Get documents about "High Performance Fingerprint Identification System
Document Sample
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 4, July 2010
High Performance FingerPrint Identification System
Dr.R.Seshadri ,B.Tech,M.E,Ph.D Yaswanth Kumar.Avulapati,M.C.A,M.Tech,(Ph.D)
Director, S.V.U.Computer Center Research Scholar, Dept of Computer Science
S.V.University, Tirupati S.V.University, Tirupati
E-mail : ravalaseshadri@gmail.com E-mail:yaswanthkumar_1817@yahoo.co.in
Abstract
Biometrics is the science of establishing the Verification system authenticates a person’s
identity of an individual based on their physical, chemical identity by comparing the captured biometric
and behavioral characteristics of the person. Fingerprints characteristic with its own biometric template(s) pre-
are the most widely used biometric feature for person stored in the system It conducts one-to-one comparison
identification and verification in the field of biometric to determine whether the identity claimed by the
identification .A finger print is the representation of the individual is true.
epidermis of a finger. It consists of a pattern of interleaved A verification system either rejects or accepts the
ridges and valleys. submitted claim of identity Identification system
Fingerprints are graphical flow-like ridges recognizes an individual by searching the entire template
present on human fingers. They are fully formed at about database for a match. It conducts one-to-many
seven months of fetus development and finger ridge comparisons to establish the identity of the individual.
configurations do not change throughout the life of an In an identification system, the system establishes
individual except due to accidents such as bruises and a subject’s identity without the subject having to claim an
cuts on the fingertips. This property makes fingerprints a identity.
very attractive biometric identifier. This paper presents Prehistoric picture writing of a hand with ridge
an approach to classifying the fingerprints into patterns was discovered in Nova Scotia. In ancient
different groups and increase the performance of the Babylon,fingerprints were used on clay tablets for
system.It increases the performance of fingerprint business transactions. In ancient China, thumb prints were
matching while matching the input template with stored found on clay seals.In 14th century Persia, various official
template. government papers had fingerprints (impressions), and
one government official, a doctor, observed that no two
fingerprints were exactly alike.
Keywords-Biometrics, Verification, Identification In 1686, Marcello Malpighi, a professor of
anatomy at the University of Bologna, noted in his
Introduction treatise; ridges, spirals and loops in fingerprints. He made
A fingerprint is a pattern of ridges and valleys no mention of their value as a tool for individual
located on the tip of each finger. Fingerprints were used identification. A layer of skin was named after him;
for personal identification for many centuries and the "Malpighi" layer, which is approximately 1.8mm thick.
matching accuracy was very high. Patterns have been In 1823, John Evangelist Purkinji, a professor of
extracted by creating an inked impression of the fingertip anatomy at the University of Breslau, published his thesis
on paper. discussing 9 fingerprint patterns, but he too made no
mention of the value of fingerprints for personal
Today, compact sensors provide digital images of identification. During the 1870's, Dr. Henry Faulds, the
these patterns. Fingerprint system can be separated into British Surgeon-Superintendent of Tsukiji Hospital in
two categories Verification and identification. Tokyo, Japan, took up the study of "skin-furrows" after
noticing finger marks on specimens of "prehistoric"
120 http://sites.google.com/site/ijcsis/
ISSN 1947-5500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 4, July 2010
pottery. A learned and industrious man, Dr. Faulds not Enrollment Mode
only recognized the importance of fingerprints as a means
Finger print Feature Template
of identification, but devised a method
Acquisition Extraction
of classification as well.
In 1880, Faulds forwarded an explanation of his
classification system and a sample of the forms he had
designed for recording inked impressions, to Sir Charles
Darwin. Darwin, in advanced age and ill health, informed Authentication Mode
Dr. Faulds that he could be of no assistance to him, but Finger Print Feature
promised to pass the materials on to his cousin, Francis Matching
Acquisition Extraction
Galton.
