Integrated Biometrics (Face, Fingerprint, Iris, Palmprint ...technique used in image compression....
Transcript of Integrated Biometrics (Face, Fingerprint, Iris, Palmprint ...technique used in image compression....
IJSRD - International Journal for Scientific Research & Development| Vol. 6, Issue 09, 2018 | ISSN (online): 2321-0613
All rights reserved by www.ijsrd.com 641
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using
PCA
Khushboo1 Sat Pal2 1,2Baba Mastnath University, India
Abstract— Integrated Biometrics is a rising domain in
biometric technology where more than one biometric trait is
combined to improve the performance. Integrated biometrics
has much higher efficiency than unimodal biometrics.
Integrating the biometric system results in enlarge the user
database but increase the level of security. In this paper, a
study of integrated biometrics has been done with five
biometrics considered face, iris, ear, palm and finger
respectively. In biometric system, Problems arise when
integrated performing recognition in a high-dimensional
space. Significant improvements can be achieved by mapping
the data into a lower dimensionality space. This can be done
by PCA approach. PCA method reduces memory requirement
of the system and computation time. This paper presents a
method for face, iris, fingerprint, palm print and ear
recognition based on Principal Component Analysis (PCA). I
have applied the same PCA algorithm for all these biometric
traits.
Key words: PCA, Applications, Face Recognition, Iris
Recognition, Fingerprint Recognition, Palm Print
Recognition, Ear Recognition
I. INTRODUCTION
Biometrics refers to the use of physiological or biological
characteristics to measure the identity of an individual. These
features are unique to each individual and remain mostly
stable during a person’s lifetime.
Fig. 1:
These features make biometrics a promising secure
solution to the society. The access to the secured area can be
made by the use of ID numbers or password. But such
information can easily be accessed by intruders and they can
breach the doors of security. The problem arises in case of
monetary transactions and highly restricted to information
zone. Thus to overcome the above mentioned issue biometric
traits are used. The biometrics possesses unique, time
invariant, consistent and not able to be forgotten or lost
features. These features made biometrics an important
component in security-related applications such as: logical
and physical access control, airport/sea security, border
control, forensic investigation, IT security, identity fraud
protection, and terrorist prevention or detection, etc.[3].
Biometric systems work by first capturing a sample
of the feature, such as recording a digital sound signal for
voice recognition, or taking a digital color image for face
recognition or taking the print for the palmprint recognition.
The sample is then transformed into a biometric template
using some sort of mathematical function. The biometric
template will provide a normalized, efficient and highly
discriminating representation of the feature, which can then
be objectively compared with other templates in order to
determine identity.
Most biometric systems allow two modes of
operation [5]. First one is an enrolment mode for adding
templates to a database, and second one is a verification/
identification mode, where a template is created for an
individual and then a match is searched for in the database of
pre-enrolled templates [40].
Enrollment Process
Fig. 2: Enrollment Process
Fig. 3: Verification Process
The new template is matched against the stored
template and a measure M is calculated. The Decision module
accepts or rejects the claimed user using the measure M [40].
Fig. 4: Identification Process
The new template is matched against all the
templates in the database producing a score S for each
template. Depending on the score the Decision module
decides who the user is [40].
The various biometrics traits available are face,
fingerprint, iris, palm print, hand geometry and ear, thumb.
The reliability of several biometrics traits is measured with
the help of experimental results. In this study, Among the
available biometric traits some of the traits have been
considered namely face, iris, ear, palm and finger
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 642
respectively. Research groups around the world are
developing algorithms and systems based on face, iris,
fingerprint, palm print and ear. But I have used here PCA
algorithm for all these biometric traits.
PCA was invented in 1901 by Karl Pearson.
Principal component analysis (PCA) is a classic technique
used for compressing higher dimensional data sets to lower
dimensional ones for data analysis, visualization, feature
extraction, or data compression. The Principal Component
Analysis (PCA) is one of the most successful techniques that
have been used in image recognition and compression. The
purpose of PCA is to reduce the large dimensionality of the
data space to the smaller intrinsic dimensionality of feature
space which is needed to describe the data economically. The
PCA is a technique that allows, from extracting the
eigenvectors and eigenvalues of the covariance matrix of
images, to create a space of reduced images, which contains
the “main components” of the images for subsequent
recognition. Although PCA is widespread adopted in the
recognition of face images, we apply here this technique also
as a part of the face, iris, fingerprint, palmprint and ear
recognition [5].
It is a way of identifying patterns in data, and
expressing the data in such a way as to highlight their
similarities and differences. Since patterns in data can be hard
to find in data of high dimension, where the luxury of
graphical representation is not available, PCA is a powerful
tool for analyzing data. PCA is applied on Eigen face
approach to reduce the dimensionality of a large data set. The
advantage of PCA is that once we have found these patterns
in the data, and we compress the data, by reducing the number
of dimensions, without much loss of information. This
technique used in image compression. When the original data
is reproduced, the images have lost some of the information.
This compression technique is said to be lossy because the
decompressed image is not exactly the same as the original,
generally worse.
PCA is the concept of Eigenvalues and Eigenfaces.
PCA is a method of transforming a number of correlated
variables into a smaller number of uncorrelated variables. .
PCA can be applied to the task of face recognition by
converting the pixels of an image into a number of eigenface
feature vectors, which can then be compared to measure the
similarity of two face images. PCA involves the calculation
of the eigenvalue decomposition of a data covariance matrix
or singular value decomposition of a data matrix, usually after
mean centering the data for each attribute [2]. After feature
extraction, the image is represented as a feature vector. We
used Euclidean Distance similarity measures to measure the
similarity of test and training images feature.
II. EARLIER WORK
Three algorithms - Artificial Neural Network, Eigenfaces and
Active Appearance Model based methods for face
recognition. Eigenfaces for face representation was used first
used by Sirovich and Kirvy which was later developed
by Turk and Pentland for face recognition. Different
techniques have been developed using neural networks. The
implementation by Lawrence, Giles, Tsoi and Back showed
good results. Taylor and Cootes used Active Appearance
Model to design a system for face identification. Some
comparison has been done between eigenfaces vs.
fisherfaces, eigenfaces vs. feature based techniques and
likewise. [34] Have proposed approach to replace the Gabor
features by a graph matching strategy and HOGs (Histograms
of Oriented Gradients). [35] Have proposed the FERET
Evaluation Methodology for Face Recognition Algorithm.
[36] Have proposed Robust Facial Feature Tracking
methodology for tracking the facial features of human face.
In iris recognition , many researchers gave their
contributions, [18] proposed an improved AD Adaboost
algorithm for eye detection in an image, [19] presented a
matching strategy based on possibilistic fuzzy clustering
algorithm for iris recognition ,[20] introduced the zero
crossing detection method for iris recognition, [21] proposed
the iris recognition system based on chaos encryption , [22]
proposed an iris recognition system using phase based image
matching and presented an algorithm of wavelet transform for
iris recognition[4]. Gabor filters and discrete wavelet
transform zero-crossing representation
In fingerprint recognition, [18] proposed multilayer
perceptrons and use the elements of the orientation image as
input features. [19] Proposed a neural network as decision
stage and the fingerprint features were extracted using the
discrete wavelet transform. [13] Proposed a method using the
2D hidden Markov model. [10] The orientation image is
partitioned into regions by minimizing a cost function that
takes into account the variance of the element orientations
within each region. An inexact graph matching technique is
then used to compare therelational graphs with class-
prototype graphs.
In palmprint recognition, [23] have used Principal
Component Analysis (PCA), Fisher Discriminant Analysis
(FDA) and Independent Component Analysis (ICA) for the
feature extraction from the raw images. [24] Used the
approach of compact extraction of principle lines from the
palmprint images by using filtering operations consecutively.
Here, the image is first smoothed and then worked upon. The
palmprint images are passed through several filters.[26] have
used the two dimensional Gabor for the development of a
high performance palmprint identification. [27] Proposed an
approach which makes use of the multispectral analysis of the
hybrid features to improve the performance of the palm print
recognition system. [29] Have proposed an online palm print
identification system. This system was developed to make
authentication possible in the real time also. [30] have
proposed a novel preprocessing technique for DCT domain
palmprint recognition in which the task of feature extraction
is carried out in local zones using 2 dimensional Discrete
Cosine Transform (2D-DCT). [65] Proposed a dynamic
selection scheme by introducing global texture feature
measurement and the detection of local interesting points
In ear recognition [31] have propose force field
transformation for the force field feature extraction, [32] have
proposed local surface patch comparisons using range data ,
Voronoi diagram matching, neural networks, and genetic
algorithms. [33] Have proposed geometric feature extraction
and 2D, 3D data, ICP. [37] Detected image regions with a
large local curvature with a technique called step edge
magnitude. [38] Use weak classiers based on Haar-wavelets
in connection with AdaBoost for ear localization. [39]
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 643
developed an ear detection method which fuses range images
and corresponding 2D color images .
