Design a New Methodology Based on PBSDC for Face Recognition

crumcasteΤεχνίτη Νοημοσύνη και Ρομποτική

17 Νοε 2013 (πριν από 3 χρόνια και 6 μήνες)

87 εμφανίσεις

Design a New Methodology Based on PBSDC for
Face Recognition
Amit Singh
1
,Anita Yadav
2
,Shradha Singh
3

Computer Science & Engg.

1
Radha Raman Engg. & Technology,Ratibad Bhopal (M.P.)
,
India

3
Mody Institute of Technology & Sciences,Laxmangarh (Rajasthan),India

1
amitsingh3432@gmail.com

2
er.anita12@gmail.com

3
shradha18sigh@gmail.com



Abstract

The objective of face recognition involves the
extraction of different features of the human face like ridges,
minutia’s etc from the face image for discriminate it from
other
persons. It is the problem of searching a face in given database to
find the matches as a given face. The purpose is to find a face that
has highest similarity with a given face in the database. Many
face recognition algorithms have been developed an
d used as an
application of access. For enhancing the performance and
accuracy of biometric face recognition system, we proposed a
multi
-
algorithmic approach that is a well combination of four
different recognition methodologies is called PBSDC technology.


Keywords
-

Face recognition system, Pixel, Image processing,
edge, Euclidean distance.

I.


I
NTRODUCTION


Face detection locates and segments face regions in
cluttered images. It has numerous applications in areas like
surveillance and security control syste
ms, content
-
based image
retrieval, video conferencing and intelligent human computer
interfaces. Some of the current face
-
recognition systems
assume that faces are isolated in a scene. We do not make that
assumption.

The system segments faces in cluttered

images [1, 2, and 3]
with a portable system, we can ask the user to pose for the face
identification task.

This can simplify the face
-
detection algorithm. In addition
to creating a more cooperative target, we can interact with the
system in order to impr
ove and monitor its detection. The task
of face detection is seemingly trivial for the human brain, yet it
remains a challenging and difficult problem to enable a
computer /mobile phone/PDA to do face detection. The human
face changes with respect to inter
nal factors like facial
expression, beard, mustache, glasses, etc. is sensitive to
external factors like scale, lightning conditions, and contrast
between face, background and orientation of face. Thus, face
detection remains an open problem. Many research
ers have
proposed different methods for addressing the problem of face
detection. Face detection is classified into feature
-
based and
image
-
based techniques [5, 7]. The feature
-
based techniques
use edge information, skin color, motion, symmetry, feature
an
alysis, snakes, deformable templates and point distribution.
Image
-
based techniques include neural networks, linear
subspace methods, like eigen faces [3, 4, 6] fisher faces etc.
The problem of face detection in still images is more
challenging and difficu
lt when compared to the problem of face
detection in video, since motion information can lead to
probable regions where faces could be located.

II.

FACE

RECOGNITION

TECHNIQUE


The basic algorithm starts with a pre
-
processing step,
consisting of digitization a
nd segmentation. The next step is
called face segmentation. We define the face segmentation
problem as: given a scene that may contain one or more faces,
create sub
-
images that crop out individual faces. After face
segmentation, the device enters into the
face identification
mode, as shown.

(small)
Suspect database
Face
Data Base
Feat ure
Data Base
Face
Segment ation
Feat ure
Extract ion
classifier
mat ches
GUI
Displays possible
candidat es for selection

Figure 1.

III.

P
ROPOSED
W
ORK

A.

Method Description

My proposed work is combination of Partitioned Function
System, Edge of the image block, Centroid and Weight of the
image block,

Block distance, SD of the block Region. It is very
useful method to find recognition in the pre defined database.

Partitioned Function
:
-

In this function, we create a same size
block of the image.

Identify applicable sponsor/s here.
(sponsors)

Edge
:
-

Edge detection detects outlines of an object and
boundaries between objects and the background in the image.
The Roberts’ Cross algorithm performs is an edge detection
algorithm that performs a two dimensional spatial gradient
convolution on the image.

Centroid and Weight
:
-

Centroid'


1
-
by
-
n vector t
hat specifies
the center of mass of the region. The first element of Centroid
is the horizontal coordinate of the center of mass, and the
second element is the vertical coordinate.

Block Distance
:
-

The block distance measures the path
between the pixels
based on a 4
-
connected neighborhood.

