International Journal of Engineering Trends and Technology (IJETT) – Volume 8 Number 9- Feb 2014
A Coarse to Fine Minutiae-Based Latent Palm print
Matching and fusion
P. Kavya1,J.Refonaa2
Sathyabama University1, Faculty of Computing2
M.E Computer Science and Engineering1,Sathyabama University2
Chennai-600119, India
ABSTRACT
In this paper, a coarse to fine matching strategy based
on
minutiae clustering and minutiae match
propagation is designed specifically for palmprint
matching and to deal with the large database and
local feature-based minutiae clustering algorithm is
designed to cluster minutiae into several groups such
that minutiae belonging to the same group have
similar local characteristics. The proposed palmprint
matching algorithm has been evaluated on a latent-tofull palmprint database consisting of 44 latents and
12,489 background full prints. Our method involves
image acquisition via a dedicated device under
contact-free
and
multi-spectral
environment,
preprocessing to extract features and locate region of
interest (ROI) from each individual hand images,
future-level registration to combine ROIs from
different spectral images in one sequence and fusion
to combine two multispectral palm images. The
matching results show a rank-1 identification
accuracy of 80 percent, which is more accurate than
the state-of-the-art latent palmprint matching
algorithm. The computation time of our algorithm is
an order of magnitude faster than a previous
algorithm.
Keywords— Latentpalmprint matching, minutiae
clustering,minutiadescriptor,ROI,match
propagation.
I.
INTRODUCTION
Palmprints recognition has a considerable potential
as personal identification/verification technique
which share most of the discriminative features
with finger prints and in addition possess much
larger skin area and other discriminative features
such as principal lines for access control , scanning
the palmprint is not only fast technique but also
highly acceptable for the public.
ISSN: 2231-5381
II.
RELATED ARTICLES
[1] Heeseung Choi, Kyoungtaek Choi, and
Jaihie Kim In this paper, they developed a novel
high-resolution palm print recognition system,
which can handle palm prints with large amount of
crease, leading to higher accuracy than the previous
systems. The main contributions are: First use of
multiple features for palmprint recognition to
significantly
improve
the
matching
accuracy.Second design of a quality based and
adaptive orientation field . It can reliably estimate
the ridge direction by adaptively choosing suitable
estimation method according to the image quality.
Third use of a novel heuristic rule for identification
applications to combine different features.Fourth
the discriminative power of different feature
combinations is analyzed and we find that density
is very useful for palm print recognition.
[2] Jifeng Dai, and Jie Zhou (2011) we discover
two low discriminative regions in fingerprint and
propose an effective approach to detect minutiae in
such regions. In order to improve low quality
fingerprint matching, we propose to use neighbours
of a minutia to measure its quality and incorporate
the quality to minutiae similarity calculation.
Experimental
results
over
FVC-onGoing
demonstrate the proposed approaches is effective.
[3]Adams Kong, DavidZhangb, MohamedKamelc
(2009) In order to improve the performance of
minutiae-based fingerprint matching algorithm, we
take the minutiae discriminbility into account. In
the light of minutiae distribution characteristic, we
discover two low discriminative regions in
fingerprint and propose an effective approach to
detect minutiae in such regions. In order to improve
low quality fingerprint matching, we propose to use
neighbours of a minutia to measure its quality and
http://www.ijettjournal.org
Page 476
International Journal of Engineering Trends and Technology (IJETT) – Volume 8 Number 9- Feb 2014
incorporate the quality to minutiae similarity
calculation. Experimental results over FVC2004
and FVC-onGoing demonstrate that the proposed
approaches demonstrate the proposed approaches is
effective, however matching processes including
minutiae similarity calculation, alignments and
orientation reconstruction all are time consuming.
III.
database. The average computation time of our
algorithm for a single latent-to-full match is about
141 ms for genuine match.the proposed system
handles Uncontrollable latent image quality. Small
area of latent palmprints compared to full
palmprints.Large nonlinear image distortion and
large number of spurious minutiae.
SUMMARY OF EXISTING SYSTEM
Biometric based recognition systems have wide
applications in the field of personal verification.
