A review on fake biometric detection system for various applications

IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308
_______________________________________________________________________________________
Volume: 05 Issue: 03 | Mar-2016, Available @ http://www.ijret.org 495
A REVIEW ON FAKE BIOMETRIC DETECTION SYSTEM FOR
VARIOUS APPLICATIONS
Payal Patil1
, Malvika Saraf2
1
Research Scholar, Department of Electronics Engineering. W.C.E.M, Nagpur, Maharashtra, India.
2
Assistant Professor, Department of Electronics Engineering. W.C.E.M, Nagpur, Maharashtra, India.
Abstract
Now a days Security is a major concern for Scenario. So many securities are available but it should be reliable. A biometric
system is a computer system which is related to the human characteristic. It is mainly used in identification and access control on
their behavioral and physiological category. For example signature, voice, retina, key stroke, face, iris and fingerprint etc. This
paper introduces a software base multi attack protection method which is based on various biometric modalities such as iris, face,
signature and hand palm image.. This Hand palm technique is used for physical access. The real and fake images are identified by
using image quality assessment (IQA) technique. Fake identities always have some different feature than original such as
sharpness, different color, information quality etc. In this paper, liveness detection method is used. Which provide a very good
performance and low degree of complexity. Also quality of Image is using two methods Full- Reference (FR) and No-Reference
(NR). This image quality assessment (IQA) method is suitable for real time application which has been used for very low
complexity.
Keyword: Statistical Feature Extraction Biometric, Attack, Image Quality Assessment, Full-reference IQA, NO-
Reference IQA,.
---------------------------------------------------------------------***---------------------------------------------------------------------
1. INTRODUCTION
The terms ―Biometric‖ system related to the technology.
That means bio (life) and metric (measure).It analyze the
human characteristics, such as face, iris, hand, fingerprint
etc. This system also recognizes person according to their
characteristics. The physiologic Characteristics are related to
the size of the organs for example face, iris, retina, etc. and
Behavioral characteristics are related to behavior of person
[4] i.e. Voice, signature, keystroke etc. Biometric system
divides in sensing, feature extraction, and matching
modules.
In this paper, Image Quality Assessment (IQA) is used to
determine the real and fake image. which depend on multi
attack and multi biometric protection method. IQA is able to
perform under different biometric system and spoofing
scenarios. It also provides very good protection level again
certain Non-spoofing attacks. Image quality assessment
consists of two methods such as subjective and objective
method. Subjective method gives best results, related to the
human vision but this method is more expensive and costly.
Objective method is used to determine the quality of image
depending on the point of view of original image.
Image quality measurements are used to design and
implement a system that provides security against the fake
image by using IQA technique. Fake identities always have
some different feature than original image (real).The IQA
measurement of structural distortion should be a good
approximation. So the efficient and accurate measures
should certainly enhance their applicability in real world
application.
2. SECURITY OF BIOMETRIC SYSTEM
In the security level of biometric system is improved by first
detecting the fake image and then removes that image. It is
mainly used in identification and access control on their
behavioral and physiological category. For example
Signature scan is used to measure the speed and pressure
stroke. Voice measure the sound wave, Retina measures the
unique characterize of blood vessel and vein pattern, also it
include Key stroke, face, iris and fingerprint etc.
Fig-1: Internal Structure of biometric system
This paper introduce, a Software base multi attack
protection method which is based on various biometric
modalities such as iris, face, signature and hand palm image
are said to be consider. This Hand palm technique is used
for physical access.

