LATENT FINGERPRINT AND VEIN MATCHING USING RIDGE FEATURE IDENTIFICATION

Text-only Preview

IJRET: International Journal of Research in Engineering and Technology
eISSN: 2319-1163 | pISSN: 2321-7308
LATENT FINGERPRINT AND VEIN MATCHING USING RIDGE
FEATURE IDENTIFICATION
Rajeswari.P1, Sathya.M2, Joy Kinshy.P3
1PG Scholar, Computer Science and Engineering, Knowledge Institute of Technology, Salem, TN, India
2Assistant Professor, Computer Science and Engineering, Knowledge Institute of Technology, Salem, TN, India
3PG Scholar, Computer Science and Engineering, Knowledge Institute of Technology, Salem, TN, India
Abstract
Fingerprint is an impression of friction ridges of the fingers. It has getting better either by enrollment or by the impressions lifted from
crime scenes. Latent prints are partial prints, invisible and it had been get from accidental impressions of crime scenes. Minutiae
matches had been defined as the points which are marked with 3 different regions like start, end and intersection ridges of the
fingerprints. For an authentication system, full-to-full matching fingerprint are efficient. But it is not efficient in latent-to-full
matching fingerprints. In our proposed system, latent-to-full matching fingerprint must be efficient with the distance had been
calculated with in the minutiae points by using 8x8 Gabor filter, using this spatial frequencies had been calculated. In this case, the
spoof attacks had been occurred. To reduce these attacks, we propose an algorithm, Ridge Feature Identification and it may combine
the work of taking distance minutiae calculation and the finger-vein matching to become the system more efficient and provides the
liveliness in the authentication system.
Keywords: Fingerprint, Latent prints, Ridge Feature Identification, Minutiae matches, Finger-vein.
----------------------------------------------------------------------***-----------------------------------------------------------------------
1. INTRODUCTION
ridges).In fingerprint,level-2 fingerprint features has been
executed with high performance and individuality in the
Now a days, Biometrics maps to a new civilian applications of
fingerprints and it may produce the imperfections randomly in
commercial use. Automatic Fingerprint Identification System
the case of friction ridges and they are known as the minutiae.
(AFIS) appeared as an essential tool for all the biometrics and
These type of fingerprint acquisition typically utilizes the
the law enforcement agencies [1].The demand of the secured
fingerprint
resolution
must
higher
than
biometric system, now lead to the growth in the features and
410dpI.Although,[2]level-1 features may be utilized by
individualities for the responsibility of quite complicated
Automated Fingerprint resolution, and this may produce the
fingerprint and finger-vein present in the fingertips of the
pattern type and ridge flow features present in our fingers and
fingerprint. This important technology is widely used in area-
it may be got from a low-resolution images, and this features
access control, Pc login, and e-commerce. These all biometrics
are used only for fingerprint classification.
are attracted towards this technology, because of password
theft, loss and release of users memory [10].
Fingerprint [6] images are of three types. (i) rolled, (ii)plain
and (iii)latent. Although rolled and plain fingerprint images
In biometrics system, the security and convenience of the
are used for forensic applications, whereas rolled print may be
system are important [10].The system requires high response
used for government applications and commercial one. This
times and fast accuracy. The biometrics includes the patterns
may have the friction ridge impressions of full nail (end-to-
based on fingerprint, finger-vein, facial features, the iris, and
end) for the purpose of registry.
the voice, hand geometry. However, some of the features are
susceptible to forgery, so if it is used in combination the
But in plain fingerprint, once the finger is pressed in a flat
system will be efficient. The fingerprint and finger-vein
surface and not be rolled, both this plain and rolled prints are
produces high confidentiality over other measures.
taken by the live scan machine or inked impressions on paper.
Latent fingerprint is defined as the partial print or injured
1.1 Fingerprint
print. It defines that the impressions we get it in a damaged
In general, not even twin sisters or twin brothers may not have
conditions or partial prints. But half of the fingerprint is there
the same fingerprint. They may be varying with respect to
to identify a system.
their genetic arrangements of cells and tissues. Fingerprint
may consist of friction ridges and it is a combination of
In identification system, the enrolled fingerprint is stored at an
ridges(black
line)
and
valleys(space
between
the
two
initial stage and the verifying fingerprint is the print for the
__________________________________________________________________________________________
Volume: 03 Special Issue: 07 | May-2014, Available @ http://www.ijret.org
17

