Proceedings of

VESCOMM-2016
4th NATIONAL CONFERENCE ON “RECENT TRENDES IN VLSI, EMBEDED SYSTEM, SIGNAL PROCESSING AND COMMUNICATION
In Association with “The Institution of Engineers (India)” and IJRPET
February 12th, 2016

Paper ID: VESCOMM 13

COMBINATION OF FINGERPRINT FOR PRIVACY
PROTECTION: PRE-PROCESSING
Miss.Rathod Leena Anil
Prof. Mantri D. B.
Department of Electronics and Telecommunication,
V.V.P. Institute of Engg & Technology, Department of Electronics and Telecommunication,
Solapur University, Solapur, Ms, India V.V.P. Institute of Engg & Technology,
[email protected] Solapur University, Solapur, Ms, India
[email protected]
Abstract – Biometrics is the measurement
and statistical analysis of people’s physical and encryption and decryption methods are used for
behavioural characteristics. Using biometrics to fingerprint privacy and protection. But this
verify identity means using a physical characteristic encryption method is not sufficient for fingerprint
such as face, voice or fingerprints to authenticate an privacy protection because decryption is required
individual’s claimed identity. Fingerprint matching is before the fingerprint matching, which exposes the
by far the most successful biometric technology fingerprint to attacker. In recent years significant
because its ease of use, non-intrusiveness and efforts have been put into developing specific
reliability. Here we introduce a novel system for
protection techniques for fingerprint. Most of the
protecting fingerprint privacy by combining two
different fingerprints into new identity. Firstly we existing techniques make use of keys for the
extract the minutiae position from one fingerprint, fingerprint privacy protection.
the orientation from other fingerprint and reference
point from both fingerprints. The coding strategy is In 2004 two different fingerprints were
applied and a combined minutiae template is combined together into a single new identity either
generated and stored in database. In the in feature level or image level. The concept of
authentication process, the system needs two query combining two different fingerprints into a new
fingerprints from the same fingers which are used in identity is created by combining the minutiae
enrollment. A two-stage fingerprint matching process positions extracted from the two fingerprints. The
is proposed for matching the two query fingerprints image level based fingerprint combination
against a combined minutiae template.
technique has two advantages: (1) it is difficult for
attacker to distinguish a mixed fingerprint from the
Keywords – Fingerprint enhancement, pre-processing original fingerprints, and (2) existing fingerprint
minutiae, orientation, combination. matching algorithm are applicable for matching
two mixed fingerprints.
I. INTRODUCTION
Here in this paper a novel system has been
Recognition of person by means of proposed for protecting the privacy of the
biometric characteristics is an emerging fingerprints. There are two steps enrollment and
phenomenon in modern society. It has received authentication phase. In the enrollment phase the
more and more attention during the last period due
system captures two fingerprints from two
to the need of security in a wide range of
different fingers. We propose a combined
application. Among the many biometric features
minutiae template generation algorithm to
the fingerprint is considered one of the most
create a combined minutiae template from the
practical ones. Fingerprint recognition requires a
two fingerprints. In such a template, the
minimal effort from the user does not capture other
minutiae positions are extracted from one
information than strictly necessary for the
fingerprint, while the minutiae directions
recognition process and provides relatively good
depend on the orientation of the other
performance. fingerprint and some coding strategies. The
Securing a stored fingerprint image is of template will be stored in a database for the
paramount importance because a compromised authentication which requires two query
fingerprints. A two-stage fingerprint matching
fingerprint cannot be easily revoked. Traditional
process is further proposed for matching the
two query fingerprints against a combined
minutiae template.

Organized by Department of Electronics and Telecommunication, V.V.P.I.E.T, Solapur

1
 Proceedings of
VESCOMM-2016
4th NATIONAL CONFERENCE ON “RECENT TRENDES IN VLSI, EMBEDED SYSTEM, SIGNAL PROCESSING AND COMMUNICATION
In Association with “The Institution of Engineers (India)” and IJRPET
February 12th, 2016

II. METHODOLOGY
From the above system design till now
we have carried out only a few steps of the
A. System Design: whole algorithm. They are the reading of the
The fig 1 below shows the enrollment fingerprints and the preprocessing step.
Reading of the fingerprints means we are
phase of our system.
going to take two fingerprints database images
stored in our system using the MATLAB
commands as we are going to perform our
project in MATLAB and the preprocessing step
means we are going to enhance the images of
the fingerprints.