_______________________________________________________________________________________
The Biometric system consists of two models such as
verification and identification mode. The first mode is the
verification also it called authentication. In verification
mode it performs one to one comparison between captured.
Fig-2: Basic Block Diagram of Biometric
In fig.2 shows feature extractor module is used to correct the
feature and extracted from the source.[5][6]
During enrollment process,[3] biometric information is
captured and stored in templates, from a single source. The
data base, card, or both are stored in templates .During
matching module the stored template is passed to the
matcher, and compare with existing templates. The
matching program analyzes the template from the individual
input source.
3. IMAGE QUALITY ASSESSMENT METHOD
In image processing system, The Quality Assessment (QA)
of an image measures its reduction at different stages such
as acquisition, compression, transmission, and reproduction.
The quality of image depends on by environmental disasters
such as adverse brightness, noise, blur. Predicting quality
should be accurate, consistent and monotonic for a good
image quality measurement (IQM).image quality
measurement (IQM) is categories into four general methods
such as performance, complementarity, complexity and
speed. Image quality approaches for good performance and
high computation load which has been considered.
The evaluation of image quality assessment further
classified into two devices such as subjective and objective
method as shown in fig2.
The Subjective experiment is used for viewing distance,
display device, lighting condition, subjective mood, and
vision ability. The main approach of Objective image
quality assessment is used for mathematical tool which are
capable to an image quality accurately. Objective quality
assessment method can be classified into two main types.
The first type is Full-reference and last is No-reference
image. The References image of perfect quality is fully
available in FR-IQA method. The FR IQA methods are used
for gray scale image in full references including (MSE,
PSNR, SNR, SC, MAS, and MAMS) etc. This FR-IQA
Method used for color image. It has different dynamics
range NR-IQA method used color image it has different
dynamic range.NR-IQA Method in which don‘t have access
to the references image also determined the quality level of
image.
Fig-3: Classification of IQA method
4. LITERATURE SURVEY
I. “Javier Globally, Sebastian Marcel, Member, and
Julia Fierez”. IEEE Transactions on image
processing, vol.23, no 2, February 2014.
 Image Quality Assessment for Fake Biometric
detection:
 This paper proved, image quality assessment (IQA)
technique used in fake biometric detection system also
provide very good performance again multi-attack (non-
spoofing).
 It used for multitask and multi biometric protection
method.
 This paper has used liner discriminate analysis (LDA)
and quadratic discriminate analysis (QDA) for iris and
fingerprint modality.
II. J.Galball,J.Ortizlopez,J.Fierrez.andJ.Ortega-
Garcia”inproc.5thIAPR Mar/Apr.2012
 IrisLiveness Detection Based on Quality Related
Features:
 In this paper, new parameterizations based on Quality
related measure. This is used in software for iris livness
detection.
Enrollment
Stored
templates
Template
Generator
Feature
Extractor
Matcher
Application
devices
Image quality Assessment
Subjective Objective
Single
stimulates
Double
stimulates
Full-
Reference
No-
Reference
Mathematical
metrics
Other
metrics

_______________________________________________________________________________________
 Hough transform used to detected iris from the
background.
 Image quality measure IQM is used for high frequency
to detected fake image. Real sample will different from
fake image.
 It is also tried to detected external element by using
feature extraction module that are eyelid or eye lashed.
III. “Zhou Wang, student Member, IEEE and Alan
C.Bovik”fellow, IEEE signal processing letter,
March.
 Universal Image Quality Index:
 In this paper, there are various images processing
applicable for easy to calculate the error. In Image
quality index there are combination of three factors used
that are contrast distortion, loss of correlation and
luminance distortion.
 In contrast distortion, will measuring the similarity of
contrast and dynamic range will be [0, 1].
 Loss of correlation will measures the degree of liner
correlation between ‗x‘ and ‗y‘.It‘s dynamic range will
be [-1, 1].
 In Luminance distortion dynamic range will be [0, 1], it
will measures mean luminance in between ‗x‘ and
‗y‘.Traditional method of error calculated the quality of
image.
IV. “SNEHAS, Mrs. R.INDUMATHI”, IJETS.ISSN
(P):2349-3968 volume 2 Is March-2015.
 Fake Biometric Detection Using Improved Feature in
Image and Dempster-Shafer Method:
 In this paper, software based multi biometric and multi
attack protection method base on image quality
assessment method used to identify whether image are
real and fake.
 It also on adding livens assessment that provides good
performance and low degree of complexity. Various
biometric system used in iris, fingerprint, face and hand
palm.
 This project used for Dempster –Shafer theory in fake
identification.
V. RJayavadivel,Prabhushankar,S.Rajesh”,ISSN
(online):2319-8753 Vol.4, ISSUE7 July 2015.
 Statistical Image Quality Assessment for Fake
Biometric Detection Based on SVM, Application to
Iris and Face Recognition:
 This paper used (IQA) image quality assessment play an
important role for the performance of biometric system
including iris and faces image. Quality of data
assessment is a key word in order to the application of
Iris and face biometric.
 Classified technique of this project SVM support vector
machine is used for training and testing the iris and face
image.
 The real time work on iris and face image which are
applicable for biometrics system that should be done by
efficient.
VI. “IsmailAvcibas, Member, IEE, NasirMember,
IEEE;transactiononprocessing,vol.12, N2February
2003.
 Steganalysis Using Image Quality Metrics:
 This paper is based on the factor that hiding
information in digital media which requires alterations
of the signal. That introduces some forms of image
quality metric based on distance between an unmarked
image and its filtered image.
 In image quality assessment can be used to describe
between cover image and stego images.
 In Steganalysis used for low pass filtering which is
based on Gaussian surface. Image quality metric based
on distances between an unmarked image and its
filtered version.
5. CONCLUSION
In above Literature survey, we can conclude that important
element in Quality of image metrics by improving in
robustness of large real word of biometrics system, they are
simple fast non-intrusive user friendly and cheap. In
additional to verify the competitive performance they show
multi biometrics and multi attack characteristics. They are
also used in livness detection technique refer to the ability to
detect particular properties such as face, finger, iris etc.
In this paper, we are going to implemented method to
analyze different database, acquisitions, condition and
different attack of scenarios. For remove the noise and blur
image we used Low pass Filter to improve the quality level
of image by using image quality assessment technique
(IQA).In our project we detected various biometric
application such as Iris, Face, Hand and Signature. This
technique are used in ATM machine, Banking sector,
Airport, Railway, Home appliances in fake biometric
detection system.
REFERENCES
[1]. Javier Galbally, Sebastian Marcel, Member, IEEE, and
Julian Fierrez, February 2014 Image Quality Assessment for
Fake Biometric Detection: Application to Iris, Fingerprint,