Also in 1880, Dr. Faulds published an article in
the Scientific Journal, "Nautre" (nature). He discussed
fingerprints as a means of personal identification, and the
use of printers ink as a method for obtaining such
Matching Score
fingerprints. He is also credited with the first fingerprint
Fig 2.Enrollment and Authentication of a fingerprint system
identification of a greasy fingerprint left on an alcohol
bottle. Fingerprint matching can be performed based
In order to implement a fingerprint system, the on Minutiae, Correlation based, Ridge feature based.
various research methodologies involved in it like In minutiae based matching it stores minutiae is a set
fingerprint image capture, image preprocessing, feature of points in a plane and the points are matched in the
extraction, storage and image matching must be clearly
template and the input minutiae. In correlation based
defined are shown in figure. 1
matching two finger print images and correlation
between corresponding pixels is computed. Ridge
Image Capture feature based is a advanced technology that capture
the ridges. The most popular technologies used to
identify fingerprint are Optical, silicon and ultra
sound.
Image Preprocessing & Previous Work:
Feature Extraction
The previous work is based on the theory
of fingerprint classification they stored only single
finger print of person in the database. This single
Matching finger print can be index or thumb. Let us see how
the previous system will work. In the enrollment
process in conventional system the database
contains the fingerprint templates in an ordinary
manner but in that system the database e contains
Stored Pattern the different set of templates according to
classification. During the enrollment process, sensor
sense the fingerprint, then next step is feature
extraction . After this step they put a classifier to
Fig 1.Various steps in a Fingerprint system
check the classification of input template that
whether it is left-loop, right-loop, arch or whorl as
A finger print system works in two different shown in the figure 3
modes they are Enrollment mode and Let us come to the verification process here the
Authentication mode as shown in figure.2. finger print is placed at sensor and then its features are
Enrollment mode in which fingerprint system is used extracted and a final template is generated for matching.
to identify and collect the related information about Now this template will not matched with every templates
the person and his/her fingerprint image. in the database rather it extracts its classified domain out
Authentication mode in which fingerprint system is of 4-domain and will perform match from this extracted
used to identify the person who is declared to be domain
him/her. 121 http://sites.google.com/site/ijcsis/
ISSN 1947-5500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 4, July 2010
After this step we put a classifier to check
the classification of input template that whether it is
arch,tentarch, loop, doubleLoop, pocked Loop, whorl
,mixed, left-loop, right-loop
Left Loop Right-Loop
Arch Whorl
Fig3.Classification of Finger prints in existing system Fig4.Classification of Finger prints in proposed
system
Fingerprint classifiers classify the input Enrollment Mode
fingerprint into four major categories namely
Left-Loop, Right-Loop, Whorl and Arch. They Finger print Feature Finger print
Acquisition Extraction Classifier
proposed classifiers works on the basis of singular
point (Delta) extracted. If there are two deltas then it
Authentication Mode
will be counted as whorl or twin loop. If there is no
delta then it will be counted as arch. If only one delta Finger Print Feature
is there then it will be consider as either left loop or Acquisition Extraction
right loop.
Problems in the Existing system:
Arch
The existing system can identify the finger FingerPrint Tentarch
prints according to their four categories namely Left- Template Loop
Loop, Right-Loop, Whorl and Arch. DoubleLoop
If the people having different types of finger PockedLoop
prints other than this four categories. It is very Whorl
difficult for the system to identify the finger prints Extracted Mixed
like mixed category, pocked loop, double loop. The Matching Area Left-loop
time taken for identifies the finger prints is also more Right-loop
in the existing system. It decreases the performance
of the system. Matching Score
Fig5.Proposed Fingerprint identification system
Proposed Work:
After classification the input template is stored in
Proposed work is based on the classification of particular area. A area in the database contains the
fingerprints. In our proposed system during the templates of same classification. Normally fingerprints
enrollment process fingerprint is captured with a are classified as Whorl(27%), arch (4%) loops(65%)and
sensor, then next step is feature extraction . we mixed (4%) we further divide this domain into
further classify the finger prints as arch,tentarch,loop, four parts i.e. left http://sites.google.com/site/ijcsis/ (25%)
122 loop (26%) right loop
doubleLoop, pocked Loop, whorl ,mixed, left-loop, pocked loop (9%)and ISSN 1947-5500 (5%), apx
double loop
right-loop as shown in figure below
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 4, July 2010
Fingerprint Classifier: Performance of Existing System
The proposed classifiers works on the basis For Best case i.e. the template is First match,
of core and Delta extracted. If there is two deltas Time required = 1 X 1 = 1 ms they calculate for
then it will be counted as whorl or twin loop. If there worst case They assumed 1, 50000 templates ,
is no delta then it will be counted at arch. If only one According to c lassific ation there will be 45000
delta is there then it will be either left loop or right whorls (30%) + 48000 Left Loop (32%) + 49500
loop. If there is only one delta and one core then it Right Loop (33%) + 7500 Arch (5%)
will be pocked loop. If there is two deltas and one
core then it will be double loop. If there is two deltas
and two cores then it will be mixed as shown in the At First stage they get the template
figure.6 classification and accordingly particular domain
will be extracted. Now they calculate the time taken
for each classification
For Whorl = 1ms X 45000 = 45 sec.
