See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/221173670

Biometric technologies and applications

Conference Paper · January 2007

Source: DBLP

CITATIONS READS
24 3,170

2 authors:

Patrick Shen-Pei Wang Svetlana Yanushkevich

Northeastern University The University of Calgary
236 PUBLICATIONS   3,068 CITATIONS    250 PUBLICATIONS   1,593 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Machine Reasoning for Decision support View project

Risk Assessment for Automated Border Control View project

All content following this page was uploaded by Patrick Shen-Pei Wang on 01 June 2014.

The user has requested enhancement of the downloaded file.

 BIOMETRIC TECHNOLOGIES AND APPLICATIONS
Patrick S. P. Wang Svetlana N. Yanushkevich
Northeastern University Biometric Technology Laboratory
Boston, MA, USA University of Calgary Calgary, Alberta, Canada
email: [email protected] email: [email protected]

ABSTRACT corresponding computer models, is somewhat opposite to

Biometric technologies focus on the verification and iden- identification, which require signal processing with the pur-
tification of humans using their possessed biological pose of featuring the models used for recognition. How-
(anatomical, physiological and behavioral) properties. This ever, we could generate a synthetic face from its corre-
paper overview current advances in biometric technologies, sponding computer model. Such a model could include
as well as some aspects of system integration, privacy and muscular dynamics to model facial expressions.
security and accompanying problems such as testing and In Table 1, the basic terminology of synthetic biomet-
evaluation. rics is given. In particular, the term “face reconstruction”
indicates a class of problems aimed at synthesizing a model
KEY WORDS of a static face. The term “mimics animation” is defined as
Biometrics, intelligent systems, security, image processing, the process of modeling facial appearance and facial topol-
pattern recognition. ogy, a behavioral characteristic called facial expression, the
visible result of synthetic emotion.
1 Introduction
Biometric technology may be defined as the automated use
2 Direct Biometrics
of physiological or behavioral characteristics to determine
The term direct biometrics refer to traditional human recog-
or verify an individual’s identity. The word biometric also
nition methods. The most recent development and applica-
refers to any human physiological or behavioral charac-
tions of biometric technologies largely rely on the funda-
teristic which possesses the requisite biometric properties
mental definition of pattern matching, which require learn-
[1,2]. They are:
ing (analysis) and recognition (synthesis).
Universal (every person should have that characteristic), The significant progress have been achieved in this
Unique (no two people should be exactly the same in area since developing the computer-aided tools for signal
terms of that characteristic), (images, audio signal and other) processing, analysis and
Permanent (invariant with time), pattern recognition systems [3].
Collectable (can be measured quantitatively),
Reliable (must be safe and operate at a satisfactory per-
formance level), 2.1 Biometric data analysis and pattern recognition
Acceptable (non-invasive and socially tolerable), and
Non-circumventable (how easily the system is fooled into The problem of analysis of biometric information has long
granting access to impostors). been investigated. Many researchers have provided ef-
ficient solutions for human authentication based on sig-
Biometric technologies attempt to generate computer nature, fingerprints, facial characteristics, hand geometry,
models of the physical and behavioural characteristics of keystroke analysis, ear, gait, iris and retina scanning. Ac-
human beings with a view to reliable personal identifica- tive research is being conducted using both traditional and
tion. The above characteristics include visual images and emerging technologies, to find better solutions to the prob-
other human phenomena such as speech, gait, odour, DNA, lems of verification where claimants are checked against
and indeed anything at all which might help to uniquely their specific biometric records in a database, and identi-
identify the individual. fication where a biometric database is searched to see if a
Biometric technologies are usually thought as im- particular candidate can be matched to any record.
plementation of pattern recognition algorithms, since it is Detailed descriptions and analysis of the principles,
aimed at identifying humans. It, therefore, adapts methods methods, technologies, and core ideas used in biometric au-
and algorithms from computer vision, but it is not restricted thentication systems can be found in [2,4]. It explains the
to visual images. definition and measurement of performance and examines
Recently, the other direction of the biometrics, the factors involved in choosing between different biomet-
namely biometric synthesis, has obtain more attention. rics. It also delves into practical applications and covers
Synthesis, or rendering biometric phenomena from their the parameters critical for successful system integration:
 Table 1. Direct and inverse problems of biometric technology.
DIRECT PROBLEM INVERSE PROBLEM
Signature identification Signature forgery
Handwriting character recognition Handwritten text forgery
face recognition Face reconstruction and mimics animation
Voice identification and speech recognition Voice and speech synthesis
Iris and retina identification Iris and retina image synthesis
Fingerprint identification Fingerprint imitation
hand geometry identification Hand geometry imitation
Infrared identification infrared image reconstruction
Gait identification Gait modeling
Ear identification Ear-print imitation