Here is the table shows the different algorithms used
by researchers in different biometric traits.
Algorithms used Face Finger
print Iris
Palm
print Ear
Principal
Component
Analysis (PCA)
[48] [52] [10] [16] [33]
Independent
Component
Analysis
[48] [52] [10] [16] [77]
Discrete Cosine
Transform(DCT) [49] [78] [79] [30] [119]
Linear
Discriminant
Analysis(LDA)
[50] [52] [41] [81] [82]
Locality
Preserving
Projections(LPP)
[50] ------- ------
-
------
-
------
-
Discrete wavelet
transform(DWT) [87] [83] [88] [89] [90]
Neural networks [50] [110] [111] [112] [75]
Wavelet-Curvelet
Technique [58] [93] [94] [95] [91]
2D wavelet
transform [49] [97] [98] [99] [100]
Neural networks
with Gabor filters [50] ------ ------ ------ ------
Novel Thinning
Algorithm
------
- [55] ------ [113] ------
MERIT ------
- [56] ------ ------ ------
Image
Segmentation [118] [60] [117] [115] [116]
Cluster Algorithm [121] [61] [122] [123] [120]
Weighted Linear
Embedding
(WLE)
------ [52] ------ [124] ------
local discriminant
embedding
analysis (LDE)
------ [124] ------ [124] ------
LGIC technique ------ [52] ------ [52] ------
Gabor filter [104] [86] [103] [124] [101]
Edge detection [125] [52] [127] [126] [76]
Gabor Wavelet
Transforms [96] [105] [42] [68] [106]
Log gabor
wavelets [107] [59] [10] [108] [109]
Circular
Symmetric Filters ------ ------ [43] ------ ------
Haar Wavelet
transform [49] [128] [46] [129] [38]
Self-organizing
map neural
network
[130] [132] [47] [131] [133]
M-ICA [136] [137] [44] ----- -----
Phase Based
Image Matching [134] [85] [22] [80]
Indexing
technique ----- [139] [138] [63] -----
Competitive
Coding Scheme ----- ----- ----- [66] -----
Minutiae
extraction [140] [141] ----- [69] -----
Latent Semantic
Analysis [150] ----- ----- ----- -----
ICP [142] ----- ----- ----- [71]
Geometric
approach [143] [144] ----- ----- [40]
force field
transformations ----- ----- ----- ----- [73]
novel graph
matching based
algorithm
----- ----- ----- ----- [74]
Elastic bunch
graph matching [148] ----- [149] ----- -----
Cumulative Sums
based Approach ----- ----- [79] ----- -----
Kernel PCA [48] ----- [146] [92] [145]
Image Processing [147] ----- ----- [114] -----
CVQ technique [135] ----- ----- ----- -----
Table 1: Shows the Different Algorithms used in Different
Biometric Traits
III. APPLICATIONS
A. Applications of Biometrics
Applications of biometric system are : Security (access
control to buildings, airports/seaports, ATM machines and
border checkpoints ,computer/ network security , email
authentication on multimedia workstations),Surveillance (a
large number of CCTVs can be monitored to look for known
criminals, drug offenders, etc. ),General identity verification
(electoral registration, banking, electronic commerce,
identifying newborns, national IDs, passports, drivers’
licenses, employee IDs), Criminal justice systems (mug-
shot/booking systems, post-event analysis, forensics),Image
database investigation ,Smart Card applications , Multi-
media environments with adaptive human computer
interfaces , Video indexing ,Witness face reconstruction [25].
B. Applications of PCA
PCA is a useful statistical technique that has found
application in fields such as face recognition and image
compression. The jobs which PCA can do are prediction,
redundancy removal, feature extraction, visualization and
data compression, etc. PCA is a common technique for
finding patterns in data of high dimension. It covers standard
deviation, covariance, eigen vectors and eigen values. These
are mathematical concepts that will be used in PCA. Now a
day, PCA is using for most of the biometric traits like face,
hand, fingerprint, iris, ear, palmprint, thumb etc.
IV. HOW PCA WORKS
Suppose Γ is an N2x1 vector, corresponding to an NxN face
image I [1].
1) Step 1: obtain face images I1, I2, ..., IM (training faces)
2) Step 2: represent every image Ii as a vector Гi
3) Step 3: compute the average face vector Ψ:
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 644
4) Step 4: subtract the mean face:
i i
5) Step 5: compute the covariance matrix C:
Where A [1 2 . . . M] (N²xM matrix)
6) Step 6: compute the eigenvectors ui of AAT
(The matrix AAT is very large)
Step 6.1: consider the matrix ATA (MxM matrix)
Step 6.2: compute the eigenvectors vi of ATA
Thus, AATand ATA have the same eigenvalues and their
eigenvectors are related as follows: ui = Avi .
Step 6.3: compute the M best eigenvectors of AAT : ui =
Avi
7) Step 7: keep only K eigenvectors (corresponding to the
K largest eigenvalues)
Each face (minus the mean) Φi in the training set can be
represented as a linear combination of the best K
eigenvectors:
Each normalized training face Φi is represented in this basis
by a vector:
Image recognition using Euclidean distance in PCA:
follow these steps:
1) Step 1: normalize :
2) Step 2: project on the eigenspace
3) Step 3: represent as:
4) Step 4: find 𝑒𝑟 𝑚𝑖𝑛𝑙 ||𝛺𝑙 ||
5) Step 5: if er < Tr, then is recognized as face l from the
training set.
The distance er is called distance within the face space. We
use the common Euclidean distance to compute er.
A. Flowchart of PCA
Fig. 5: Flowchart
Here is the flowchart to present how the MATLAB software
program works for all Biometrics:
B. Flowchart of Proposed System
Fig. 6: Flowchart of Proposed System
V. DESCRIPTION OF BIOMETRICS USING PCA
A. Face Recognition using PCA
The task of recognition of human faces is quite complex. The
human face is full of information but working with all the
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 645
information is time consuming and less efficient. It is better
to get unique and important information and discards other
useless information in order to make system efficient. Face
recognition systems can be widely used in areas where more
security is needed. M.A. Turk and Alex P. Pentland
developed a near real time Eigen faces system for face
recognition using Euclidean distance.
The eigenfaces approach is now largely superceded
in the face recognition literature. A set of eigenfaces can be
generated by performing a mathematical process
called principal component analysis (PCA) on a large set of
images depicting different human faces. eigenfaces can be
considered a set of "standardized face ingredients", derived
from statistical analysis of many pictures of faces. Any
human face can be considered to be a combination of these
standards faces [6].
There are two phases in the identification phase:
training and testing. In the training phase the eigenvalues and
eigenvectors of the training set are extracted and the
eigenvectors are chosen based on the top eigenvalues.
Training set is a set of clean images without any duplicates.
In the testing phase the algorithm is provided a set of known
faces and a set of unknown faces as the probe set. The
algorithm matches each probe to its possibly identity in the
gallery [14]
I have used Frontal face dataset which is Collected
by Markus Weber at California Institute of Technology, 450
face images with resolution 896 x 592 pixels in the Jpeg
format, Belongings to 27 or so unique people under with
different lighting/ expressions/ backgrounds. In our
experimental result, we have used 5 individuals with different
5 face images. So, we have 25 training face images and 10
test images (5 individuals with different 2 face images). By
using PCA, we reduced the dimensions from (896 x 592) to
(56 x 56). First largest 21 eigen values are selected for 21
eigen faces instead of 25 eigenface. The Euclidean distance
is used to find out the distance between the test image and
training images. The training image which has the minimum
distance with the test image is supposed to be an individual
with perfect match. The proposed matlab program works in
jpeg format images.
I have applied the MATLAB program on 10 test
images, and all are recognized with exact individual. One
result with proper match is shown below:
Fig. 7:
The left image is the test image and it is recognized
by the right side image from the training images.