For LL = 1ms X 48000 = 48 sec.
For RL = 1ms X 49500= 49.5 sec
For Arch = 1msX 7500= 7.5 sec.
Average time = 150/4= 37.4 sec.
For an Average case, Time required= apx 20-24 sec.
Proposed System Fingerprint classification:
Let us assume that we classify fingerprints
as Whorl, loop,mixed. Loops make up nearly
65% of all fingerprints, whorls are nearly 27%,
arches are nearly 4%and mixed are nearly 4% Since
the loops are 65%, we further divide this domain
into four parts i.e. left loop 26% right loop 25%
pocked loop 9%and double loop 5%, apx .
Performance of Proposed System
For Best case i.e. the template in First match,
Time required = 1 X 1 = 1 msNow let us calculate for
worst case We have assumed 1, 50000 templates ,
According to classific ation there will be
40500whorls (27%) + 39000 Left Loop (26%) +
37500 Right Loop (25%) + 13500 Pocked Loop (9%)
+7500 Double Loop(5%)+6000 Arch(4%)+6000
Mixed(4%).At First stage we get the template
classification and accordingly particular domain will
be extracted. Now we calculate the time taken for
each classification
For Whorl = 1ms X 40500 = 40..5 sec.
For LL = 1ms X 39000 = 39 sec.
For RL = 1ms X 37500= 37.5 sec
For PL = 1ms X 13500= 13.5 sec
Fig 6. Position and number of Core and Delta in For DL = 1ms X 7500= 7.5 sec
different Finger prints For Mixed = 1ms X 6000= 6 sec
123 For Arch = 1msX 6000= 6 sec.
http://sites.google.com/site/ijcsis/
ISSN 1947-5500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 4, July 2010
A, no. 8, pp. 1913–1923, Aug. 2004.
Average time = 150/7= 21.42sec.
For an Average case, Time required= apx 12-18 sec. 6. K. Ito, H. Nakajima, K. Kobayashi, T. Aoki, and
T. Higuchi, “A fingerprint matching algorithm using
Performance Factor phaseonlycorrelation,” IEICE Trans. Fundamentals,
vol. E87-A,no. 3, pp. 682–691, Mar. 2004.
PF=Time taken in worst case of existing system 7. M. Kawagoe and A. Tojo, “Fingerprint pattern
37.4sec classification,”
Pattern Recognition, vol. 17, no. 3, pp. 295–303,
PF=Time take in worst case of proposed system 1984.
21.42 Sec 8. www.aladdinusa.com
Biometrics Information Group
i.e. the new approach is better than the existing one. www.biometricsinfo.org.
9. A. K. Jain, R. Bolle, S. Pankanti (eds), Biometrics:
Coclusion: Personal Identification in Networked Society, Kluwer
Academic, December 1998.