recognition accuracy, total cost of ownership, acquisition teraction which enable input of handwriting and signatures
and processing speed, intrinsic and system security, privacy [8,9].
and legal requirements, and user acceptance.
2.5 Faces
2.2 Multimodal biometrics
Face recognition systems detect patterns, shapes, and shad-
Through rapid advancements and developments of past ows in the face, perform feature extraction and recognition
years, there have been tremendous achievements have been of facial identity. In the broader view, it include all types of
reach in improvement of reliability of recognition. For facial processing such as tracking, detection, analysis and
example, there have been developed character recognition synthesis.
methods that can reach as high as almost 99.99% accuracy The most popular approach is based on eigenfaces,
rate [3]. However, real-life environments pose significant that represent the differences between the face under recog-
difficulties on biometric-based recognition systems. To in- nition and the enrolled ones in the database. The principle-
crease overall reliability, the contemporary biometric sys- component analysis using higher-order statistics is the un-
tems measure multiple physiological or behavioral traits. derlying mathematics for this facial pattern recognition.
This approach is called multimodal biometrics (see Hand- Many biometric systems are confused when identify-
book of Multibiometrics [5]. ing the same person smiling, aged, with various accessories
The most often multi-biometric data, employed in the (moustache, glasses), and/or in badly lit conditions. For ro-
biometric systems, include iris and retina of the eye, fin- bustness of recognition, advanced techniques such as mor-
gerprint, geometry and palmprint of the hand, and also face phable models and expression-invariant face representation
and ears. For example, face geometry is a highly dynamic methods. On the other hand, facial recognition tools can be
but reach topological structure (smile, lip, brow, and eye improved by training on a set of synthetic facial expressions
movements). Combining facial images with more static and appearance/environment variations generated from real
biometric such as fingerprint, is an example of the concept facial images [10,11].
of multibiometrics. The most advance on-going research in this area is
The multimodal human recognition is deployed in devoted to understanding of how humans can routinely per-
physical access security systems and other areas such as form robust face recognition, in order to improve machine
banking systems [1,5,6]. recognition of human faces. This research is relevant to
computer vision paradigm. A comprehensive references to
2.3 Fingerprints the current state-of-the-art approaches to face processing
can be found in [12].
Fingerprint is, perhaps, the oldest type of biometrics, used
in ancient world. The most popular utilization example of 2.6 Iris and retina
fingerprints is forensic investigations [7]. Today’s finger-
print readers is the most developed type of biometric sen- Iris recognition systems scan the surface of the iris to com-
sors. pare patterns. It was Daugman who first introduced so-
called Daugman code to represent an iris pattern. The
2.4 Signatures iris biometrics is considered to be the most reliable one,
as the plots for comparing the hamming distances for 9.1
Current interest in signature analysis is motivated by the million iris comparisons to the Beta-binomial distribution
development of improved devices for human-computer in- showed that the data fit the distribution remarkably well
[11]. Retina recognition systems scan the surface of the as passive surveillance, contact, cooperative, non-
retina and compare nerve patterns, blood vessels and such cooperative), environmental factors (light, smog, tem-
features. Various model of the iris, retina, and eye have perature), appearance (aging, camouflage).
been used to improve recognition, and can be found in [14-
16]. Therefore, synthetic biometric data plays an impor-
tant role in enhancing the security of biometric systems.
Traditionally, security strategies (security levels, tools, etc.)
2.7 Gait biometrics are designed based on assumptions about a hypothetical
robber or forger. Properly created artificial biometric data
Gait recognition is defined as the identification of a person provides for detailed and controlled modeling of a wide
through the pattern produced by walking [6,17]. The po- range of training skills, strategies and tactics, thus enabling
tential of gait as a biometric was encouraged by the consid- a better approach to enhancing the system’s performance.
erable amount of evidence available, especially in biome- This study aims to develop new approaches for the detec-
chanics literature [19,20]. A unique advantage of gait as tion of attacks on security systems.
biometrics is that it offers potential for recognition at a dis- The tools for analysis and recognition (direct biomet-
tance or at low resolution, when other biometrics might not rics) of human characteristics have their analogs in the syn-
be perceivable. As gait is behavioural biometrics there is thesis (Figure 1.
much potential for within-subject variation [21]. This in-
cludes footwear, clothing and apparel. Recognition can RECOGNITION AND SYNTHETIC
be based on the (static) human shape as well as on move- IDENTIFICATION OF BIOMETRIC DATA
BIOMETRIC DATA GENERATION
ment, suggesting a richer recognition cue. Model-based
techniques use the shape and dynamics of gait to guide the BEHAVIORAL
PHYSICAL
extraction of a feature vector. MODELS