Table showing the distance between test image and
all training images. The test image has the minimum distance
with image 2 by minimum distance 1.619653077917682
Image
s
Minimum
Distance
Image
s
Minimum
Distance
1 3.6631152227755
05 14
3.6459816846536
34
2 1.6196530779176
82 15
7.5263106674452
26
3 3.1061940715067
31 16
6.2199686211636
78
4 4.2750330886209
18 17
3.5396720554887
23
5 3.4398250859590
34 18
3.8162938957098
51
6 2.5940748800938
42 19
3.9704657945910
42
7 2.2647439367216
11 20
4.3542686719853
32
8 4.4588529935605
16 21
3.1569922546851
93
9 4.9149855473645
22 22
5.4177434028974
36
10 3.1982077633311
67 23
4.2460535400070
97
11 5.2421629199057
21 24
5.3197437439429
76
12 3.4329490096996
86 25
3.7289095208330
27
13 3.7766899246178
94
Table 2: Distance between Test Image and Training Images
The graph shows the distance found between the test
images and training images. The distance is found by using
the Euclidean distance method.
Fig. 8: shows the graph plot distance found with test image
verses training images
B. Fingerprint Recognition using PCA
Fingerprints are currently emerging as the widespread
biomedical identification method in both forensic and civilian
applications. Fingerprint recognition is one of the most
reliable and valid personal recognition method which has
been in use of long time. Fingerprint probably is the most
widely used as a personal identification tool. It has been used
for many centuries, primarily because of its individuality and
0 5 10 15 20 25 300
1
2
3
4
5
6
7
8
images
min
imum
dis
tanc
e m
atch
ed
matches 2.000000, score 1.619653
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 646
uniqueness and reliability. Of all the Biometrics, fingerprint
identification is one of the most famous and publicized
biometrics and has been successfully used in security
applications. Nowadays, the automatic fingerprint
identification algorithms are very expansive on
computations. Due to the large size of present day fingerprint
databases, it is necessary to use methods to reduce the number
of one-to one fingerprint comparisons when performing the
fingerprint query execution. A fingerprint is believed to be
unique to each person. Fingerprints of even identical twins
are different [6].
The fingerprint image is made up of pattern of ridges
and valleys; they are the replica of the human fingertips. The
fingerprint image represents a system of oriented texture and
has very rich structural information within the image. This
flow-like pattern forms an orientation field extracted from the
style of valleys and ridges called minutia. Now days, Many
algorithms are used for feature extraction and pattern
matching for fingerprint recognition. But we have used PCA
for fingerprint recognition because of its simplicity and less
computational work and require less space in the system
because of its low dimensionality approach [7].
I have used fingerprint database. All images are in
PNG format. There are 16 people with different 8 fingerprint
images with different lighting/ expressions/ backgrounds and
resolution is (248 x 338) pixels. In the experimental result, I
have used 6 individuals with different 5 fingerprint images.
So, I have 30 training fingerprint images and 12 test images (
6 individuals with different 2 fingerprint images). By using
PCA, I reduced the dimensions from (248 x 338) to (100 x
100). First largest 24 eigen values are selected. The PNG
format of images has changed to jpeg. The proposed matlab
program works in jpeg format images. The Euclidean
distance is used to find out the distance between the test
image and training images. The training image which has the
minimum distance with the test image is supposed to be an
individual with perfect match. If I are decreasing the
dimensions and increasing the eigenvalues from 24 to 29 then
the distance also decreases.
Applied the MATLAB program on 12 test images,
and all are recognized with exact fingerprint match. One
result with proper match is shown below
Fig. 9:
The left image is the test image and it is recognized
by the right side image from the training images.
Table showing the distance between test image and
all training images. The test image has the minimum distance
with image 2 by minimum distance 2.889597219692923.
Imag
es
Minimum
Distance
Imag
es
Minimum
Distance
1 3.7344410007568
68 16
3.5031131625998
504
2 2.8895972196929
23 17
3.5947058692960
74
3 3.5139404691032
436 18
3.6730570935262
04
4 3.2168469448116
754 19
3.1267284655385
676
5 3.9914547291484
817 20
3.5490203998781
964
6 3.7082450605064
285 21
3.5557397183066
333
7 3.4197704051786
713 22
3.5508943764682
72
8 5.2262852140173
81 23
4.0814273476168
8
9 3.4797088181246
41 24
3.7254612036702
826
10 4.9884213907681
15 25
4.0502310729967
79
11 5.2931814160943
675 26
4.3637751110559
595
12 4.3699001142691
200 27
3.7332782686689
94
13 4.4212664157955
23 28
3.9223158270055
05
14 4.3156793504587
965 29
3.7942697772504
568
15 3.7695229587313
32 30
3.4325023035618
925
Table 3: Distance between Test Image and Training Images
The graph shows the distance found between the test image
and training images. The distance is found by using the
Euclidean distance method.
Fig. 10: shows the Graph Plot Distance found with Test
Image verses training images.
C. Iris recognition using PCA
Iris pattern recognition is one of the most reliable, secure and
promising approaches for individual authentication. Iris
recognition is considered as a most reliable and accurate
method because of its high recognition rate and uniqueness.
Among all biometrics, iris recognition is the most consistent
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 647
one. The iris is a thin circular diaphragm, which lies between
the cornea and the lens of the human eye. The pattern of the
human iris differs from person to person; there are not even
two irises alike, not even for genetically identical twins. The
iris is considered one of the most stable biometric, as it is
believed to not change The iris is considered one of the most
stable biometric, as it is believed to not change [8].
Various algorithms have been applied for feature
extraction and pattern matching processes .These methods
use local and global features of the iris. A great deal of
advancement in iris recognition has been made through these
efforts. Here, I have used PCA for feature extraction. In PCA,
The aim of feature extraction is to find a transformation from
an n-dimensional observation space to a smaller m
dimensional feature space [9]. Main reason for performing
feature extraction is to reduce the computational complexity
for iris recognition. Most existing iris recognition methods
are based on the local properties such as phase, shape, and so
on. However, iris image recognition based on local properties
is difficult to implement. Principal component analysis can
produce spatially global features [10]. The original data are
thus projected onto a much smaller space, resulting in data
reduction. Using PCA the feature vector is generated. The
matching of test iris and data base iris is performed using
PCA.
I have used MMU iris database images with
resolution 320 x 240 pixels in the bitmap format, Belongings
to 46 unique people with different 5 left and 5 right iris
images .In the experimental result, I have used 3 individuals
with different 3 left iris images and 3 right iris images . so, I
have 18 training iris images and 12 test images ( 3 individuals
with different 2 left iris images and 2 right iris images). By
using PCA , I reduced the dimensions from (320 x 240) to (56
x 56). First largest 15 eigenvalues are selected. The bitmap
format of images has changed to jpeg. The proposed matlab
program works in jpeg format images. The Euclidean
distance is used to find out the distance between the test
image and training images. The training image which has the
minimum distance with the test image is supposed to be
perfect iris match.
I have applied the MATLAB program on 12 test
images, and all are recognized with exact iris match. One
result with proper match is shown below.
Fig. 11:
The left image is the test image and it is recognized
by the right side image from the training images.
Table showing the distance between test image and
all training images. The test image has the minimum distance
with image 6 by minimum distance 0.5912620231613743.
Imag
es
Minimum
Distance
Imag
es
Minimum
Distance
1 1.4207929915162
376 10
1.7666360015230
704
2 2.1598878288685
32 11
1.9892906756400
18
3 1.4592054612753
664 12
2.2982665543640
395
4 2.4132833806738
314 13
3.1598112106653
033
5 1.6212619444271
357 14
3.4114385260840
48
6 0.5912620231613
743 15
3.4939594550225
124
7 2.8226185759142
02 16
2.8259585113782
997
8 1.9817126868927
14 17
2.7088968349929
3
9 2.3262217457647
383 18
2.3963525707589
04
Table 4: Distance between test image and training images.
The graph shows the distance found between the test
images and training images. The distance is found by using
the Euclidean distance method.
Fig. 12: shows the graph plot distance found with test image
verses training images
D. Palmprint recognition using PCA
Palmprint is one of the relatively new physiological
biometrics because of its stable and unique characteristics.
The rich texture information of palmprint offers one of the
powerful means in personal recognition. Palmprint
recognizes a person based on the principal lines, wrinkles and
ridges on the surface of the palm. These line structures are
stable and remain unchanged throughout the life of an
individual. More importantly, no two palmprints from
different individuals are the same, and people feel easy to
have their palmprint images taken for testing. Therefore
palmprint recognition offers promising future for medium-
security access control system [16]. Palmprint recognition is
a very interesting research area.
