FINGER VEIN AUTHENTICATION USING

MAXIMUM CURVATURE POINTS

SUBMITTED BY GUIDED BY

Akash V Mrs.P.Ponsudha
Gireesh V
Joel J
Navin R

Date: 07-04-2017
1
 Abstract
• The existing biometric systems like finger print
recognition, iris scanning, facial recognition are not
suitable for high security systems.
• They fail in cases when face is covered with caps or
make-up, or finger is covered in dirt or glue etc.
• They can also be easily cheated using household
items.
• The proposed finger vein recognition system with
maximum curvature points, is a cost-effective and
highly secure method of personal identification.
• It cannot be cheated as the finger vein pattern is
inside the finger. No cheating methods can be forged.2
 Objectives

• To implement a new and highly secure

method of biometric authentication system,
that cannot be easily fooled.
• To increase the efficiency and reduce the time
required for the biometric authentication
system using maximum curvature algorithm

3
 LITERATURE SURVEY
S.NO PAPER TITLE YEAR OF PROPOSED WORK ADVANTAGES DRAWBACK
PUBLICATION

1 A finger vein 2016 This paper A highly This method

recognition system proposes a finger secure is a highly
vein recognition method of time
system biometric consuming
implemented authenticatio method and
using lacunae, n that cannot is also not
fractal dimension be easily that efficient
and gabor filter as cheated. since it
the algorithms focuses on
used for feature gaps and
extraction and the not the
matching of the actual vein
extracted feature pattern
is done using the
distance classifier

4
 LITERATURE SURVEY
S.NO PAPER TITLE YEAR OF PROPOSED WORK ADVANTAGES DRAWBACK
PUBLICATION

2 Vein Detection 2015 This paper deals Novel This isn’t an

System using with the design method of authenticati
Infrared Light. development of vein pattern on system, it
non-invasive vein analysis just analyses
detection system instead of veins for
and is invasive assisting
implemented intravenous doctors for
based on near access. intra-venous
infrared imaging drug-
and interfaced to delivery.
a laptop to make
it portable. A
customized CCD
camera is used for
capturing the vein
images.

5
 LITERATURE SURVEY
S.NO PAPER TITLE YEAR OF PROPOSED WORK ADVANTAGES DRAWBACK
PUBLICATION

3 High Security using 2015 The aim of this This is a This method
Palm Vein paper is to much more is a very
Recognition introduce a secure slow
Technology. biometric biometric method of
recognition system than biometric
system by the existing authenticati-
scanning and biometric on as it
processing palm systems. takes a lot of
vein images time to
process the
whole palm
vein section.

6
 Existing System
• The existing biometric systems are highly
complex in time and space.
• The are not accurate and fail in many everyday
conditions.
• They generally use extrinsic physical attributes of
a person like finger-prints, which are easily
accessible to others.
• They can be easily cheated using just house-hold
items.
7
 Proposed System
• In the proposed model, we intended to
increase the efficiency and decrease the time
required for finger vein pattern recognition.
• The system will capture finger vein pattern
image using a CCD camera. This is then pre-
processed and masks and filters are applied to
detect the finger vein region.
• Then the vein pattern is extracted using
maximum curvature algorithm
8
Over-all Block Diagram

9
 Finger vein recognition
• To obtain the pattern for the database record, an individual inserts a
finger into an attester terminal containing a near-infrared LED
(light- emitting diode) light and a monochrome CCD (charge-
coupled device) camera. The hemoglobin in the blood absorbs near-
infrared LED light, which makes the vein system appear as a dark
pattern of lines. The camera records the image and the raw data is
digitized, certified and sent to a database of registered images. For
authentication purposes, the finger is scanned as before and the data
is sent to the database of registered images for comparison. The
authentication process takes less than two seconds.
• Blood vessel patterns are unique to each individual, as are other
biometric data such as fingerprints or the patterns of the iris. Unlike
some biometric systems, blood vessel patterns are almost
impossible to counterfeit because they are located beneath the skin's
surface
10
 Maximum Curavature Algorithm
• Step 1: Express the points on the spline parametrically, so the spline is the
set of points of the form (x(t),y(t))(x(t),y(t)), where tt is a parameter.
Here x(t)x(t) represents the xx-coordinate (as a function of the parameter tt)
and y(t)y(t) represents the yy-coordinate. Since this is a cubic spline, you
can find functions x(t),y(t)x(t),y(t) that are cubic polynomials with known
coefficients that provide this parametric expression.
• Step 2: Use the formula for computing the curvature, given a parametric
representation of the curve. This gives you a formula for the curvature as a
function of tt, namely, κ(t)κ(t). Note that since x(t)x(t) and y(t)y(t) are cubic
polynomials, you can explicitly compute their first and second derivatives,
so you can analytically compute an explicit expression for κ(t)κ(t), i.e., for
the curvature as a function of tt.
• Step 3: Find the value of tt that maximizes κ(t)κ(t). Note that we are now
dealing with a function κ:R→Rκ:R→R, i.e., we are in the one-dimensional
case. Thus, we can find the maximum numerically using any of a number of
methods: gradient descent, Newton's method, or a number of other methods.