Gait signature derives from bulk motion and shape

characteristics of the subject, articulated motion estimation VISIBAL BAND
IR BAND
using an adaptive model and motion estimation using de-
ACOUSTIC BAND
formable contours.

DISTANCE
2.8 Other biometrics NEAR DISTANCE
CONTACT
MODELS
A variety of biometrics such as ear geometry [22], odour,
electrocardiogram, keystroke dynamics [1,5] and other KNOWLEDGE
DOMAIN
other physiological and behavioral characteristics are be- SIGNAL DOMAIN
ing investigated to be deployed for human authentication. REPRESENTATION

NON-
CORRELATED
3 Inverse Biometrics CORRELATED
DATA

Synthetic biometrics offer the ways to improve reliability

of the biometric-based systems. It can be accomplished by
providing variations on biometric data mimicking unavail- Figure 1. Analysis-by-synthesis approach in facial image.
able or hard to access data (for example, modeling of badly
lit faces, noisy iris images, “wet” fingerprints etc.) Such
an artificial biometric data are understood as biologically The crucial point of modeling in biometrics is the
meaningful data for existing biometric systems [23,24]. analysis-by-synthesis paradigm. This paradigm states that
Synthetic data can also be used for “spoofing” bio- synthesis of biometric data can verify the perceptual equiv-
metric devices with “forged” data. Summarizing, synthetic alence between original and synthetic biometric data, i.e.,
biometric synthesis based feedback control. For example, facial anal-
Improve data can:
the performance of existing identification sys- ysis can be formulated as deriving a symbolic description
tems. This can be accomplished by using automat- of a real facial image. The aim of face synthesis is to pro-
ically generated biometric data to create statistically duce a realistic facial image from a symbolic facial expres-
meaningful sets of data variations (appearance, envi- sion model [25].
ronmental, and others, including “forgeries”).
Improve the robustness of biometric devices by modeling 3.1 Synthetic fingerprints
the strategies and tactics of forgery.
Improve the efficiency of training systems by providing the Albert Wehde was the first to “forge” fingerprints in the
user-in-training with the tools to model various condi- 1920’s. Wehde “designed” and manipulated the topology
tions of biometric data acquisition (non-contact such of synthetic fingerprints at the physical level. The forgeries
were of such high quality that professionals could not rec- Many biometric systems are confused when identi-
ognize them. Today’s interest in automatic fingerprint syn- fying the same person smiling, aged, with various acces-
thesis addresses the urgent problems of testing fingerprint sories (moustache, glasses), and/or in badly lit conditions
identification systems, training security personnel, biomet- (Fig. 2). Facial recognition tools can be improved by
ric database security, and protecting intellectual property. training on a set of synthetic facial expressions and appear-
Cappelli et al. [26] developed a commercially available ance/environment variations generated from real facial im-
synthetic fingerprint generator called SFinGe. Kuecken ages.
[27] developed a method for synthetic fingerprint genera-
tion based on natural fingerprint formation and modeling
based on state-of-the-art dermatoglyphics.