In Palmprint recognition, it is sometimes difficult to
extract the line structures that can discriminate every
individual well. Besides, creases and ridges of the palm are
always crossing and overlapping each other which
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 648
complicates the feature extraction task [16]. An important
issue in palmprint recognition is to extract palmprint features.
Among the works that appear in the literature are eigenpalm
, Gabor filters , Fourier Transform , and wavelets . I have used
“eigenpalm” (PCA) in the study. Eigenpalm are just like the
eigenface. It works with the same manner as for face
recognition system. The features are extracted with PCA and
then matching process is done [62].
I have used hand database with different 300 hand
images with resolution 230 x 260 in the tif format .In the
experimental result, I have used 5 individuals with different
4 palmprint images. So, I have 20 training images and 10 test
images (5 individuals with different 2 palmprint images). By
using PCA, I reduced the dimensions from (230 x 260) to
(100 x 100). First largest 12 eigen values are selected for 12
eigenpalms instead of 20 eigenpalms. The tif format of
images has changed to jpeg. The proposed matlab program
works in jpeg format images The Euclidean distance is used
to find out the distance between the test image and training
images. The training image which has the minimum distance
with the test image is supposed to be perfect match.
I have applied the MATLAB program on 10 test
images, and all are recognized with exact palmprint match.
One result with proper match is shown below:
Fig. 13:
The left image is the test image and it is recognized
by the right side image from the training images.
Table showing the distance between test image and
all training images. The test image has the minimum distance
with image 14 by minimum distance 1.0786326202370273.
Imag
e Minimum Distance
Imag
e Minimum Distance
1 6.80975829423400
2 11
4.94269604254555
35
2 6.44992519346678
9 12 5.87120416077242
3 6.73476982962015
75 13
5.72429021168663
2
4 6.73480009255091
7 14
1.07863262023702
73
5 6.72736976435878
4 15
1.74444191962936
41
6 4.67673702502589
5 16
3.70912160631344
67
7 4.30099505853018
2 17
1.91043167035315
99
8 5.41776481775816
9 18
5.19886924455541
5
9 5.11118192213683 19 5.39035507687603
75
10 3.56827986846222
03 20
4.10041029246808
6
Table 5: Distance between test image and training images.
The graph shows the distance found between the test
images and training images. The distance is found by using
the Euclidean distance method.
Fig. 14: shows the graph plot distance found with test image
verses training images
E. Ear recognition using PCA
The possibility of identifying people by the shape of their
outer ear was first discovered by the French criminologist
Bertillon, and refined by the American police officer
Iannarelli, who proposed a first ear recognition system based
on only seven features. The detailed structure of the ear is not
only unique, but also permanent, as the appearance of the ear
does not change over the course of a human life [12].
Additionally, the acquisition of ear images does not
necessarily require a person's cooperation but is nevertheless
considered to be non-intrusive by most people. Ears have
gained attention in biometrics due to the robustness of the ear
shape. The shape does not change due to emotion as the face
does, and the ear is relatively constant over most of a person’s
life [13]. It has been suggested that the shape of the ear and
the structure of the cartilaginous tissue of the pinna are
distinctive. Matching the distance of salient points on the
pinna from landmark location of the ear is the suggested
method of recognition in this case.
Ears have several advantages: reduced spatial
resolution, a more uniform distribution of color, and less
variability with expressions and orientation of the face. In
face recognition there can be problems with e.g. changing
lightning, and different head positions of the person. There
are same kinds of problems with the ear, but the image of the
ear is smaller than the image of the face, which can be an
advantage. In practice ear biometrics aren’t used very often.
There are only some cases in the crime investigation area
where the earmarks are used as evidence in court. However,
it is still inconclusive if the ears of all people are unique.
There are some researches done which favor that ear
uniqueness is good enough h[14]. The most interesting parts
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 649
of the ear are the outer ear and ear lope, but the whole ear
structure and shape is used.
In this paper, I have used principal component
analysis, also known as “eigenfaces”, which is a
dimensionality-reduction technique in which variation in the
dataset is preserved. The classification is done in eigenspace,
which is a lower dimension space defined by principal
components or the eigenvectors of the data set.
I have taken IIT Delhi Ear Database version 1.0,
This is touch less ear image database mainly. All the images
are acquired from a distance (touch less) using simple
imaging setup and the imaging is performed in the indoor
environment. The currently available database is acquired
from the 121 different subjects and each subject has at least
three ear images. All the subjects in the database are in the
age group 14-58 years. The database of 471 images has been
sequentially numbered for every user with an integer
identification/number. The resolution of these images is (272
x 204) pixels and all these images are available in jpeg format.
In the experimental result, I have used 10 individuals with
different 3 ear images. So, I have 30 training face images and
20 test images (10 individuals with different 2 ear images).
By using PCA, I reduced the dimensions from (272 x 204) to
(100 x 100). First largest 21 eigen values are selected for 21
eigenear instead of 30 eigenear. The proposed matlab
program works in jpeg format images The Euclidean distance
is used to find out the distance between the test image and
training images. The training image which has the minimum
distance with the test image is supposed to be an ear with
perfect match.
I have applied the MATLAB program on 20 test
images, and all are recognized with exact ear match. One
result with proper match is shown below:
Fig. 15:
The left image is the test image and it is recognized
by the right side image from the training images.
Table showing the distance between test image and
all training images. The test image has the minimum distance
with image 8 by minimum distance 0.7625512875712156.
Imag
es
Minimum
Distance
Imag
es
Minimum
Distance
1 3.6415662325106
113 16
2.0522029700881
63
2 3.5279409023380
35 17
2.3192799508064
272
3 3.5713602457418
32 18
2.7439082290819
865
4 3.6642828670141
91 19
2.2317384315180
53
5 3.5903777541068
087 20
2.7437715888705
645
6 3.4734443779222
595 21
2.6639559952505
483
7 1.0825819993289
152 22
2.1621744146398
667
8 0.7625512875712
156 23
2.1134032073819
453
9 1.2458929317615
064 24
2.5232900947231
03
10 3.0159897078665
100 25
2.8456270277603
49
11 3.2116148934801
75 26
2.8747147788553
43
12 3.2226047212110
234 27
2.4855933107944
93
13 2.8189486366466
703 28
3.3216860730778
21
14 2.6627780720555
716 29
3.5037337925125
04
15 2.7557690319927
51 30
2.7363496713997
04
Table 6: Distance between test image and training images.
The graph shows the distance found between the test
images and training images. The distance is found by using
the Euclidean distance method.
Fig. 16: shows the graph plot distance found with test image
verses training images
VI. RESULT / CONCLUSION
In this paper, I have used PCA algorithm for all biometric
traits such as face, iris, fingerprint, palm print and ear
recognition. The same MATLAB software program is used
for all biometrics. The results are obtained are discussed
earlier. A short format of result is shown here of all biometric
traits.
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 650
Bio
metric
Traits
using
(PCA)
Image
Format
Format
Changed
To
Images
Dimensions
(pixels)
Dimensions Reduced
To
(pixels)
Matched
image
number
with
(M.D)
Minimum
Distance
Found with training
images
FACE Jpeg Jpeg (896 x 592) (56 x 56) 2 1.619653077917682
FINGER Png Jpeg (248 x 338) (100 x 100) 2 2.889597219692923
IRIS bitmap Jpeg (320 x 240) (56 x 56) 6 0.5912620231613743
PALM tif Jpeg (230 x 260) (100 x 100) 14 1.0786326202370273
EAR Jpeg Jpeg (272 x 204) (100 x 100) 8 0.7625512875712156
Table 7: shows the Short Description of the Result Obtained of all Biometric Traits
From the experimental results mentioned above, it
has been proven that PCA is well suited for all biometrics and
given better results. All test images (face, ear, iris, fingerprint,
palmprint) found with perfect match in the training images.
Main reason for using PCA is to reduce the computational
complexity and reduce the large dimensionality of the data
space to the smaller intrinsic dimensionality of feature space.
PCA based method is computationally inexpensive and
requires less time and therefore we considered the algorithm
of PCA if the noise is not strong. The aim of working on the
PCA is to develop a system with increased speed and
accuracy. In Comparison with other methods, our algorithm
can be implemented without using hard mathematical
computations.
REFERENCES
[1] M. Turk and A. Pentland, "Eigenfaces for Recognition",
Journal of Cognitive Neuroscience, vol.3, no. 1, pp. 71-
86, 1991, hard copy.
[2] “Eigenfaces face recognition (MATLAB)”, 2 December
2010 based on M. Turk and A. Pentland, seminal work.
