 2010, pp. 33603367.
[10] Neetesh Gupta, Niket Bhargava, Dr.
Bhupendra Verma, Md.Ilyas Khan and Shiv
Kumar, A New Approach For CBIR Using
Coefficient Of Correlation, in International
Conference on Advances in Computing, Control,
and
Telecommunication
Technologies.,2009,
pp.380-384.
[11] Dong Xu, Member, IEEE, Shuicheng Yan,
Member, IEEE, Dacheng Tao, Stephen Lin, and
Hong-Jiang Zhang, Fellow, Marginal fisher
analysis and its variants for human gait recognition
and content- based image retrieval, IEEE
transactions on image processing, vol. 16, no.
11,PP 2811- 2821 November 2007.
[12] S. Sarkar, P. J. Phillips, Z. Liu, I. R. Vega, P.
Grother, and K. W. Bowyer, The HumanID gait
challenge problem: Data sets, performance, and
analysis, IEEE Trans. Pattern Anal. Mach. Intell.,
vol. 27, no. 2, pp. 162177, Feb. 2005.
[13] Darshak G. Thakore1, A. I. Trivedi, Vallabh
Vidyanagar, Content based image retrieval
techniques Issues, analysis and the state of the
art.
[14] Dr.A.Venkataramana, B.Krishna, B.Saideep, B.Sai
kumar, Combined DCT, Radon Transform and
2DPCA Based Approach for Gait Recognition,
Int.J.Computer Technology & Applications,Vol 3
(2),PP 818-822.
[15] Michele saad,Content Based Image RetrievelLiterature survey, march 18,2008.
[16] Dr. Fuhui Long, Dr. Hongjiang Zhang and
prof.feng, Fundamentals of content based image
retrieval.

Volume 04 No.9 Issue: 02

International Journal of Communication and Computer Technologies

Page 4057
www.ijccts.org

International Journal of Communication and Computer Technologies

Volume 04 No. 9 Issue: 02 March 2016
ISSN NUMBER : 2278-9723

[17] A.Surendar, Efficient power reduction and

glitch free mux based digitally controlled delay
line.International Journal of Applied Engineering
Research ISSN 0973-4562 Volume 10, Number
10 (2015), pp. 9655 9659.
[18]A.Surendar, Virus detection by using a pattern
matching algorithm for network security.
International Journal of Applied Engineering
Research Volume 10, Number 10 (2015), pp. 9566
9569.
[19] A.Surendar,
A parallel reconfigurable
platform for efficient sequence alignment, African
Journal of Biotechnology ISSN 1684-5315,
Volume 13(33), 13 August, 2014 pp. 3344-3351,
DOI:10.5897/AJB2014.13680.
[20] A.Surendar,Hardware Based Algorithm for
Bioinformatics
ApplicationA
Survey,
International Journal of Applied Engineering
Research,ISSN 0973-4562, Volume 8, Number 6
(2013), pp. 745-754
[21] A.Surendar,Evolution of Reconfiguration
Based Algorithm For Bioinformatics Application:
An Investigation, International Journal of Life
Science Biotechnology and Pharma Research,
ISSN 2250-3137 Volume 2, Number 4 (2013), pp.
17-27.

Volume 04 No.9 Issue: 02

International Journal of Communication and Computer Technologies

Page 4058
www.ijccts.org