3.2 Synthetic signatures

The simplest method of generating synthetic signatures is

based on geometrical models [28–30]. Spline methods
and Bezier curves are used for curve approximation, given Figure 2. Modeling of facial accessories, aging, drunk, and
some control points. The following evaluation properties a badly lit faces.
are distinguished for synthetic signatures [31]: statistical,
kinematical (pressure, speed of writing, etc.), geometric,
also called topological, and uncertainty (generated images Usage of databases of synthetic faces in a facial
can be intensively “infected” by noise) properties. A model recognition context has been reported in [38].
based on combining shapes and physical models in syn-
thetic handwriting generation has been developed in [32].
The so-called delta-log normal model was developed in [9]. 3.5 Usage of synthetic biometrics
This model can produce smooth connections between char-
The commercially available synthetic fingerprints gener-
acters, but can also ensure that the deformed characters are
ator [26] has been used, in particular, in the Finger-
consistent with the models. In [33], it was proposed to gen-
print Verification Test competition since 2003. An ex-
erate character shapes by Bayesian networks. By collect-
ample of a tool used to create databases for finger-
ing handwriting examples from a writer, a system learns
prints is SFinGe, developed at the University of Bologna
the writers’ writing style.
(http://bias.csr.unibo.it/research/biolab/sfinge.html). The
generated databases were entered in the Fingerprint Veri-
3.3 Synthetic retina and iris images fication Competition FVC2004 and performed just as well
as real fingerprints [39].
Iris pattern painting has been used by ocularists in manu-
facturing glass eyes or contact lenses for sometime. The 3.6 Cancelable biometrics
ocularist’s approach to iris synthesis is based on the com-
position of painted primitives, and utilized layered semi- The issue of protecting privacy in biometric systems has in-
transparent textures built from topological and optic mod- spired the area of so-called cancelable biometrics. It was
els [34]. These methods are widely used by today’s ocular- first initiated by the Exploratory Computer Vision Group
ists: vanity contact lenses are available with fake iris pat- at IBM T.J. Watson Research Center and published in [37].
terns printed onto them (designed for people who want to Cancelable biometrics aim to enhance the security and pri-
change eye colors). Other approaches include image pro- vacy of biometric authentication through generation of “de-
cessing and synthesis techniques such as PCA combined formed” biometric data, i.e. synthetic biometrics. Instead
with super-resolution [35], and random Markov field [36]. of using a true object (finger, face), the fingerprint or face
In [37], a cancelable iris image design is proposed for the image is intentionally distorted in a repeatable manner, and
problem as follows. The iris image is intentionally dis- this new print or image is used. If, for some reason, the old
torted to yield a new version. For example, a simple per- print or image is “stolen”, an essentially “new” print can be
mutation procedure is used for generating a synthetic iris. issued by simply changing the parameters of the distortion
An alternative approach is based on generation of iris layer process. This also results in enhanced privacy for the user
patterns [31]. since his true print is never used anywhere, and different
distortions can be used for different types of accounts.
3.4 Synthetic faces
3.7 Biometric data model validation
Face recognition systems detect patterns, shapes, and shad-
ows in the face. The reverse process - face reconstruction - Data generated by various models are classified as accept-