11
Flowchart

The flowchart depicts the over-all

processing of the finger vein
recognition system.

12
 Softwares Used
• MATLAB (GUIDE)

13
 Results and Discussion
The camera first captures the finger vein pattern
image.

The finger vein region is then identified by applying

mask and multi-dimensional filter.

14
 Results and Discussion

Then the maximum curvature algorithm is used to

extract the binary vein patterns.

This is then cross-correlated with the finger vein

patterns registered to match and identify the
individual and grant access.

15
 Results and Discussion
Through our simulation, when the vein pattern is
registered in the database, the output is obtained as
recognized.

16
 Results and Discussion
And when the vein pattern is not recognized the output
is obtained as not recognized.

17
 Conclusion
• In our proposed system, we use maximum curvature
algorithm to extract vein patterns and match them with
existing patterns in the database. This makes our system
robust and highly efficient, as it focuses on the vein patterns
rather than
• This method is highly secure as the vein patterns are inside
the finger and they are not accessible to anybody. Also the
finger vein patterns leave no trace while scanning and so, the
system cannot be easily cheated.

18
 Future Scope
• In our project we have analyzed how effective
and secure finger vein recognition systems
are, and how it over-comes the disadvantages
of the existing biometric systems.
• In future ,it can be implemented as a
replacement or as an add-on for almost all the
biometric authentication systems

19
 REFERENCES
• [1]Zhi Liu and Shangling Song, “An Embedded Real Time Finger Vein Recognition System
For Mobile Devices”, IEEE Transactions on Consumer Electronics, Vol. 58, No. 2, pp. 522-
527, May 2012.
• [2] Ajay Kumar, Yingbho zhou, “Human Identification Using Finger Images”,IEEE
Transactions on Image Processing, Vol. 21, NO. 4, pp.2228-2244,April 2012.
• [3]Zhi Liu, YilongYin, HongjunWanga, ShanglingSong, QingliLi, “Finger vein recognition with
manifold learning”, Journal of Network and Computer Applications, 33 (2010) 275282
• [4]Desong Wang, Jianping Li and Gokhan Memik, “User Identification Based on Finger-vein
Patterns for Consumer Electronics Devices, IEEETransaction on Consumer Electronics,
Vol.56, No.2, pp.799-804, May 2010.
• [5]Wonseok Song, Taejeong Kim, Hee Chan Kim, Joon Hwan Choi, Hyoun-Joong Kong,
Seung-Rae Lee, “A finger-vein verification system using mean curvature”, Pattern
Recognition Letters, 32, pp. 15411547, 2011.
• [6]Z. Feng, “Variation and Minkowski dimension of fractal interpolation
• surface”, Journal of Mathematical Analysis and Applications, vol. 345,
• no.1, pp. 322-334, 2008.

20
 REFERENCES
• [7]C. Rueden, K. W. Eliceiri, and J. G. White, “VisBio: A computational tool for
visualization of multidimensional biological image data Traffic”, vol.5, pp. 411417, 2004.
• [8]P. Bouboulisa, Leoni Dallab, V. Drakopoulos, “Construction of recurrent bivariate
fractal interpolation surfaces and computation of their box-counting dimension”,
Journal of Approximation Theory, 141, pp. 99 117,2008.
• [9]Sepehr Damavandinejadmonfared, Ali Khalili Mobarakeh, ”Evaluate and Determine
the Most Appropriate Method to Identify Finger Vein”, International Symposium on
Robotics and Intelligent Sensors, Procedia Engineering 41 (2012) 516-512.
• [10] K. I. Kilic and R. H. Abiyev, “Exploiting the synergy between fractal dimension and
lacunarity for improved texture recognition”, Signal Processing, vol. 91, no. 10, pp.
2332-2344, 2011.
• [11]Younghwan Kim, Jang-Hee Yoo, “A Motion and Similarity-Based Fake Detection
Method for Biometric Face Recognition Systems”, IEEE Transaction on Consumer
electronics, Vol. 57, No. 2, pp. 756-762, May 2011
• [12] www.hitachi-ics.co.jp.
• [13] www.retailsystemspl.com.au

21
Thank you

22