[3] “Multimodal Face and Ear Images” , Journal of
Computer Science 5 (5): 374-379, 2009 ,ISSN 1549-
3636 , Science Publications.
[4] Turk, M.A. and A.L. Pentland, 1991, “Face recognition
using Eigen faces”, Proc. IEEE computer society Conf
Computer Vision and pattern recognition, pp: 586-591.
[5] Taranpreet Singh Ruprah ,”Face Recognition Based on
PCA Algorithm”, Special Issue of International Journal
of Computer Science & Informatics (IJCSI), ISSN
(PRINT) : 2231–5292, Vol.- II, Issue-1, 2.
[6] Mohammed S. Khalil, Muhammad Imran Razzak,
Muhammad Khurram Khan, “Fingerprint Classification
Using PCA, LDA, L-LDA and BPN”, Center of
Excellence in Information Assurance (CoEIA),King
Saud University, Saudi Arabias.
[7] Ching-Tang Hsiegh, Shys-Rong Shyu, “Principal
Component Analysis for Minutiae Verification on
Fingerprint Image”, Proceedings of the 7th WSEAS
International Conference on Multimedia Systems &
Signal Processing, Hangzhou, China, April 15-17, 2007
.
[8] Pravin S. Patil,S. R. Kolhe ,R. V. Patil, P. M. Patil, “The
Comparison of Iris Recognition using Principal
Component Analysis, Log Gabor and Gabor Wavelets” ,
International Journal of Computer Applications (0975 –
8887) ,Volume 43– No.1, April 2012.
[9] Mansfield and J. Wayman (2002), “Best Practice
Standards for Testing and Reporting on Biometric
Device Performance,” Nat‟l Physical Laboratory of UK.
[10] Jin-Xin Shi and Xiao-Feng Gu (2010), “The
Comparision of Iris Recongnition Using Prinncipal
Component Analysis, Independent Component Analysis
and Gabor Wavelets”, 3rd IEEE International
Conference on Computer Science and Information
Technology (ICCSIT), 61-64.
[11] L. Masek (2003), “Recognition of human iris patterns for
biometrics identification” , B. Eng. thesis, University of
Western Australia, Perth, Australia.
[12] Anika Pflug, Christoph Busch, “Ear Biometrics: A
Survey of Detection, Feature Extraction and Recognition
Methods”, July 2, 2012.
[13] Christopher Middendorff, Kevin W. Bowyer, Ping Yan,
“Multi-Modal Biometrics Involving the Human Ear”.
[14] Hanna-Kaisa Lammi, “EAR BIOMETRICS”,
Lappeenranta University of Technology, Department of
Information Technology.
[15] Bartlett, M.S., Movellan, J.R., & Sejnowski, T.J., “Face
recognition by independent component analysis”, IEEE
Transactions on Neural Networks, 13(6), pp 1450-1464
(2002).
[16] Tee Connie, Andrew Teoh, Michael Goh, David Ngo,
“Palmprint Recognition with PCA and ICA”.
[17] Jaspreet Kour, Shreyash Vashishth, Nikhil Mishra,
Gaurav Dwived, Prateek Arora , “Palmprint Recognition
System”, International Journal of Innovative Research in
Science, Engineering and Technology, Vol. 2, Issue 4,
April 2013.
[18] Benke Xiang and Xiaoping Cheng, “Eye Detection
Based on Improved AD AdaBoost Algorithm,” Second
IEEE International Conference on Signal Processing
Systems, vol 2, pp 617-620, 2010.
[19] Chung–Chih Tsai, Heng-Yi Lin, Jinshiuh Taur and
Chin–Wang Tao, “A New Matching Approach for Local
Feature Based Iris Recognition System,” Fifth IEEE
International Conference on Industrial Electronics and
Applications, pp. 387-392, July 2010.
[20] Qichuan Tian, Xirong Liu, Ziliang Li and Linsheng
Li,“Imperfect Iris Information for Identity Recognition,”
Second IEEE International Congress on Image and
Signal Processing, pp. 1-5, October 2009.
[21] Liu Yang, Yue Xue Dong, Liu Ying Fei and He Yan,
“Iris Recognition System Based on Choas Encryption,”
IEEE International Conference on Computer Design and
Applications, vol 1, pp. 537-539, 2010.
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 651
[22] Kazuyuki Miyazawa, Kaichi Ito, Takafumi Aoki, Koji
Kobayashi and Atsushi Katsumata, “An iris Recognition
System Using Phase Based Image Matching,” IEEE
International Conference on Image Processing, pp. 325-
328, 2006.
[23] Tee Connie, Andrew Teoh Beng Jin, Michael Goh Kah
Ong, David Ngo Chek Ling, “An automated palmprint
recognition system”, Image and Vision Computing ,
Vol.23, pp.501–515, 2005.
[24] Patprapa Tunkpien, Sasipa Panduwadeethorn,
Suphakant Phimoltares, “Compact Extraction of
Principle Lines in Palmprint Using Consecutive Filtering
Operations”, Proceedings of the Second International
Conference on Knowledge and Smart Technologies,
pp.39-44, 2010.
[25] Rabia Jafri ,Hamid R. Arabnia, “A Survey of Face
Recognition Techniques”, Journal of Information
Processing Systems, Vol.5, No.2, June 2009
[26] I Ketut Gede Darma Putra, Erdiawan, “High
Performance Palmprint Identification System Based On
Two Dimensional Gabor” , TELKOMNIKA Vol. 8, No.
3, pp.309-318, 2010.
[27] Sina Akbari Mistani, Shervin Minaee, Emad
Fatemizadeh, “Multispectral Palmprint Recognition
Using a Hybrid Feature” Electrical Engineering
Department, Sharif University of Technology, Tehran,
pp.1-7, 2011.
[28] Kong W.K., Zhang, D., Li W.X., “Palmprint feature
extraction using 2-D Gabor filters.” Pattern recognition,
Vol. 36, pp.2339–2347, 2003.
[29] Zhang W.K. Kong, J. You, M. Wong, “On-line palmprint
identification”, IEEE Transactions on Pattern Analysis
and Machine Intelligence, Vol. 25 (9), pp.1041–1051,
2003.
[30] H. Imtiaz, S. Aich, S. A. Fattah, “A novel pre-processing
technique or DCT domain Palmprint recognition”,
International Journal of Scientific & Technology
Research, Vol.1,Issue 3, pp.31-35, 2012.
[31] D. Hurley, M. S. Nixon, and J., Carter, “Force field
feature extraction for ear biometrics” Computer Vision
and Image Understanding, 98:491–512, 2005.
[32] Bhanu and H. Chen., “Human ear recognition in 3D” ,in
Workshop on Multimodal User Authentication, pages
91–98, 2003.
[33] P. Yan and K. W. Bowyer, “Multi-Biometrics 2D and 3D
ear recognition”. In Audio- and Video-based
BiometricPerson Authentication, pages 503–512, 2005.
[34] H. Shin, S. D. Kim, and H. C. Choi, "Generalized elastic
graph matching for face recognition," Pattern
Recognition Letters, Vol.28, pp.1077–1082, 2007.
[35] P. J. Phillips, H. Moon, P. J. Rauss, and S. A. Rizvi, "The
FERET Evaluation Methodology for Face Recognition
Algorithms," IEEE Transactions on Pattern Analysis and
Machine Intelligence, Vol.22, pp.1090-1104, 2000.
[36] F. Bourel, C. C. Chibelushi, and A. A. Low, "Robust
Facial Feature Tracking," in British Machine Vision
Conference, Bristol, 2000, pp.232-241.
[37] Chen H, Bhanu B, “Contour Matching for 3D Ear
Recognition” , In: Pro-ceedings of the Seventh IEEE
Workshop on Applications of Computer
Vision(WACV/MOTION); 2005.
[38] Islam S, Davies R, Bennamoun M, Mian A, “Efficient
Detection and Recognition of 3D Ears”, International
Journal of Computer Vision. 2011;95:52.
[39] Yan P, Bowyer KW, “Biometric Recognition Using 3D
Ear Shape”,Pattern Analysis and Machine Intelligence.
2007 August;29:1297 -1308.
[40] Dasari Naga Shailaja, “ A Simple Geometric Approach
for Ear Recognition” , department of computer science
and engineering.
[41] J. Beveridge, K. She, B. Draper, and G. Givens (2001),
“A Nonparametric Statistical Comparison of Principal
Component and Linear Discriminant Subspaces for Face
Recognition,” Proc. IEEE Conf. Computer Vision and
Pattern Recognition, 535-542.