is a classical problem of criminology. able or unacceptable for further processing and use in var-
ious applications. The application-specific criteria must databases (for example, databases of synthetic fingerprint)
provide a reasonable level of acceptability. Acceptability of synthetic biometrics for testing biometric hardware and
is defined as a set of characteristics which distinguish orig- software. The other application is biometric-based decision
inal and synthetic data. A model that approximates origi- making support systems for security, banking, and forensic
nal data at reasonable levels of accuracy for the purpose of applications. A generator of synthetic biometric informa-
analysis is not considered a generator of synthetic biomet- tion (for example, an aging or surgically changed face), is
ric information. a vital component of such systems. Yet another recently
Artificial biometric data must be verified for their emerging application is the creation of simulators for train-
meaningfulness. Statistical model verification is accom- ing highly qualified personnel in biometric-based physical
plished by solving the equations that describe physics- access control systems such as airport gates, hospital reg-
based models, and obtaining the correct values. Model val- istration, and others. The ability to increase the reliability
idation must prove if the equations that describe the model and accuracy of these systems while probing their vulner-
are right. Comparing the statistical distributions of real bio- abilities under numerous environmental conditions is criti-
metrics to the statistical distributions from empirical and cal, as biometrics becomes an essential part of law enforce-
physics-based models for a wide range of operational con- ment and security communities.
ditions validates these models for the range of conditions
provided by the real biometric samples [40]. A simple
Acknowledgment
method for validating these distributions is via visual com-
parison of overlapped distributions. This paper was prepared while Dr. P.S.P. Wang was
The MITRE research project [23] used synthetically the iCore Visiting Professor in the University of Calgary,
generated faces to better understand the performance of Canada. His visit was supported by iCore, the Informat-
face recognition systems. If a person’s photo in the sys- ics Circle of Research Excellence, the province of Alberta,
tem’s database was taken 10 years ago, is it possible to Canada. Dr. Yanushkevich acknowledges the Canadian
identify the person today? A pose experiment was also Foundation for Innovations (CFI) and the National Science
conducted with synthetic data to isolate and measure the and Engineering Research Council of Canada, for funding
effect of camera angle in one-degree increments. the equipment and researchers in the Biometric Technolo-
The modeling technique will provide an effective, gies Laboratory (http://btlab.enel.ucalgary.ca), University
more structured basis for risk management in a large bio- of Calgary.
metric system. This will help users choose the most effec-
tive systems to meet their needs in the future.
References
3.8 Ethical and social aspects of inverse biometrics [1] A. Jain, R. Bolle, and S. Pankanti, Eds., Biometrics:
Personal Identification in a Networked Society, Kluwer,
Ethical and social aspects of inverse biometrics include 1999
several problems, in particular, the prevention of undesir- [2] R. Bolle, J. Connell, S. Pankanti, N. Ratha, and A. Se-
able side-effects, and targeting of areas of social concern in nior, Guide to Biometrics, Springer, 2004
biometrics. Prevention of undesirable side effects aims at [3] C. Chen, and P. Wang, Eds. Handbook of Pattern