IJRET: International Journal of Research in Engineering and Technology
eISSN: 2319-1163 | pISSN: 2321-7308
authentication purpose, we have to verify among the enrolled
segment the image into a set a pixels and individual pixel may
prints. If the fingerprint is plain or rolled, it is easy to verify
consist of useful information about the minutiae. Now a day,
the system in AFIS. But if it is latent, the identification system
boundary detection using segmentation is efficient and label
is not successful and it is failed. So [1], the fingerprint
formation is the enhancing technique.
examiners of manual identifiers, use the procedure ACE-V in
the latent fingerprint Identification System. The ACE-V
1.2 Finger-Vein
procedure includes (Analysis, Comparisons, Evaluations and
Verifications).
Finger-vein recognition is a technique to provide liveliness in
the sensor-level spoof attacks[2].In this recognition technique,
Step 1: First, Analysis the image whether rolled, plain or latent
it may provide the finger response to electrical signals,
[3]. It may verify that the sufficient ridge information is
temperature and electrocardiograph signals in the finger, time
available and mark the features along with associated quality
varying perspiration
from fingertips and percentage of
information done by human experts.
generated oxygen saturated hemoglobin in the blood.
Step 2: Compared to the original image in the database
(includes the level 1, level 2 and level 3).
Now a day, it is almost used in biometric and forensics, the
Step 3: Evaluate and classify the fingerprint pair as
vein images are acquired from the near-infrared-based or
individualization (match or non-match).
thermal-infrared-based optical imaging technique. This optical
Step 4: By verifying and check the result by another examiner,
imaging technique is economically feasible and sensitive to
to verify the identity is correct or not.
skin as a deeper tissue features.
The analysis and identifications seems to be critical issues.
The finger-vein patterns can be extracted by placing the finger
The errors may be done by the human examiners like
in between the camera and infrared light source [10].The
erroneous exclusion and erroneous individualization[3].The
infrared light is passed through the hands in the backside of
minutiae
features
includes
ridges
intersection,
ridge
finger and the hemoglobin absorbs the light and produces the
bifurcation, ridge starting, ridge ending provides the marking
patterns of veins in the palm side of the hand as shadows. It
of those particular region and performs the action by taking
consists of vein patterns and irregular shading and noise.
the matching score between the enrolled and verifying
fingerprints and that can be performed by baseline matching
Almost, in a single image, the vein patterns are not clear and it
algorithm. Focus on this method includes the local minutiae
consists of thickness of finger bones and muscles. So,
matching; global minutiae matching and matching score
simultaneous extraction of finger-vein patterns is efficient and
computation are efficient in this method.
useful. Personal Identification using finger vein patterns has
received a lot of interest in research area of forensic and
In many aspects, Feature extraction is a major process. In this
civilian application [2] [10].
feature extraction, the features are defined in [3], CDEFFS
document and use the term consistent here (1) Reference
Miura and Nagasaka et al. [10] using a repeated line tracking
points includes type, location and directions. (2) Ridge flow
algorithm to further improve the performance of vein
map (3) ridge wavelength map (4) Ridge quality map. By
identification. A detailed evaluation of this method may
these features, the feature extraction is efficient over it. This
evaluate the robustness in the extraction of finger vein has
may be generated based on the validated ridges.
been improved randomly by using the local maximum
curvature.
In relevant aspects, Anil k.Jain et.al [1] using Hough
transform is to evaluate the straight lines present in a
In [2], improves the performance metrics by using the finger-
fingerprint images. Based on these observations, edge
vein and low-resolution fingerprint images combines these in
detection is the reprocessing procedure in this method. The
a
new
score
level
combination.
In
this
finger-vein
process includes (1) get an imperfect image as input (2) extent
identification system, extract the shape and improves the
the identity by using arbitrary shapes. Besides, on latent
accuracy in this system. By using this [10], this system may
fingerprint enhancement [6] can be done by providing Gabor
not achieves the high individuality in very large population.
filter for enhancement purpose. Here, it has two parameters,
(1) local ridge orientation and (2) frequency generation.
2. RELATED WORK
According to this method, Gabor filtering can connect the
In this section, we reviewed the related work in two areas. One
broken ridges and separate the joined ridges. Here, in this
with fingerprint and the other work with finger-vein. Mostly,
method, the true ridges are weakened and spurious ridges are
all the algorithms work with the help of the minutiae points
strengthening after this Gabor filtering.
present in the fingerprint. In this method [1], feature extraction
is the initial process and it extracts the minutiae and
Focus on this previous method, Image segmentation is an
orientation field from both the latent print and rolled print.
important method in fingerprint image. This method may
With the use of the gradient based method, local minutiae
__________________________________________________________________________________________
Volume: 03 Special Issue: 07 | May-2014, Available @ http://www.ijret.org
18

