Fingerprint Authentication: Matching Methods, Errors, and Integration

This research explores the various fingerprint matching methods and in particular correlation-based matching, minutiae-based matching, and non-minutiae feature-based matching. The report also identifies fingerprinting errors such as False Rejection Rate, False Acceptance Rate, Equal Error Rate, Zero FMR, and Zero FNMR. The report further explores the transformation and integration of biometric capabilities and issues that arise when integrating these biometric methods.

5/27/2019
Fingerprint Authentication
Student’s name
Institution Affiliation(s)

Table of Contents
Abstract......................................................................................................................................3
1. Introduction and Background.................................................................................................4
1.1 Introduction......................................................................................................................4
1.2 Background.......................................................................................................................5
1.3 Research Aims and Questions..........................................................................................6
2. Literature Review...................................................................................................................6
2.1. Fingerprint matching.......................................................................................................6
2.1.1. Correlation-based matching......................................................................................7
2.1.2. Minutiae-based matching..........................................................................................8
2.1.3. Non-Minutiae feature-based matching...................................................................11
2.2. Performance Evaluation................................................................................................13
2.3 Fingerprinting Errors......................................................................................................13
2.3.1. False Rejection Rate (FRR)....................................................................................14
2.3.2. False Acceptance Rate (FAR).................................................................................16
2.3.3. Equal Error Rate.....................................................................................................18
2.3.4. Zero FMR...............................................................................................................22
2.3.5. Zero FNMR.............................................................................................................24
2.4 Transforming and integrating your biometrics capability..............................................25
2.4.1. Systems integration expertise.................................................................................26
2.4.2. Issues in Integrating Biometrics.............................................................................27
2.4.3. Integrated Biometric Technology Development.....................................................27
2.4.4. Cost issues in Fingerprinting..................................................................................28
3. Proposed Method and Future Work.....................................................................................29
4. Conclusions..........................................................................................................................30
5. References............................................................................................................................31
Table of Figures
Figure 1: Types of fingerprints used as evidence.....................................................................10
Figure 2: Biometric Error Rates...............................................................................................13
Figure 3: False Accept Rate.....................................................................................................15
Figure 4: Graph showing the relationship between errors (CER, FRR, and FAR)..................17
Figure 5: Biometrics Error Rates.............................................................................................18
Figure 6: An example of FMR(t) and FNMR(t) curves...........................................................22
Figure 7: Relation between FNMR and FMR..........................................................................23
1

Abstract
Fingerprint authentication is a biometric method that is used for a person’s
identification. The method has been widely used by security agencies such as the police or in
companies to identify employees. This research explores the various fingerprint matching
methods and in particular correlation-based matching, minutiae-based matching, and non-
minutiae feature-based matching. The report also identifies fingerprinting errors such as
False Rejection Rate, False Acceptance Rate, Equal Error Rate, Zero FMR, and Zero
FNMR. The report further explores the transformation and integration of biometric
capabilities and issues that arise when integrating these biometric methods. Integrated
biometric technology development and factors influencing fingerprint integration such as
cost have been discussed. Various tables have been provided and outline the various
literature reviews that were instrumental in carrying out this research.
Keywords: Biometric, Fingerprint, fingerprint matching, fingerprint identification, minutia,
fingerprint recognition.
2

1. Introduction and Background
1.1 Introduction
Fingerprints appear at the patterns discovered on a fingertip. There are multiplicities
of methods to fingerprint authentication for example as customary police technique, by
means of pattern-matching systems or tools, plus things similar to more border patterns plus
Ultra-Sonics. This appears to be an extremely high-quality preference for in-house systems.
In the identification of fingerprints, various techniques are used, which include using
ultraviolet light which identifies a fingerprint on surfaces in which fingerprints cannot be
seen easily (Kioc, Maharjan, Adhikari, & Shrestha, 2018). Fingerprints can also be identified
using photographs, which are also done by pressing an individual finger onto an ink.
Fingerprint can be developed through a visible technique known as the ‘powder and brush’
technique where the surface is brushed with a powder that is very fine and sticky to the
droplets.
In situations where the surface may become some surfaces may absorb the powder
and make the fingerprints undistinguishable, electrostatic is used (Kioc et al., 2018). Here,
very fine powder will be placed on an electrode that is positively adjacent where it becomes
charged; hence is attracted to the specimen that is negatively charged. High voltage moves
the particles to travel quickly and stick firmly to the fingerprint. As this process continues,
the fingerprint will be sufficiently built-up. Casting is the best method of preserving plastic
fingerprint. Here, a liquid material will be poured on the fingerprint and also hardened in
order to make an impression cats. This casting method is best since it can store fingerprint for
a longer duration. Other fingerprints that are visible can be preserved using photography
(Hofer, 2018).
Fingerprints are scanned into the automated fingerprint system where ridge details
and other identifying characteristics are digitized in such in detail that the system can find a
match among the millions of fingerprints that are available in the database. This new
structure of identification has helped governments in different ways. It is vastly used in civil
identification projects like registration for elections, driving license, welfare systems et
cetera. Through this system, a government can make sure that no identity theft takes place, or
one person is not using two identities in order to vote. This kind of crime is quite common all
over the world. Sometimes a highly sensitive job requires the employer to check the
background of the candidate for the job so that all kind of risks can be avoided. This type of
identification check is mostly done for high-level posts in the government or law enforcement
agencies (Hofer, 2018).
For instance, in the United States of America, this automated system of fingerprint
identifications has the entire fingerprint collection from the country and is under the authority
of the Federal Bureau of Investigation. Other countries also have their own automated
fingerprint identification systems which have capabilities to do work like electronic image
storage, hidden searches, and the exchange of these fingerprints can also take place. It is used
for various reasons which can include identification of criminals, checking of backgrounds,
and in passport checks, it is one of the most important checks. This system is now popular
3