[42] Hao Mang, Cuiping Xu (2006), “Iris Recognition
Algorithms based on Gabor Wavelet Transforms”,
Proceedings of the 2006 IEEE International Conference
on Mechatronics and Automation, Luoyang, China,
1785-1789.
[43] L. Ma, Y. Wang, and T. Tan, “Iris Recognition Using
Circular Symmetric Filters” Proc. 16th Int‘l Conf.
Pattern Recognition, vol. II, pp. 414-417, 2002.
[44] Seung-In Noh, Kwanghuk Pae, Chulhy Lee, Jaihie Kim,
“Multiresolution Independent Component
Identification”, Proceedings of the 2002 International
Technical Conference on Circuitd Systems, Computers
and Communications, Phuket, Thailand, (2002).
[45] Ma, Li, Tan, Tieniu, Wang, Yunhong, “Iris recognition
using circular symmetric filters”, Proceedings of the 16th
International Conference on Pattern Recognition, V01.2,
(2002), pp. 414 -417.
[46] Lim S., Lee K., Byeon O., Kim T., “Efficient Iris
Recognition through Improvement of Feature Vector and
Classifier”, Journal of Electronics and
Telecommunication Research Institute, Vol. 23, No. 2,
(2001), pp. 61 - 70.
[47] Dargham, J. A., Chekima, A., Liau Chung Fan and Lye
Wil Liam, “Iris recognition using self-organizing neural
network”, Student Conference on Research and
Development, (2002), pp. 169 -172.
[48] Uma Shankar Kurmi, Dheeraj Agrawal, R. K. Baghel,
“Study of Different Face Recognition Algorithms and
Challenges” ,Dept. of Electronics & Communication,
Maulana Azad National Institute of Technology, Bhopal,
India.
[49] Anshuman Prakash,“Study of Different Algorithms for
Face Recognition”, ELECTRONICS &
COMMUNICATION ENGINEERING.
[50] Proyecto Fin de Carrera, “Face Recognition Algorithms”
.
[51] Fernando Alonso-Fernandez ,Josef Bigun, Julia Fierrez,
Hartwig Fronthaler, Klaus Kollreider, “Fingerprint
Recognition” .
[52] Esther Rani P , Shanmugalakshmi R, “Finger Knuckle
Print Recognition Techniques-A Survey” , The
International Journal Of Engineering And Science
(IJES), Volume 2 ,Issue 11,Pages 62-69,2013.
[53] Canny J., “A Computational Approach to Edge
Detection,” IEEE Trans. on Pattern Analysis and
Machine Intelligence, 3 vol. 8, no. 6, 679-698, 1986.
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 652
[54] P. Yan, K. W. Bowyer, ”ICP-based approaches for 3D
ear recognition,” Proc. of SPIE Biometric Technology
for Human Identification, 282-291, 2005.
[55] Muzhir Shaban Al-Ani , “A Novel Thinning Algorithm
for Fingerprint Recognition” , International Journal of
Engineering Sciences.
[56] Avinash Pokhriyal et. al., “MERIT: Minutiae Extraction
using Rotation Invariant Thinning”, International
Journal of Engineering Science and Technology Vol.
2(7), 2010, 3225-3235.
[57] L. Ravi Kumar1, S. Sai Kumar2, J. Rajendra Prasad3, B.
V. Subba Rao4, P. Ravi Prakash5 “ Fingerprint Minutia
Match Using Bifurcation Technique”, S Sai Kumar et al
, International Journal of Computer Science &
Communication Networks,Vol 2(4), 478-486, Sep. 2012.
[58] Muzhir Shaban Al-Ani et. al., “Face Recognition
Approach Based on Wavelet-Curvelet Technique”,
Signal & Image Processing: An International Journal
(SIPIJ) Vol.3, No.2, April 2012.
[59] Nabanita basu , “Comparative study of the different
feature extraction algorithms used for fingerprint
identification”.
[60] Sangram Bana , Dr. Davinder Kaur, “Fingerprint
Recognition using Image Segmentation”
,INTERNATIONAL JOURNAL OF ADVANCED
ENGINEERING SCIENCES AND TECHNOLOGIES ,
Vol No. 5, Issue No. 1, 012 – 023.
[61] Ren Qun, Tian Jie, He Yuliang and Cheng Jiangang,
“Automatic Fingerprint Identification Using Cluster
Algorithm” .
[62] G. Lu, D. Zhang, K. Wang, Palm print recognition using
eigenpalms features, Pattern Recognition Letters 24 (9)
(2003) 1463–1467.
[63] Gyaourova and A. Ross, “Index codes for multibiometric
pattern retrieval,” IEEE Trans. Inf. Forensics Security,
vol. 7, no. 2, pp. 518–529, Apr. 2012.
[64] J. Dai, J. Feng, J. Zhou, “Robust and Efficient Ridge-
Based Palmprint Matching,” IEEE Transaction on
Pattern Analysis and Machine Intelligence, Vol.34, No.
8, pp. 0162-8828, August 2012
[65] J. You, W. Kong, D. Zhang, and K. Cheung, “On
hierarchical palmprint coding with multiple features for
personal identification in large databases,” IEEE Trans.
Circuits Syst. Video Technol., vol. 14, no. 2,pp. 234–
243, Feb. 2009.
[66] Kong and D. Zhang, “Competitive coding scheme for
palmprint verification,” in Proc ICPR, 2011, pp. 520–
523.
[67] Huang,W. Jia, D. Zhang, “Palmprint verification based
on robust line orientation code,” Pattern Recognition,
Science Direct, pp. 1504 – 1513, 2008.
[68] S. M. Prasad, V. K. Govindan, P. S. Sathidevi,
“Palmprint Authentication Using Fusion of Wavelet
Based Representations,” IEEE, pp. 978-1-4244-5612-3,
2009.
[69] R. Cappelli, M. Ferrara, and D. Maio, “A Fast and
Accurate Palmprint Recognition System Based on
Minutiae,” IEEE Transaction on System, Man and
Cybernetics- Part B: Cybernetics, Vol. 42, No. 3, pp.
1083-4419, June 2012.
[70] Ali Hussein Ali Al-Timemy , “A Robust Algorithm for
Ear Recognition System Based on Self Organization
Maps” , The 1Regional Conference of Eng. Sci. NUCEJ
Spatial ISSUE vol.11,No.2, 2008 pp 315-321.
[71] P. Yan, K. W. Bowyer, ”ICP-based approaches for 3D
ear recognition,” Proc. Of SPIE Biometric Technology
for Human Identification, 282-291, 2005.
[72] Victor, B., Bowyer, K., Sarkar, S. An evaluation of face
and ear biometrics in Proceedings of International
Conference on Pattern Recognition, pp. 429-432.
[73] Hurley, D.J., Nixon, M.S., Carter, J.N. A New Force
Field Transform for Ear and Face Recognition. In
Proceedings of the IEEE 2000 International Conference
on Image Processin ICIP 2000b, pp. 25-28
[74] Burge, M. and Burger, W. Ear Biometrics. In A. Jain R.
Bolle and S. Pankanti, editors, BIOMETRICS: Personal
Identification in a Networked Society, pp. 273-
286.KluwerAcademic, 1998.
[75] Moreno, B., Sánchez, Á., Vélez. J.F. On the Use of Outer
Ear Images for Personal Identification in Security
Applications. IEEE 33 rd Annual International Carnahan
Conference on Security Technology, 1999, pp. 469-476.
[76] Hancock E., Kittler J., ”Edge-labeling Using Dictionary-
based Relaxation,” IEEE Trans. on Pattern Analysis and
Machine Intelligence, vol. 12, no. 2, 165-181, 1990.
[77] IshaDas, SrinivasaRajaG,”3d Ear Shape Biometric
Recognition by Using Ica Alorithm” , IOSR Journal of
Engineering.
[78] Muzhir Shaban Al-ANI , Wasan M. Al-Aloosi ,
“Biometrics Fingerprint Recognition using Discrete
Cosine Transform (DCT) ”, International Journal of
Computer Applications (0975 – 8887),Volume 69–
No.6, May 2013.
[79] Usha R.Kamble, L.M.Waghmare, “Iris Recognition
using Cumulative Sums based Approach and DCT” ,
International Conference on Emerging Technology
Trends on Advanced Engineering Research (ICETT’12)
.
[80] Koichi Ito, Takafumi Aoki, Hiroshi Nakajima, Koji
Kobayashi and Tatsuo Higuchi, “A PALMPRINT
RECOGNITION ALGORITHM USING PHASE-
BASED IMAGE MATCHING” , Graduate School of
Information Sciences.