_______________________________________________________________________________________
and Face Recognition IEEE Transactions On Image
Processing, Vol. 23, No. 2.
[2]. D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar.
Handbook of Fingerprint Recognition. Springer Verlag,
New York, NY, USA, June 2003
[3]. T. van der Putte and J. Keuning. Biometrical fingerprint
recognition: don‘t get your fingers burned. In Proceedings of
IFIP TC8/WG8.8 Fourth Working Conference on Smart
Card Research and Advanced Applications, pages 289– 303.
Kluwer Academic Publishers, September 2000.
[4]. J. Blommé. Evaluation of biometric security systems
against artificial fingers. Master‘s thesis LITH-ISY-
EX3514-2003, Department of Electrical Engineer- ing,
Linköping University, Linköping, Sweden, October 2003
[5]. Jain, Anil K.; Ross, Arun (2008). "Introduction to
Biometrics". In Jain, AK; Flynn; Ross, A. Handbook of
Biometrics. Springer. pp. 1–22. ISBN 978-0-387-71040-2.
[6] Sahoo, SoyujKumar; Mahadeva Prasanna, SR,
Choubisa, Tarun; Mahadeva Prasanna, SR (1 January 2012).
"Multimodal Biometric Person Authentication : A Review".
IETE Technical Review 29 (1): 54. doi:10.4103/0256-
4602.93139 (inactive 2015-01-04). Retrieved 23 February
2012
[8]. Z.Sun and T.Tan, 2011, Ordinal measures for iris
recognition, IEEE Trans. on Pattern Analysis and Machine
Intelligence, vol. 31, no. 12, pp. 2211–2226, Dec. 2009.
2011 18th IEEE International Conference on Image
Processing.
[9]. Z.Wei, T.Tan, Z.Sun, and J.Cui, 2005, Robust and fast
assessment of iris image quality, in Proc. Int. Conf. on
Biometrics, vol. 3832, pp. 464–471, LNCS 3832
[10]. N.D. Kalla, J.Zuo, N.A.Schmid, and B.Cukic, 2010,
Estimating and fusing quality factors for iris biometric
images, IEEE Trans. on Systems, Man, and Cybernetics—
Part A: Systems and Humans, vol. 40, no. 3, pp. 509–524.
[11]. Belcher and Y.Du, 2008, A selective feature
information approach for iris image-quality measure, IEEE
Trans. on Information Forensics and Security, vol. 3, no. 3,
pp. 572–577
[12]. J.Zuo, F.Nicolo, Natalia A.Schmid, and H.Wechsler,
2010, Adaptive biometric authentication using nonlinear
mappings on quality measures and verification scores.
[13]. U. M. Chaskar, M. S. Sutaone, N.S. Shah, Jaison T,
May 2012, Iris Image Quality Assessment For Biometric
Application, IJCSI International Journal of Computer
Science Issues, Vol. 9, Issue 3, No 3, ISSN (Online): 1694-
0814 www.IJCSI.org.
[14]. Kshamaraj Gulmire, Sanjay Ganorkar, Iris
Recognition: An emerging biometric technology, IOSR
Journal of Electronics and Communication Engineering
(IOSR-JECE) www.iosrjournals.org
[15]. Damer, N et al, Biometric source weighting in multi-
biometric fusion: Towards a generalized and robust solution
Signal Processing Conference (EUSIPCO), Sept. 2014
BIOGRAPHIES
Payal R. Patil is a M.tech students from
W.C.E.M Nagpur, Maharashtra, India. She
completed Diploma in Electronics and
telecommunication from G.H. polytechnic
in 2010. She completed B.E. in
Electronics and telecommunication from
G.H.Raisoni institute of Engineering and
Technology for Women, from Rashtrasant Tukadoji
Maharaj Nagpur University, Maharashtra in 2013. Her
areas of interest Digital communication, Microcontroller,and
image processing
Malvika U. Saraf is the Head of
Electronics / Electronics and
Telecommunication from Wainganga
college of Engineering and Management,
Nagpur, Maharashtra, India she
completed Mtech from G.H.Raisoni
institute of Engineering and Technology
for Women, from Rashtrasant Tukadoji Maharaj Nagpur
University, Maharashtra. She has an experiences of about 6
year in teaching field She has 2 year of industrial
experience. HER areas of interest are Digita Image
Processing Digital Design.

A review on fake biometric detection system for various applications

More Related Content

What's hot (20)

Similar to A review on fake biometric detection system for various applications (20)

More from eSAT Journals (20)

Recently uploaded (20)

A review on fake biometric detection system for various applications