IJRET: International Journal of Research in Engineering and Technology
eISSN: 2319-1163 | pISSN: 2321-7308
descriptors are built from the minutiae and orientation field is
alignment-based greedy matching algorithm. By this method,
also reconstructed.
the performance rate may be increased correspondingly.
In [13], exposed the system with reduced manual input and
1. Local minutiae descriptors
improves the matching accuracy. This enhancement algorithm
manually marked the ROI and the singular points. The
In these descriptors, the minutiae points are coordinated and
commercial SDK provides the enhancement algorithm in an
formed as the cylinder like shape with varying size; it is
orientation field estimation algorithm and fits it to the coarse
described as minutiae cylinder code (MCC) by the density of
field estimation as a skeleton. This system performs the
neighboring minutiae in a particular direction.
operation of lights-out mode in an efficient way.
2. Orientation Field Reconstruction
The proposed method in [2] can acquired simultaneous finger-
Gradient based method used in this method and the orientation
vein and finger surface images are presented. This method
field is also reliable with good images and reconstructed only
illustrates and utilizes more user-friendly and peg-free
under the convex hull of minutiae points.
imaging.
The
steps
in
this
method
include
image
normalization, segmentation and rotation of the interclass
1
image had been developed.
=

()

-1
(1)
Anil K.Jain et.al [3] used local minutiae matching, global
Where,
minutiae matching and matching score computation. This [3]
= matching minutiae score around two fingerprints.
may clearly demonstrates the features of the minutiae points
() = the Th pair in matched minutiae cylinder code.
and the lines present. Naoto Miura et.al [10] used the repeated
line tracking method, to detect the patterns of veins and

= 1 - (
)
(2)
removed by background by blacked out regions. The pixel
2
marked as a current tracking point is recorded as a matrix
named as "locus space". The
Where,
locus space values have the high
() = spatial distance.
or frequency.
= number of minutiae in the latent.
In[13],includes four steps to enhance the algorithm,1)manual
Feng et al. [12] extract the fingerprint features and the features
markup of ROI and singular points 2)STFT 3)Orientation field
had been marked in the particular fingerprint. Based on this
estimation 4)Gabor filters.
extracted fingerprint, the orientation field is estimated and the
curvature field also constructed from this features. The
3. METHODS AND DATA ANALYSIS
pyramid formation of fingerprint is made and extracts the
3.1 User Interface Design
singular points at lower and higher levels.
The objective of user interface design is to make the user's
Almost in filtering large fingerprint database for latent
interaction as simple and more efficient as possible, in terms
matching [6], the features in fingerprint includes 3 levels of
of completing user goals is often referred as user-centered
resolutions includes minutiae, pores and ridge shapes. Here [6]
design.
Good
customer
boundary
design
accelerates
described a minutiae-based method and the features includes
concluding the task at hand without drawing fired attention to
the feature marking and feature extraction at lost the filtering
it. Graphic design can be exploited to upkeep its usability and
techniques are enhanced and the matching process starts and
visibility. The design process must balance with the technical
identify a particular person in a system.
functionality and visual elements are used to create a system
that is not only operational but also usable and adaptable to
The ridge lines present in the fingerprint evaluates the
changing user needs.
orientation and curvature field is computed. The singular point
extracts at both high and lowers level locations. The pattern
type is also recognized as loop, tented arch, plain arch, whorl
etc. This system may propose the multistage filtering in this
fingerprint database as follows: singularity filtering and
orientation filtering.
Jianjiang Feng [5] described the method of descriptor-based
minutiae matching algorithm and combining the information
of texture and the minutiae information is performed. The
minutiae correspondence problem solved with a simple
__________________________________________________________________________________________
Volume: 03 Special Issue: 07 | May-2014, Available @ http://www.ijret.org
19