[81] Yen –po Lee, “Palm vein recognition based on a
modified (2D)2 LDA” , Springer-Verlag.
[82] Zhang Xiaoxun , “symmetrical null space LDA for face
and ear recognition” ,
[83] Department of computer science ang engineering,
Beijing institute of Technology, Beijing 100081, PR
China.
[84] Shashi Kumar D R, K B Raja, R K Chhotaray,Sabyasachi
Pattanaik , “DWT Based Fingerprint Recognition using
Non Minutiae Features” , IJCSI International Journal of
Computer Science Issues, Vol. 8, Issue 2, March 2011
ISSN (Online): 1694-0814 .
[85] Jyoti Rajharia , P.C. Gupta, “A New and Effective
Approach for Fingerprint Recognition by using Feed
Forward Back Propagation Neural Network” ,
International Journal of Computer Applications (0975 –
8887)Volume 52– No.10, August 2012.
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 653
[86] Koichi Ito, Ayumi Morita, Takafumi Aoki, Hiroshi
Nakajima,Koji Kobayashi, and Tatsuo Higuchi , “A
Fingerprint Recognition Algorithm Combining Phase-
Based Image Matching and Feature-Based Matching” ,
Graduate School of Information Sciences, Tohoku
University.
[87] Jinfeng Yang, Yihua Shi, Jinli Yang , “Finger-Vein
Recognition Based on a Bank of Gabor Filters”, Springer
Berlin Heidelberg.
[88] Pallavi D.Wadkar, Megha Wankhade , “FACE
RECOGNITION USING DISCRETE WAVELET
TRANSFORMS” , International Journal of Advanced
Engineering Technology.
[89] Ms.Lenina Vithalrao Birgale, Manesh Kokare , “Iris
Recognition Using Discrete Wavelet Transform”,
International Conference on Digital Image Processing.
[90] K.vaidehi, T S.subashini, V Ramalingam, S Palanivel
and M Kalaimani. Article: Transform based approaches
for Palmprint Identification. International Journal of
Computer Applications 41(1):1-5, March 2012.
Published by Foundation of Computer Science, New
York, USA
[91] Gagandeep Bhatia, “Extraction of Unique Feature Sets
(Bio-metric Identifier)For Human Ear’s Image using
DWT Analysis” , International Journal of Scientific
Research Engineering & Technology (IJSRET) Volume
2 Issue2 pp 066-071 May 2013.
[92] Basit , M. Shoaib, “A human ear recognition method
using nonlinear curvelet feature subspace” ¸ International
Journal of Computer MathematicsVolume 91, Issue 3,
2014.
[93] Murat Ekinci , Murat Aykut, “Palmprint Recognition by
Applying Wavelet-Based Kernel PCA”, JOURNAL OF
COMPUTER SCIENCE AND TECHNOLOGY 23(5):
851–861 Sept. 2008.
[94] R. Raja Sekar, K. Meena, “Fingerprint Recognition
Using Multi-Resolution Techniques”, International
Journal of Electronics Communication and Computer
Engineering Volume 4, Issue (2) ICEA-2013, ISSN
2249–071X.
[95] Jie Sun,Zhe-Ming Lu, Lijian Zhou, “Iris Recognition
Using Curvelet Transform Based on Principal
Component Analysis and Linear Discriminant
Analysis”, Journal of Information Hiding and
Multimedia Signal Processing ©2014 ISSN 2073-4212
Ubiquitous International Volume 5, Number 3, July
2014.
[96] G.Seshikala, U.P.Kulkarni, M.N.Giri Prasad, “Feature
Fusion of Palm and Face Based on Curvelet Transform”
, IJCSN International Journal of Computer Science and
Network, Volume 3, Issue 1, February 2014 ISSN
(Online) : 2277-5420 .
[97] Vinay Kumar B, “Face Recognition Using Gabor
Wavelets” , Visvesvaraya Technological University,
Belgaum .
[98] avinash pokhriyal, sushma lehri, “ a new method of
fingerprint authentication using 2d wavelets”, Journal of
Theoretical and Applied Information Technology.
[99] Ajita Singh, Jayesh Gangrade, “An Iris Feature
Extraction Using 2D-Dual Tree Complex Wavelet
Transform”, International Journal of Engineering and
Advanced Technology (IJEAT) ISSN: 2249 – 8958,
Volume-2, Issue-6, August 2013.
[100] Ali Mohsin, Al-juboori, Wei Bu ,Xiangqian Wu,
Qiushi Zhao, “Palm Vein Verification Using Multiple
Features and Isometric Projection” , International
Journal of Signal Processing, Image Processing and
Pattern Recognition Vol.7, No.1 (2014), pp.33-44.
[101] Nosrati M.S., “Using 2D wavelet and principal
component analysis for personal identification based on
2D ear structure”, ieeexplore.ieee.org.
[102] Rahman Khorsandi, Steven Cadavid, Mohamed
Abdel-Mottaleb, “Ear recognition via sparse
representation and Gabor filters”.
[103] Ali Mohsin ,Al-juboori, Wei Bu, Xingqian
Wu,Qiushi Zhao, “Palm Vein Verification Using Gabor
Filter”, IJCSI International Journal of Computer Science
Issues, Vol. 10, Issue 1, No 1, January 2013.
[104] Sanchez-Avila, R. Sanchez-Reillo , “Two different
approaches for iris recognition using Gabor filters and
multiscale zero-crossing representation”Gabor Ear
Recognition via Sparse Rep
[105] Vitomir Struc, Rok Gaj sek and Nikola Pave si c,
“Principal Gabor Filters for Face Recognition”,Journal
of Computational and Applied Mathematics, Volume
227, Issue 2, 15 May 2009, Pages 294–307.
[106] Javier A. Montoya Zegarra, Neucimar J. Leite,
Ricardo da Silva Torres, “Wavelet-based fingerprint
image retrieval”, Special Issue on Emergent
Applications of Fractals and Wavelets in Biology and
Biomedicine
[107] Monika Rout , “Enhancement of Retinal Fundus
Image Using 2-D GABOR WAVELET Transform” .
[108] Ling Fan , Tan Kah Kee Coll, Xiamen Univ,
Zhangzhou, China, Hong Duan , Fei Long, “Face
recognition by subspace analysis of 2D Log-Gabor
wavelets features” ,ieee.org.
[109] Rajesh Malviya, Roopesh Kumar, Anil Dangi,
Pankaj Kumawat, “Verification of Palm Print Using Log
Gabor Filter and Comparison with ICA”, International
Journal of Computer Applications in Engineering
Sciences [vol i, special issue on CNS, July 2011].
[110] Ajay Kumar , David Zhang, “Ear authentication
using Log-Gabor Wavelets”, Proc. SPIE 6539,
Biometric Technology for Human Identification IV,
65390A (April 12, 2007).
[111] Purneet Kaur, Jaspreet Kaur, “Fingerprint
Recognition Using Genetic Algorithm and Neural
Network”, International Journal of Computational
Engineering Research, Vol 03, Issue, 11.
[112] Novruz Allahverdi, “An efficient iris recognition
system based on modular neural networks”.
[113] Rashmi Shrivas, Nilmani Verma, Vikas Singh,
“Palm print Biometrics using Feed Forward Back
Propagation Neural Network”, International Journal of
Computer Applications, (0975 – 8887),Volume 74–
No.3, July 2013 .
[114] Adams Konga, David Zhangb, Mohamed Kamelca,
“A survey of palmprint recognition”, Pattern
Recognition journal homepage:
www.elsevier.com/locate/pr.
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 654
[115] K.Y. Rajput, Melissa Amanna, Mankhush Jagawat,
Mayank Sharma, “Palmprint Recognition Using Image
Processing”, International Journal of Computing Science
and Communication Technologies, VOL. 3, NO. 2, Jan.
2011. (ISSN 0974-3375).
[116] A Region-of-Interest Segmentation Algorithm for
Palmprint Images, Kai-Wen Chuang, Chen- Chung Liu,
Sheng-Wen Zheng, the 29th Workshop on
Combinatorial Mathematics and Computation Theory.
[117] Sepehr Attarchi, Karim Faez, Aref Rafiei , “A New
Segmentation Approach for Ear Recognition”, Systems,
Lecture Volume 5259, 2008, pp 1030-1037.
[118] Lee Luan Ling, Daniel Felix de Brito, “Fast and
Efficient Iris Image Segmentation”, Journal of Medical
and Biological Engineering, 30(6): 381-392 381.