B. Pre-processing:
Fingerprint image quality is an important
factor in performance of minutiae extraction and
matching algorithms. A good quality fingerprint
image has high contrast between ridges and valleys.
Fig 1: Enrollment phase
A poor quality fingerprint image is low in
divergence, noisy, exhausted, or smudgy, causing
In the enrollment phase, the system spurious and missing minutiae. Poor quality can be
captures two fingerprints from two different due to cuts, crinkles, or bruises on surface of
fingers, say fingerprints A and B from fingers A fingertip, excessively wet or dry skin condition,
and B respectively. We extract the minutiae uncooperative attitude of subjects, broken and
positions from fingerprint A and the orientation impure scanner devices, little quality fingers
from fingerprint B using some existing (elderly people, manual worker), and other factors.
techniques. Then, by using our proposed Image enhancement techniques are employed to
coding strategies, a combined minutiae decrease noise and enhance the definition of ridges
template is generated based on the minutiae against valleys. In order to ensure good
positions, the orientation and the reference performance of ridge and minutiae extraction
points detected from both fingerprints. Finally, algorithms in poor quality fingerprint images, an
the combined minutiae template is stored in a enhancement algorithm to improve clarity of ridge
database. structure is necessary.
The fig 2 below shows the Pre-processing is an important step for
authentication phase of our system. In the fingerprint recognition system. It enhances the
authentication phase, two query fingerprints quality and produces an image in which minutiae
are required from the same two fingers, say can be detected correctly. The pre-processing step
fingerprints A/ and B/ from fingers A and B. we are going to apply separately for both the
fingerprints. First we are going to carry out pre-
processing of fingerprint A and then we are going
to carry out the pre-processing of fingerprint B.
A fingerprint image contains regions of different
excellence. They are:
1) Well-defined region
2) Recoverable region
3) Unrecoverable region.
Well-defined regions, recoverable regions
Fig 2: Authentication phase
and unrecoverable regions may be identified
according to image contrast, alignment consistency,
As what we have done in the ridge frequency, and other local features. The
enrollment, we extract the minutiae positions principal aim of enhancement is to improve the
from fingerprint A/ and the orientation from clarity of ridge in the recoverable area in the image
fingerprint B/. Reference points are detected and to assign the unrecoverable ridges as a noisy
from both query fingerprints. This extracted area. Recoverable region is considered when ridges
information will be matched against the and valleys are corrupted by a small amount of dirt,
corresponding template stored in the database ceases, or other kind of noise. Unrecoverable
by using a two-stage fingerprint matching. The region are the regions which are impossible to
authentication will be successful if the recover them from a very corrupted and noisy
matching score is over a predefined threshold. image. The output of the pre-processing is a grey-

Organized by Department of Electronics and Telecommunication, V.V.P.I.E.T, Solapur

2
 Proceedings of
VESCOMM-2016
4th NATIONAL CONFERENCE ON “RECENT TRENDES IN VLSI, EMBEDED SYSTEM, SIGNAL PROCESSING AND COMMUNICATION
In Association with “The Institution of Engineers (India)” and IJRPET
February 12th, 2016

scale image or a binary image. We are going to use

filters for the purpose of pre-processing. We are
going to get the enhanced image at the output of the
pre-processing so we can clearly identify the ridges
and minutiae position of the fingerprints and we
can process on this easily.

CONCLUSION & FUTURE WORK

III.
We can see that pre-processing
produces better images which are clearer
and identifying minutiae points from them are easy.
By following these steps sequentially, we can
detect true minutiae points which will produce
accurate results. Further we are going to extract the
orientation for one fingerprint and minutiae from
other fingerprint and reference point from both
fingerprints and for a combined minutiae template
and store it in database. In authentication we
require two query fingerprints. A two-stage
fingerprint matching process is further
proposed for matching the two query
fingerprints against a combined minutiae
template stored in database.

REFERENCES
[1] Sheng Li, Student Member, IEEE, and Alex C. Kot, Fellow,
IEEE, “Fingerprint Combination for Privacy Protection,” IEEE
transactions on information forensics and security, vol. 8, no. 2,
February 2013.

[2] L. Hong, Y. F. Wan, and A. Jain, “Fingerprint image

enhancement: Algorithm and performance evaluation,” IEEE
Trans. Pattern Anal. Mach. Intell., vol. 20, no. 8, pp. 777–789,
Aug. 1998.

[3] B. Yanikoglu and A. Kholmatov, “Combining multiple

biometrics to protect privacy,” in Proc. ICPR- BCTP Workshop,
Cambridge, U.K., Aug. 2004.

[4] E. Camlikaya, A. Kholmatov, and B. Yanikoglu, “Multi-

biometric templates using fingerprint and voice,” Proc. SPIE,
vol. 69440I, pp.69440I-1–69440I-9, 2008.

[5] Amber Habib, Ijlal Shahrukh Ateeq, Kamran Hameed

Sir Syed University of Engineering and Technology,
Department of Biomedical Engineering, “Biometric Security
System based on Fingerprint Recognition” International Journal
of Scientific Engineering and Technology (ISSN : 2277-1581)
Volume No.2, Issue No.9 1 Sept. 2013.

[6] Ankita Mehta and Sandeep Dhariwal Electronics &

Communication Engineering Department, HCTM, Kaithal, India
“Design & Implementation of Features based Fingerprint Image
Matching System” Int. J. of Multidisciplinary and Current
research, Nov/Dec 2014.

Organized by Department of Electronics and Telecommunication, V.V.P.I.E.T, Solapur