studying the potential negative impacts of biometrics, as far Recognition and Computer Vision, World Scientific Pub-
as important segments of society are concerned, and how lishers, 2005
can these be prevented. The undesirable ethical and so- [4] J. Wayman, A. Jain, D. Maltoni, and D. Maio, Eds. Bio-
cial effects of the solutions of inverse biometrics have not metric Systems Technology, Design and Performance Eval-
been studied yet. However, it is possible to predict some of uation, Spinger, 2005.
them. The particular examples of negative impact of syn- [5] A. Ross, K. Nandakumar, and A. Jain Handbook
thetic biometrics
Synthetic are asinformation
biometric follows: can be used not only for of Multibiometrics, International Series on Biometrics
improving the characteristics of biometric devices and Springer, 6, 2006.
systems, but also can be used by forgers to discover [6] V. Shmerko, Phil Phillips, G. Kukharev, W. Rogers,
new strategies of attack. and S. Yanushkevich, Biometric Technologies, Proc. Int.
Conf. The Biometrics: Fraud Prevention, Enchanced Ser-
Synthetic biometric information can be used for generat-
vice, Las Vegas, Nevada, 270–286, 1997
ing multiple copies of original biometric information.
[7] S. A. Cole, Suspect Identities – A History of Finger-
printing and Criminal Identification, Harvard University
4 Conclusions Press, 2001
[8] J. M. Hollerbach, An oscilation theory of handwriting,
The concept of inverse biometrics arose from the analysis- Biological Cybernetics, 39, 139–156, 1981.
by-synthesis paradigm, and has become an integral part of [9] R. Plamondon, and W. Guerfali, The generation of
the modeling and simulation of human biometrics in many handwriting with delta-lognormal synergies, Bilogical Cy-
applications. Data generated by various models are used as bernetics, 78, pp. 119–132, 1998
 [10] P. Ekman, and E. L. Rosenberg, Eds. What the Face and S. Yanushkevich, Morphing Facial Expressions from
Reveals: Basic and Applied Studues of Spontaneouse Ex- Artistic Drawings, In T. Simos, G. Maroulis, Eds., Ad-
pression Using the Facial Action Coding System (FACS) vanced in Computational Methods in Sciences and Engi-
Oxford University Press, 1997 neering. Lecture Series on Computer and Computational
[11] M. Pantic, and L. J. M. Rothkrantz, Automatic analy- Sciences, Brill Academic Publishers, The Netherlands,
sis of facial expressions: the state-of-the-art, IEEE Trans. Vol. 4, 1507–1511, 2005
Pattern Analysis and Machine Intelligence, 22, 12, pp. [26] R. Cappelli, Synthetic fingerprint generation, In D.
1424–1445, 2000 Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, Eds.,
[12] W. Zhao, R. Chelappa, Eds., Face Processing: Ad- Handbook of Fingerprint Recognition, 203–232, Springer,
vanced Modeling and Methods, Elsevier, 2006 2003
[13] J. Daugman, The importance of being random: Sta- [27] M. U. Kuecken, and A. C. Newell, A model for fin-
tistical principles of iris recognition, Pattern Recognition, gerprint formation, Europhysics Letters 68(1), 141–146,
36(2), pp. 279–291, 2003 2004
[14] A. Can, C.V. Steward, B. Roysam, and H. L. Tanen- [28] J. J. Brault, and R. Plamondon, A complexity mea-
baum, A feature-based, robust, hierarchical algorithm for sure of handwritten curves: modelling of dynamic signa-
registering pairs of images of the curved human retina, ture forgery, IEEE Trans. Systems, Man and Cybernetics,
IEEE Trans. Analysis and Machine Intelligence, 24(3), 23, 400–413, 1993
347–364, 2002 [29] I. Guyon, Handwriting synthesis from handwritten
[15] T. Moriyama, J. Xiao, T. Kanade, and J. F. Cohn, glyphs, Proc. 5th Int. Workshop Frontiers of Handwriting
Meticulously Detailed Eye Model and its Application to Recognition, Colchester, UK, 309-312, 1996