[119] KAMENCAY, Patrik; ZACHARIASOVA,
Martina; HUDEC, Robert; JARINA, Roman; BENCO,
Miroslav; UBIK, Jan HL, “A Novel Approach to Face
Recognition using Image Segmentation Based on SPCA-
KNN Method”, Radioengineering;Apr2013, Vol. 22
Issue 1, p92.
[120] B. S. El-Desouky, M. El-Kady, M. Z. Rashad,
Mahmoud M. Eid, “EAR RECOGNITION AND
OCCLUSION”, International Journal of Computer
Science & Information Technology (IJCSIT) Vol 4, No
6, December 2012DOI : 10.5121/ijcsit.2012.4608
[121] Khamiss Masaoud, S. Algabary, Khairuddin Omar,
Md. Jan Nordin, Siti Norul Huda Sheikh Abdullah, “A
Review Paper on Ear Recognition Techniques: Models,
Algorithms and Methods”, Australian Journal of Basic
and Applied Sciences, 7(1): 411-421, 2013ISSN 1991-
8178.
[122] Tagging Chunhui Zhu, Fang Wen Jian, “A Rank-
Order Distance based Clustering Algorithm for Face”.
[123] Asheer K. Bachoo, Jules R. Tapamo, “Texture
Analysis and Unsupervised Clustering for Segmenting
Iris Images”.
[124] K.Umadevi1 and L.Latha, “AN EFFICIENT
SEARCHING AND CLUSTERING BASED
PALMPRINT IDENTIFICATION”, Research Journal of
Computer Systems Engineering, Vol 04; Special Issue;
June 2013.
[125] Jun Yin, Jingbo Zhou , Zhong Jin , Jian Yang, ”
Weighted Linear Embedding and Its Applications to
Finger-Knuckle-Print and Palmprint Recognition”,
Emerging Techniques and Challenges for Hand-Based
Biometrics (ETCHB), 2010 International Workshop .
[126] Rao, K.R, Ben-Arie, J., “Generic face recognition,
feature extraction and edge detection using optimal
DSNR expansion matching” , Circuits and Systems,
1993., ISCAS '93, 1993 IEEE International Symposium
on.
[127] G. Seshikala, Dr.Umakanth Kulkarni, Dr.M.N.
Giriprasad, “Palm Print Feature Extraction Using Multi
ScaleWavelet Edge Detection Method”, International
Journal of Advanced Research in Electrical, Electronics
and Instrumentation Engineering Vol. 1, Issue 1, July
2012 .
[128] U T Tania, S M A Motakabber, M I Ibrahimy “Edge
detection techniques for iris recognition system”, 5th
International Conference on Mechatronics (ICOM’13)
IOP Publishing IOP Conf. Series: Materials Science and
Engineering 53 (2013) 012041 doi:10.1088/1757-
899X/53/1/012041.
[129] Mela G. Abdul-Haleem, Loay E. George, Huda M.
Al-Bayti, “Fingerprint Recognition Using Haar Wavelet
Transform and Local Ridge Attributes Only”, Volume 4,
Issue 1, January 2014 ISSN: 2277 128X International
Journal of Advanced Research in Computer Science and
Software Engineering Research Paper.
[130] Dr. H. B. Kekre, Dr.Tanuja K. Sarode, Aditya A.
Tirodkar, “An Evaluation of Palm Print Recognition Techniques
using DCT, Haar Transform and DCT Wavelets and their
Performance with Fractional Coefficients” , International Journal of
Computer Applications.
[131] Nazir Ali Shoukat, “A Framework for Face
Recognition using Self Organizing Map (SOM) and Soft
k-NN Ensemble”, International Journal of Application or
Innovation in Engineering & Management (IJAIEM),
Volume 1, Issue 1, September 2012 ISSN 2319 – 4847.
[132] S. Raja, V. Joseph Raj, “A NEW RECOGNITION
TECHNIQUE NAMED SOMP BASED ON
PALMPRINT USING NEURAL NETWORK BASED
SELF ORGANIZING MAPS”.
[133] J.B Hayfron-Acquah, Mavis Sarah Gyimah, “
Classification and Recognition of Fingerprints using Self
Organizing Maps(SOM) ”, IJCSI International Journal of
Computer Science Issues, Vol. 11, Issue 1, No 1, January
2014 ISSN ( 1694-0814).
[134] Ali Hussein Ali Al-Timemy, “A Robust Algorithm
for Ear Recognition System Based on Self Organization
Maps”, The 1stRegional Conference of Eng. Sci. NUCEJ
Spatial ISSUE vol.11,No.2, 2008 pp 315-321 ISSUE
vol.11, No.1,2008 Al-Timemy 315.
[135] Ito, K, Aoki, T. , Hosoi, T. ,Kobayashi, K., “Face
recognition using phase-based correspondence
matching” , Automatic Face & Gesture Recognition and
Workshops (FG 2011), 2011 IEEE International
Conference on,21-25 March 2011,Page-173 - 178
[136] Arman Mehrbakhsh, Alireza Khalilian,
“Experiments with Face Recognition Using a Novel
Approach Based on CVQ Technique” .
[137] M. Alex O. Vasilescu and Demetri Terzopoulos,
“Multilinear Independent Components Analysis”.
[138] Xiaoyong Wang , Xiaojun Jing ,Xifu Zhu ,Songlin
Sun , Linbi Hong, “A novel approach of fingerprint
recognition based on multilinear ICA”, Network
Infrastructure and Digital Content, 2009. IC-NIDC 2009.
IEEE International Conference on, 6-8 Nov. 2009,Page-
740 – 744.
[139] N. Poonguzhali, M. Ezhilarasan, “Iris Indexing
Techniques: A Review”, International Journal of Computer
Applications, Volume 73 - Number 18, 2013.
[140] Davide Maltoni, Dario Maio, Anil K. Jain, Salil
Prabhakar, “Handbook of Fingerprint Recognition”,
Springer, 21-Apr-2009 - Law - 512 pages
[141] Ayan Seal, Suranjan Ganguly, Debotosh
Bhattacharjee, Mita Nasipuri and Dipak Kr. Basu,
“Automated Thermal Face recognition based on
Minutiae Extraction”.
[142] J.Venkata Suman, Prabhakar
Telagarapu, N.V.Lalitha, G.Vijaya Santhi, “ Finger print
Integrated Biometrics (Face, Fingerprint, Iris, Palmprint & Ear) using PCA
(IJSRD/Vol. 6/Issue 09/2018/165)
All rights reserved by www.ijsrd.com 655
recognition using minutiae extraction for bank locker
security”, national conference.
[143] Karima Ouji, Boulbaba Ben Amor, Mohsen
Ardabilian,Faouzi Ghorbel, Liming Chen, “3D Face
Recognition using ICP and Geodesi Computation
Coupled Approach
[144] V. Starovoitov, D. Samal, “A GEOMETRIC
APPROACH TO FACE RECOGNITION”.
[145] Min, M.M, Thein, Y, “Intelligent Fingerprint
Recognition System by using geometry approach” ,
Current Trends in Information Technology (CTIT), 2009
International Conference ,15-16 Dec. 2009,Page-1 - 5
[146] Dr.Tamijeselvy Perumal, Shilpa Somasundar , “Ear
Recognition Using Kernel Based Algorithm”,
International Journal of Science, Engineering and
Technology Research (IJSETR), Volume 3, Issue 4,
April 2014.
[147] V. V. Satyanarayana Tallapragada , E. G. Rajan ,
“IRIS Recognition based on Non Linear Dimensionality
Reduction of IRIS Code with KPCA and SVM based
Classification” International Journal of Computer
Applications (0975 – 8887),Volume 44– No13, April
2012.
[148] Jawad Nagi, Syed Khaleel, Ahmed Farrukh Nagi,
“A MATLAB based Face Recognition System using
Image Processing and Neural Networks”.
[149] Laurenz Wiskott, Jean-Marc Fellous,Norbert
Kr¨uger, Christoph von der Malsburg, “Face Recognition
by Elastic Bunch Graph Matching”.
[150] R.M. Farouk, “Iris recognition based on elastic
graph matching and Gabor wavelets” , Understanding,
Volume, August 2011, Pages 1239–1244
[151] Jucheng Yang , Yanbin Jiao, Jinfeng Yang,Zhijun
Fang , Congcong Xiong, Lei Shu , “ Image Latent
Semantic Analysis for Face Recognition”.