worldwide as it has made life much easier for law enforcement agencies to identify good
from the bad. There is a misconception that attempting to recover fingerprints from a firearm
has fewer chances of happening but this is not right because fingerprints or palm prints can be
removed from a firearm, spent cartridge, or magazine; therefore all firearms should be
checked thoroughly for evidence (Kellman et al., 2014).
In the international level, the European police agencies have now started to share its
automated fingerprint identification system with other countries in order to progress against
the war on terror or other cross border crimes that occur. This system on the investigation has
become very popular since the start of the war on terror in the world. From the year 2000
onwards this war has taken its toll, and the automated system of investigation has really
helped to decrease the criminal activities going on in the world. A lot of criminals are being
caught due to this system (Kellman et al., 2014).
1.2 Background
Biometrics have been taken as automatic detection of people foundational on their
physiological or behavioral features. Uni-modal new technologies based biometric systems
carry out person identification foundational on a single source of biometric data and are
influenced through issues similar to non-universality, noisy sensor data plus lack of
independence of the selection of the biometric attribute, lack of an invariant illustration for
the biometric feature as well as vulnerability to circumvention. A number of these issues are
able to be improved through making use of the state-of-the-art integrated biometric systems
that combine confirmation as of numerous biometric sources. Combination of proofs acquired
from numerous indication is a challenging aspect plus combining at the identical score level
is the widespread majority method for the reason that it presents the most excellent trade-off
among the information content as well as the easiness in integration (Chen, 2019).
There are numerous biometric systems and technologies to facilitate diverse kinds of
implementations. To select the correct biometric to be extremely effective for the particular
state, one has to map through several multifaceted vendor products as well as keep an eye on
future technology based plus standards enhancements. Below is an outline of biometrics
technology and systems.
Hand geometry entails assessing and analyzing plus determining the structure and
shape of the hand. It might be appropriate where there are more clients or where client access
the system occasionally. Accurateness is able to be extremely high if preferred, as well as
flexible performance tuning plus arrangement are able to contain numerous applications.
Corporations are making use of hand geometry readers in diverse scenarios, comprising
attendance and time recording (Bailey, 2018).
The retina is a biometric method and entails assessing the layer of blood vessels
located at the back of the human eye. This method entails making use of the low-intensity
light source by means of an optical coupler to scan the distinctive eye blood vessels patterns
of the eye’s retina. Retinal scanning is able to be quite perfect; however, does necessitate the
user to look into a receptacle as well as focus on a particular point inside the system.
4