Analysis of Facial Image. Proc. IEEE Int. Conf. Systems, [30] C. Oliveira, C. Kaestner, F. Bortolozzi, and R.
Man, and Cybernetics, 629–634, 2004 Sabourin, Generation of signatures by deformation, Proc.
[16] C. Sanchez-Avila, and R. Sanchez-Reillo, Iris- the BSDIA97, 283–298, Curitiba, Brazil, 1997
based biometric recognition using dyadic wavelet trans- [31] S. N. Yanushkevich, A. Stoica, V. P. Shmerko, and
form, IEEE Aerospace and Electronic Systems Magazine, D.V. Popel, Biometric Inverse Problems, Taylor & Fran-
October, 3–6, 2002 cis/ CRC Press, Boca Raton, FL., 2005
[17] D. Cunado, M.S. Nixon, and J.N. Carter, Automatic [32] J. Wang, C. Wu, Y. Q. Xu, H. Y. Shum, and L. Li,
extraction and description of human gait models for recog- Learning Based Cursive Handwriting Synthesis, Proc. 8th
nition purposes, Computer Vision and Image Understand- Int. Workshop Frontiers in Handwriting Recognition, On-
ing, 9(1), 1–14, 2003 tario, Canada, 157–162, 2002.
[18] M.S. Nixon, J.N. Carter, M.G. Grant, L. Gordon, [33] H. Choi, S. J. Cho, and J. H. Jin Kim, Genera-
and J.B. Hayfron-Acquah, Automatic recognition by gait: tion of handwritten characters with bayesian network based
progress and prospects, Sensor Review, 23(4), 323-331, on-line handwriting recognizers, In Proc. 17th Int. Conf.
2003 Document Analysis and Recognition, Edinburgh, Scotland,
995–999, 2003
[19] L. Sloman, M. Berridge, S. Homatidis, D. Dunter, and
T. Duck, Gait patterns of depressed patients and normal [34] A. Lefohn, B. Budge, P. Shirley, R. Caruso, and E.
subjects, American Journal of Psyhiatry, 139(1), 94–97, Reinhard, An ocularists approach to human iris synthe-
1982 sis, Computer Graphics and Applications, IEEE Maga-
zine, 23(6), 70–75, 2003
[20] I.P.I. Pappas, M.R. Popovic, T. Keller, V. Dietz, and
M. Morari, A reliable gait phase detection system, IEEE [35] J. Cui, Y. Wang, J. Huang, T. Tan, Z. Sun, and L. Ma,
Transaction on Neural System Rehabilitation Engineering, An iris image synthesis method based on PCA and super-
June, 9(2), 113–125, 2001 resolution, Proc. Int. Conf. Pattern Recognition, 2004
[21] N. V. Boulgouris, D. Hatzinakos, and K. N. Platanio- [36] S. Makthal, and A. Ross, Synthesis of iris images
tis, Gait recognition: A challening signal processing tech- using Markov random fields, Proc. 13th European Signal
nology for biometric identification, IEEE Signal Process- Processing Conf., Antalya, Turkey, 2005
ing Magazine, November, 78–90, 2005. [37] N. Ratha, J. Connell, and R. Bolle, Enhancing se-
[22] D. J. Hurley, M. S. Nixon, and J. N. Carter, Force field curity and privacy in biometrics-based authentication sys-
feature extraction for ear biometrics, Computer Vision and tems, IBM Systems J. 40(3), 614–634, 2001
Image Understanding, 98, 491–512, 2005 [38] K. Sumi, C. Liu, and T. Matsuyama, Study on Syn-
[23] N. M. Orlans, D.J. Buettner, and J. Marques, A Survey thetic Face Database for Performance Evaluation, Proc.
of Synthetic Biometrics: Capabilities and Benefits, Proc. Int. Conf. Biometric Authentication, 598–604, LNCS-
Int. Conf. Artificial Intelligence, CSREA Press, vol. I, 499– 3832, Springer, 2006
505, 2004 [39] The Fingerprint Verification Competition FVC2004
[24] S. N. Yanushkevich, A. Stoica, S. N. Srihari, V. P. http://bias.csr.unibo.it/fvc2004/databases.asp
Shmerko, and M. L. Gavrilova, Simulation of Biometric [40] Y. Ma, M. Schuckers, and B. Cukic, Guidelines for
Information: The New Generation of Biometric Systems, appropriate use of simulated data for bio-authentication re-
In Proc. Int. Workshop Modeling and Simulation in Bio- search, Proc. 4th IEEE Workshop Automatic Identifica-
metric Technology, Calgary, Canada, 87–98, 2004 tion Advanced Technologies, Buffalo, New York, 251–256,
[25] Y. Luo, M. L. Gavrilova, M. C. Sousa, J. Pivovarov, 2005

View publication stats