IJRET: International Journal of Research in Engineering and Technology
eISSN: 2319-1163 | pISSN: 2321-7308
In this segmentation process fig.2, take a wide database with
Input finger
rolled fingerprint, the features of the full fingerprint is stored
image1
Apply Gabor
in the NBIS database. At a verification process, a latent of the
filtering
individual is taken and it had been matched with the database
by preceding the first process segmentation. It is a method of
splitting a digital image into multiple segments and this leads
to simply and change the representation of an image into more
Input vein
image1
useful and easy to analyze .This process had been segmented
Noise less image
by using label for every pixels and the pixels with the same
label share certain characteristics.
Apply image
segmentation
Images extraction
Fig- 2 Segmenting a Latent Image
Generate the ridge
feature templates
Score combination
Fig.-3 Binarizing and Minutiae Point Classification
No
Score > K
3.3 Latent Matching Approach
Prearranged a latent fingerprint and a rolled fingerprint, this
method extract extra features from both prints, align them in
Yes
the similar coordinate system, and calculate a match score
amongst them.
Fingerprint
Fingerprint not
matched
matched
3.3.1 Latent Fingerprint Matching
Enhanced latent matching accuracy has been described by
expending features, which are manually noticeable for latent.
Fig-1 System Flow Diagram for the proposed system
However, marking extended features (orientation field, ridge
skeleton, etc.) in poor quality latent is exact time-consuming
3.2 NBIS Segmentation Algorithm
and might be only practicable in infrequent cases. However,
only a minor portion of latent can be properly known using
This algorithm segment the original fingerprint image without
this approach. The segmented image is extracted and formed
line removal process. In this algorithm, the background is
the binary image by the process of binarization.
indicated by the blacked out region. The fig1 demonstrates
clearly that the detected fingerprint regions from the proposed
3.3.2 Feature Extraction
segmentation algorithm are much smaller and more accurate
than those of the previous method. The ability of the proposed
The planned matching approach uses minutiae and orientation
algorithm to reduce the searchable fingerprint area while
field from both latent and rolled prints. Minutiae are manually
improving accuracy can be visualized.
marked by latent examiners in the latent, and automatically
__________________________________________________________________________________________
Volume: 03 Special Issue: 07 | May-2014, Available @ http://www.ijret.org
20

IJRET: International Journal of Research in Engineering and Technology
eISSN: 2319-1163 | pISSN: 2321-7308
extracted using commercial matchers in the rolled print. Based
images by rotating the kernel in six dissimilar directions,
on minutiae, local minutiae descriptors are constructed and
emphasis into the predictable ways of the vein patterns. The
used in the proposed descriptor-based alignment and scoring
maximum of all images is converted into a binary image.
algorithms.
Further development is achieved by a two-level morphological
process: a majority filter smoothed the shapes and eliminates
3.4 Ridge Feature Process
some of the misclassified isolated pixels, and a reconstruction
procedure removes the remaining misclassified areas.
Here the process obtains the essential ridges and minutiae
information from the fingerprint image. This method can then
3.6 Matching Process
define ridge coordinates and extract ridge features between the
two minutiae points. Here, the ridge count (rc) is calculated by
The complete flow of the proposed fingerprint matching
with the number of ridges along the perpendicular axis until
algorithm is as follows:1) Originally match any pair of ridge-
the axis lights the ridge attached to the adjacent minutia. The
based coordinate systems mined from the enrolled fingerprint
ridge length (rl) is the distance on the horizontal axis from the
image and the input fingerprint image using dynamic
joint of the perpendicular and horizontal axis to a minutia. In
programming.2) Select the uppermost degree of corresponding
addition, the process improves the discriminating control of
ridge-based coordinate pairs.3) For every primarily matched
ridge structures, the ridge type (rt) is used as one of the ridge
pair, a breadth-first search (BFS) is achieved to detect the
structures in its place of a minutia type. To regulate the ridge
matched
ridge-based
coordinate
pairs
incrementally.4)
type (rt), all minutia is first ordered as an end point or a
Patterned the strength of the matched coordinate pairs using
bifurcation. If a minutia is an finale point, there is only single
the comparative position and orientation of the minutiae and
ridge fitting to the minutia. If a minutia is a branching, there
count the number of matched minutiae.5) Repeat steps 3 or 4
are three ridges joined to the minutiae.
times and then yield the maximum number of matched
minutiae.6) Calculate the matching score. If the two image
score is matched with other image score this system give the
outcome as both are same fingerprint image else both are not
same image.
4 EXPERIMENTAL ANALYSES
In order to determine the performance enhancement using the
proposed schemes, we performed difficult experiments on our
collected database. The nonlinear score combination may
adjust the matching score by the degrees of consistency
between the two matching score as illustrated below:

^
+
( + )2
= +
Fig-4 Distance Calculation of Minutiae Points a) red-minutiae
points b) blue-distance of minutiae points c) yellow-matching
Where,
process
a=positive constant and it is fixed to 1.
=range of image is selected as [1, 2].
3.5 Fingerprint and Vein Segmentation
=matching score from finger texture.
In vein segmentation, the algorithm without the line removal,
=matching score from finger-vein.
the background is labeled by the blacked out region. The
^ =combined score.
rushed white outlines were drawn manually and are replicated

in the other images to deliver visual orientations for
Where the equation evaluates that the two matching scores are
comparison. This algorithm demonstrates clearly that the
consistent then the final score is distributed by the vein
identified fingerprint regions from the proposed segmentation
matching. If it is inconsistent, the matching score provided by
algorithm are much smaller and more accurate than those of
the modulated joint probability. In most circumstances, the
the earlier method. From this method, the capacity of the
finger-vein matching is more stable, then the whole matching
proposed algorithm to reduce the searchable fingerprint area
system is more or less stable.
while improving accuracy can be visualized.
The model evaluation of proposed system can be measured by
The low contrast images, due to the light scattering outcome,
considering the environment as follows:
are improved and the fingerprint lines are detached using 2D
discrete wavelet filtering. Kernel filtering produces multiple
__________________________________________________________________________________________
Volume: 03 Special Issue: 07 | May-2014, Available @ http://www.ijret.org
21