Template matching algorithms
:
-

Cross correlation is a
template matching algorithm that estimates the correlation
between blocks of the query image and block of the database
image block.

Consider x (i) for query blocks

and y

(i) is the database images
block. Where
i
(block)

=

0, 1, 2... The cross correlation r at
delay d is defined as
:


B.

M
ethodology

of the

pr
oposed work

Q
im

Query Image

Q
db


Database Image


Process:

A=Read(Q
im
)

B=Fun_RGB2GRAY(A)

Bpart=Fun_Parti(B)

Tq=Fun_Templet_create(Bpart)

N=Fun_count(Bpart)

For j=1 to N_database_image

For i=1 to N

Di=Fun_take(I
st

image of the database)

x=Fun_RGB2GRAY(Di)

xpart=Fun_Parti(x)

Td=Fun_Template_create(xpart)

if (Tq==Td)

do continue for all block template

if all template will matched then

show(Recognition is done)

else

j=j+1

end

end

if j> N_database_image

show(Recognition is not done)

end


IV.

EXPERIMENTAL

RESULTS


We are showing the database of some face images is given
below in figure 1.


Figure. 2

Given below we take an image from the figure 1.



Fig
ure 3


12 blocks make 12 templates, each template containing
the following details.

T
1 to 12

= (Centroid & We
ight, Block Distance, SD of the
Region)



T
qui

=∑ (T
1
, T
2
, T
3
, T
4
, T
5
, T
6
, T
7
, T
8
, T
9
, T
10
, T
11
, T
12
)




Template

Centroid

Weight
of
Centroid

Avg.
Distance

Avg. SD

T
qui_1

23.11

23.98

55.6

83.588

T
qui_2

34.10

35.22

59.7

69.762

T
qui_3

29.91

3
0.37

51.3

91.883

T
qui_4

42.36

43.19

62.8

58.391

Table 1


Figure 4.


V.

CONCLUSION


In this paper, we have developed method that is very effective
because it is a very good combination
of partition

method;

edge detection, block distance, centroid and standa
rd
deviation
method

apply on face images and get the recognition result.

It
reduces

the deficiency of existing previous methods like
PCA, ICA etc. In future we add some other concept like 2D
cross correlation with ICA, PCA with DCT and moment
invariants.


R
EFERENCES


[1]

Jain, A.K. Klare, B. Park, “
Face

recognition
: Some challenges in
forensics

Automatic
Face

& Gesture
Recognition

and Workshops (FG
2011), 2011 IEEE International Conference on

Digital Object Identifier:

10.1109 / FG .2011.5771338

Publication Year:
2011 , Page(s): 726


733

[2]

Ekenel, H.K.; Stallkamp, J.; Gao, H.; Fischer, M.; Stiefelhagen, , “
Face

Recognition

for Smart Interactions

Multimedia and Expo, 2007
IEEE
International Conference on


Digital Object Identifier:
10.1109 / ICME .2007. 4284823

Publication
Year: 2007 , Page(s): 10
07
-

1010

[3]

Lone, Manzoor Ahmad; Zakariya, S.M.; Ali, Rashid; , “
Automatic
Face

Recognition

System by Combining Four Individual Algorithms

Computational Intelligence and Communication Networks (CICN), 2011
International Co
nference on

Digital Object Identifier:
10.1109 / CICN
.2011.44

Publication Year: 2011 , Page(s): 222


226.

[4]

Sanjay Kr. Singh1, D. S. Chauhan2, Mayank Vatsa3, Richa Singh,
A
Robust Skin Col
or Based Face Detection Algorithm,
Department of
Computer Science and Engineering Institute of Engineering and
Technolog JaIpur −222002, India. Tamkang Journal of Science and
Engineering, Vol. 6, No. 4, pp. 227
-
234 (2003).

[5]

J. Sobottka and I. Pittas.
Segme
ntation and tracking of faces in color
images. In Proceedings of the Second International Conference on
Automatic Face and Gesture Recognition, vol. 4, pages 236
--

241, IEEE
June 1996.

[6]

6.

Wang, C., and Brandstein, M.S., “A hybrid real
-
time face tracking
sy
stem” Proc. ICASSP 1998, Seattle, WA, May, 1998, pps. 3636
-
3740.

[7]

7.

G. Nagy, J. Zou, “Interactive Visual Pattern Recognition”, Proc.
Int. Conf. Pattern Recognition XIV, vol. 2, pp. 478
-
481, Quebec City,
2002.