Fingerprint based systems are most widely used
while iris based systems are considered to be most
reliable.The palmprint is the region between the
wrist and fingers. It has features such as texture,
wrinkles, principle lines, ridges and minutiae points
that can be used for its representation.Other
biometric traits, palmprints also satisfy the critical
properties of biometric characteristics such as
universality,
uniqueness,
permanence
and
collectability.If the subject is not able to expose the
palmprint to the scanner completely due to medical
injuries or being physically challenged, the systems
fail to perform at their best.These spurious minutiae
could lead to many false initial minutiae pairs
Certain types of latent palmprints called writer’s
palmprints might have very small overlap which
makes it difficult to find number of true minutiae
correspondences.
IV.
DRAWBACKS
Two dimensional operations are found to be
computationally more intensive and slow down the
identification process. The technique used to
extract features and to match features is found to be
computationally expensive. To compare the
fingerprints and its region is larger than a finger
print. The EER of our algorithm is 10 times lower
than that of the segment based Due to the presence
of immutable creases in palm prints and
uncontrollable image acquisition conditions, a large
number of spurious minutiae might be extracted
especially in palm print images.
V.
PROPOSED SYSTEM
The proposed palmprint matching Our method
involves image acquisition via a dedicated device
under contact-free environment,preprocessing to
locate region of interest(ROI) from each individual
hand images, feature-level registration to align
ROIs from different palm images in one sequence
and fusion to combine images for more accurate
identification. The matching results show a rank-1
identification accuracy of 79.4 percent, which is
significantly higher than the 70.8 percent
identification accuracy of a state-of-the-art latent
palmprint matching algorithm on the same latent
ISSN: 2231-5381
CONCLUSION
This paper shows that fusion of multispectral
images to deal with the different spectral
in
palmprint images, a minutiae clustering algorithm
is proposed to group minutiae into several clusters
based on the local feature in minutiae
neighbourhood. by Kalman filter technique and
ROI used to locate the region of interest and
selected minutiae correspondences are fed to a fine
matching procedure, called minutiae match
propagation,
to
establish
the
minutiae
correspondences in the whole palmprint.
ACKNOWLEDGMENT
We would like to thank Dr.B.Bharathi,
Head of the Department, Department of Computer
Science and Engineering, Ms.Refonaa for her
encouragement and support.
http://www.ijettjournal.org
Page 477
International Journal of Engineering Trends and Technology (IJETT) – Volume 8 Number 9- Feb 2014
REFERENCES
[1] Eryun Liu, Anil K. Jain“A Coarse to Fine
Minutiae-Based Latent Palmprint Matching” IEEE
Trans. Pattern Analysis and Machine Intelligence,
vol. 35, no. 10, october 2013.
[2] J. Dai and J. Zhou, “Multifeature-Based HighResolution PalmprintRecognition,” IEEE Trans.
Pattern Analysis and Machine Intelligence, vol. 33,
no. 5, pp. 945-957, May 2011.
[3] K. Cao, E. Liu, L. Pang, J. Liang, and J. Tian,
“Fingerprint matching by Incorporating Minutiae
Discriminability,” Proc. Int’ Joint Conf. Biometrics,
pp. 1-6, 2011.
[4] A. Kong, D. Zhang, and M. Kamel, “A Survey
of Palmprint Recognition,” Pattern Recognition,
vol. 42, no. 7, pp. 1408-1418,2009.
[5] A. Jain and J. Feng, “Latent Palmprint
Matching,” IEEE Trans.Pattern Analysis and
Machine Intelligence, vol. 31, no.6,pp.1032-1047,
June 2009.
[6]R. Cappelli, M. Ferrara, and D. Maio, “A Fast
and Accurate Palmprint Recognition System Based
on Minutiae,” IEEE Trans.Systems, Man, and
Cybernetics, Part B: Cybernetics, vol. 42, no. 3,pp.
956-962, June 2012.
[7]H. Wang, S. Yan, J. Liu, X. Tang, and T. Huang,
“Correspondence Propagation with Weak Priors,”
IEEE Trans. Image Processing, vol. 18, no. 1, pp.
140-150, Jan. 2009.
[8] J. Yao and W. Cham, “Clustering-Based Match
Propagation for Image-Based Rendering from
Multiple
Images,”
Proc.
Int’lConf.Image
Processing, vol. 5, pp. 2969-2972, 2004.
[9] J. Yao and W. Cham, “3D Modeling and
Rendering from Multiple Wide-Baseline Images by
Match Propagation,” Signal Processing:Image
Comm., vol. 21, no. 6, pp. 506-518, 2006.
ISSN: 2231-5381
http://www.ijettjournal.org
Page 478