IJRET: International Journal of Research in Engineering and Technology
eISSN: 2319-1163 | pISSN: 2321-7308
Table-1 Terms and performance of the system
results for two different latent fingerprint databases with a
large background database of around 32K rolled prints. The
Terms
Fingerpri
Finger-
Combine
comparison performance of the proposed matcher with three
nt
vein
d Results
different state-of-the-art fingerprint matchers. Experimental
Performance
89
88
92
results show that the proposed algorithm performs better than
Minutiae Points
69
5
75
the three fingerprint matchers used in the study across all
image qualities. A score-level fusion of the proposed matcher
Distance
96
7
98
and one of the commercial matchers shows a further boost in
Calculation
the matching performance. Latent fingerprint used in this
Security
90
90
99
descriptor based Hough Transform compares only the
Authentication
86
86
95
minutiae features like ridge start, end and bifurcations. In our
work, enhancing this project by taking the distance between
The above matrix demonstrates the performance and terms in
the minutiae points and compare with the latent image. Finger-
case of the approximation by using the algorithm level
vein matching is using in this project to overcome the spoof
description. First, the performance of the system had been
attacks in this latent fingerprint matching .This may be done
demonstrated and the match score is consistent high. Second,
by using the Gabor filter in ridge feature identification. This
minutiae points had been extracted that shows the combined
may provide the authentication in an efficient way. In future
results with reduced factors. Then, the distance minutiae
enhance this system by applying various algorithms with
calculation by using Gabor filter is demonstrated with very
different databases.
high performance. And the security and the authentication is
also high is this system of measurements.
REFERENCES
[1]. A. A. Paulino, J. Feng, and A. K. Jain, "Latent fingerprint
120
matching using descriptor-based Hough transform," in Proc.
Int. Joint Conf. Biometrics, pp. 1-7, Oct. 2011.
100
[2]. Ajay Kumar and Yingbo Zhou, " Human Identification
80
Using Finger Images," IEEE Trans. On Image Processing,
vol. 21, no. 4, Apr 2012.
60
finger-print
[3]. A. K. Jain and J. Feng, "Latent fingerprint matching,"
40
IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 1, pp.
88-100, Jan. 2011.
20
finger-vein
[4]. D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar,
0
Handbook of Fingerprint Recognition, 2nd ed. New York:
combined
Springer-Verlag, 2009.
results
[5]. J. Feng, "Combining minutiae descriptors for fingerprint
matching," Pattern Recognit., vol. 41, pp. 342-352, 2008.
[6]. J. Feng and A. K. Jain, "Filtering large fingerprint
database for latent matching," in Proc. ICPR, Dec. 2008, pp.
1-4.
[7]. J. Qi, S. Yang, and Y. Wang, "Fingerprint matching
combining the global orientation field with minutia," Pattern
Chart-1 Performances of the Overall System
Recognit. Lett., vol. 26, pp. 2424-2430, 2005.
[8]. J. Gu, J. Zhou, and C. Yang, "Fingerprint recognition by
The overhead chart embodies the whole performance of the
combining global structure and local cues," IEEE Trans.
latent fingerprint and finger-vein system from the matrix of
Image Process., vol. 15, no. 7, pp. 1952-1964, Jul. 2006.
the Table 1.
[9]. M. Tico and P. Kuosmanen, "Fingerprint matching using
and orientation based minutia descriptor," IEEE Trans.
5.
CONCLUSIONS
AND
FUTURE
Pattern Anal. Mach. Intell., vol. 25, no. 8, pp. 1009-1014,
Aug. 2003
ENHANCEMENT
[10]. Naoto Miura, Akio Nagasaka, Takafumi Miyatake,
Fingerprint matching algorithm designed for matching latent
"Feature extraction of finger-vein patterns based on repeated
to rolled/plain fingerprints which is based on a descriptor-
line tracking and its application to personal identification"
based Hough Transform alignment. A comparison between the
Machine Vision and Applications ,Feb.2004
alignment performance of the proposed algorithm and the
[11]. R. Cappelli, M. Ferrara, and D. Maltoni, "Minutia
well-known Generalized Hough Transform shows the superior
cylinder-code: A new representation and matching technique
performance of the proposed method. Here reported matching
__________________________________________________________________________________________
Volume: 03 Special Issue: 07 | May-2014, Available @ http://www.ijret.org
22

IJRET: International Journal of Research in Engineering and Technology
eISSN: 2319-1163 | pISSN: 2321-7308
for fingerprint recognition," IEEE Trans. Pattern Anal. Mach.
Intell., vol. 32, no. 12, pp. 2128-2141, Dec. 2010.
[12]. S. Yoon, J. Feng, and A. K. Jain, "Latent fingerprint
enhancement via robust orientation field estimation," in Proc.
Int. Joint Conf. Biometrics, New Delhi, India, Oct. 2011, pp.
1-8.
[13]. S. Yoon, J. Feng, and A. K. Jain, "On latent fingerprint
enhancement," in Proc. SPIE, Apr. 2010, vol. 7667, no.
766707.
BIOGRAPHIES
RAJESWARI.P is a student pursuing PG
Degree in Computer Science and Engineering
at knowledge institute of technology, Salem.
Research Interest includes Image Processing
and
Information
Security.
contact:[email protected]
SATHYA.M is an Assistant Professor in Knowledge Institute
of
echnology,Salem.Research
Interest
includes
Image
Processing and Web Mining.
JOY KINSHY.P is a student pursuing PG
Degree in Computer Science and Engineering
at knowledge institute of technology, Salem.
Research Interest includes Image Processing
and Mobile Computing.
__________________________________________________________________________________________
Volume: 03 Special Issue: 07 | May-2014, Available @ http://www.ijret.org
23