This paper presents an approach to 10.Reducing Process-Time for Fingerprint
classifying the fingerprints into different groups Identification System , Chander Kant & Rajender
and increase the performance of the system. It Nath
increases the performance of fingerprint matching 11. A. K. Hrechak and J. A. McHugh,
while matching the input template with stored Automated Fingerprint Recognition using
template.The paper presents an overview of the Structural Matching, Pattern Recognition, Vol. 23,
different steps involved in the enrollment and No. 8, 1990.
authentication modes. We have proposed seven 12. The Henry Clas sification System Copyright ©
major classifications of fingerprints like arch, 2003 International Biometric Group
doubleLoop, pocked Loop, whorl ,mixed, left-loop, 13.A. K. Jain, S. Prabhak ar. “Handbook of
right-loop .Its a new approach for classification of Fingerprint Recognition”.
fingerprints and matching in the database. This 14.www.google.co.in
paper presents an approach to speed up the 15A. K. Jain and S.Pankanti , “Fingerprint
matching process by classifying the fingerprint lassification and matching, ”InA. Bovik, Ed.,
into different groups at the time of enrollment, Handbook for Image and Video Processing .
and authentication modes. This proposed system is AcademicPress, 2000.
better than the previous one. 16. Z.W. bo, N. X. bao and W.C. jian, “ A
fingerprint matching algorithmbased on relative
References: topological relationship among minutiae, ” IEEE Int.
Conference Neural Networks & Signal Processing
1.A. K. Jain,Patrick Flynn,Arun A.Ross . “Handbook
Zhenjiang, China,2008.
of Biometrics”.
17. Y.He, J.Tian, X.Luo and T.Zhang, “ Image
2.D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar,
enhancement and minutiae matching in fingerprint
Handbook of Fingerprint Recognition. Springer,
verification, ”Patt.Recog.Lett. no.24, 2003,pp.1349-
2003.
1360.
3. C. D. Kuglin and D. C. Hines, “The phase
18.Glossary of Biometric Terms, Association for
correlation image
Biometrics and International Computer Security
alignment method,” Proc. Int. Conf. on Cybernetics
Association, to be referred at URL:
and Society, pp. 163–165, 1975.
http://www.afb.org.uk/ (1998).
4. K. Takita, T. Aoki, Y. Sasaki, T. Higuchi, and
19. Biometrics Information Management and
K. Kobayashi, “High-accuracy subpixel image
Security (2001).
registration based on phase-only correlation,” IEICE
Trans. Fundamentals,vol. E86-A, no. 8, pp. 1925–
20. Bahuguna, R.D. and Corboline, T.: Prism
1934, Aug. 2003.
fingerprint sensor that uses a holographic optical
5. K. Takita, M. A. Muquit, T. Aoki, and T. Higuchi,
element, APPLIED OPTICS,
“A subpixel
124 Vol. 35, No. 26 (1996).http://sites.google.com/site/ijcsis/
correspondence search technique for computer vision ISSN 1947-5500
applications,” IEICE Trans. Fundamentals, vol. E87-
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 4, July 2010
Authors Profile
Dr.R.Seshadri was born in
Andhra Pradesh, India, in
1959. He received his
B.Tech degree from
Nagarjuna University in
1981. He received his M.E
degree in Control System
Engineering from PSG
College of Technology,
Coimbatore in 1984. He was
awarded with PhD from Sri Venkateswara
University, Tirupati in 1998. He is currently
Director, Computer Center, S.V.University,
Tirupati, India. He has Published number of papers
in national and international conferences, seminars
and journals. At present 12 members are doing
research work under his guidance in different areas
Mr.YaswanthKumar
.Avulapati received his
MCA degree with First
class from Sri Venkateswara
University, Tirupati. He
received his M.Tech
Computer Science and
Engineering degree with
Distinction from Acharya
Nagarjuna University,
Guntur.He is a research
scholar in S.V.University
Tirupati, Andhra Pradesh.He has presented number
of papers in national and international conferences,
seminars.He attend Number of work shops in
different fields.
125 http://sites.google.com/site/ijcsis/
ISSN 1947-5500
Related docs
Other docs by ijcsiseditor
Digital Images Encryption in Spatial Domain Based on Singular Value Decomposition and Cellular Automata
Views: 0 | Downloads: 0
Agent Behavior in Multiagent Systems: Issues and Challenges in Design, Development and Implementation
Views: 1 | Downloads: 0
Optimizing Cost, Delay, Packet Loss and Network Load in AODV Routing Protocols
Views: 2 | Downloads: 0