Iris-based technology of biometric systems entails assessing characteristics discovered
in the colored eye ring of tissue of humans that surrounds the pupil. This utilizes a reasonably
usual camera component and necessitates no close contact among the client and the reader.
Additionally, it has the power for higher than standard template matching competence (W.
Yang, Wang, Hu, Zheng, & Valli, 2019).
Face recognition based system investigations facial features. It necessitates a digital
camera to build up a facial image of the client intended for verification. For the reason that
facial scanning requires additional peripheral things that are not incorporated in fundamental
personal computers, it is more of a position marketplace intended for network verification.
Though, the casino business has capitalized on this technology to produce a human’s facial
database of scam artists intended for rapid recognition through security staff.
Signature-based authentication systems make use of the investigation the means client
signs his name. Signing features, for example, velocity, speed as well as pressure are as
significant as the complete signature's fixed shape. People are intended for signatures by
means of transaction associated characteristics confirmation (W. Yang et al., 2019).
A voice-based system that is used for the verification is foundational on voice-to-print
verification, where complex technology changes voice into text. Voice technology based
biometrics necessitates a microphone, which is accessible by means of personal computers
these days Voice biometrics is to substitute the presently employed techniques, for example,
passwords, PINs or account names. However, the voice will be a matching method intended
for finger-scan systems, as numerous people notice finger scanning like a superior
verification form (W. Yang et al., 2019).
1.3 Research Aims and Questions
This aim of this research is to explore the various fingerprint matching methods and in
particular correlation-based matching, minutiae-based matching, and non-minutiae feature-
based matching. The report also purposes to identify fingerprinting errors such as False
Rejection Rate, False Acceptance Rate, Equal Error Rate, Zero FMR, and Zero FNMR. The
research questions are given as follows:
a) What are the various methods for fingerprint matching?
b) What are the types of fingerprinting errors?
c) What are the transformation and integration of biometric capabilities and issues that
arise when integrating these biometric methods?
d) What are the factors influencing fingerprint integration?
2. Literature Review
2.1. Fingerprint matching
The fingerprint identification and matching process are used to evaluate the strange
and the recognized friction skin ridge feelings from palms or fingers. The identification helps
to ascertain if the impressions are from the identical palm or finger. The roughness of the
ridged skin is flexible meaning that there cannot be two fingerprints that are exactly similar.
Identification can also be termed as individualization. Identification occurs when an expert
5

computer system or expert operates under threshold scoring regulations. It is used to exclude
one finger or palm from others. Sometimes differences or dissimilarities may arise from the
fingerprint identification process. These differences do not imply that there is no
identification.
2.1.1. Correlation-based matching
It is a fact that non-identification would not be possible because the print contains so
many matching characteristics; for instance, it has a total of 28 ridges structures that are
clearly observable. A print with many matching characteristics like this confirms
identification. It would thus not have any dissimilarity (Konecny, Prauzek, Tran, Martinek, &
Hlavica, 2018). The 28 ridge structures in identification are so much and efficient to confirm
the presence of identification in this scenario. Dissimilarity can only be in the prints that are
not matching. The structures are sufficient matching characteristics; hence, they can be used
to make an evaluation to remove the possibility that the giver of the latent print could be
someone else. Dissimilarity only shows that there is inadequate detail to be certain of the
detection. Uncertainty may exist in some latent print assessors who are interchanging the
terms distortion and dissimilarity (H. Liu, Wang, Tang, & Jezek, 2012). The impact of such
misunderstanding may be a loss of credibility when the latent print examiners cannot support
their results. The similarities are used to ascertain identity. However, dissimilarity proves that
two prints are not matching; hence; they are not from the same print. When matching
characteristics have been found to detect an identity, there cannot be dissimilarities. The
notion that dissimilarity can be present despite the number of matching features is not
applicable. If this were accurate, then there would forever be dissimilarity. This would
eventually mean that identification can never be made (Konecny, Prauzek, Kromer, &
Musilek, 2016).
Sometimes distortions can also change the manifestation of prints. The distortions can
also obstruct with the relationship. They are recurrent in all prints. Alteration is found in both
latent and pattern prints that have a similar origin. There are instances where the distortions
can be noticed. This is because it is never possible to fully capture all the details of the entire
print even when taking a rolled and known impression. The fingerprint identification can only
be made by the fingerprint examination experts (F. Zhao, Huang, Wang, & Gao, 2010).
Currently, the knowledge of fingerprint detection is better than all other forensic sciences.
The outline of ridges on the finger pads is unique. It is impossible to find two people whose
fingerprints are similar even if the individuals are identical twins. The print can be detected
when the fingers are oily or dirty and when they are latent. The injuries, for instance, the
scrapes and burns, cannot change the ridge structure. When a fresh skin develops in, a similar
pattern comes back. There are no similar fingerprints that have been established in the many
billions of automated computer and human comparisons (Akinyele, Sarumi, Abdulsamad, &
Green, 2018). Therefore, fingerprints are the foundation for illegal records. Hence, it has
served in all governments globally for over 100 years to detect criminals. The fingerprint
identification also continues to develop as the first method for identifying people. It also
surpasses DNA and all other human identification systems to discover additional rapists,
murderers, and serious offenders (Luo, Lorentzen, Valestrand, & Evensen, 2018).
6

In summary, the fingerprint identification effects further helpful identifications of
people internationally every day than other human identification processes. The little
dissatisfaction over fingerprint proof may be due to the wish to drive the resolution of
fingerprint examinations to an equal rank of conviction as that of DNA investigation. The
fingerprint society maintains the need for impartiality and continued exploration in the
vicinity of friction ridge scrutiny.
Table 1. Analysis of Correlation-based fingerprint matching
S
No.
Author Year Method Accuracy/
performance
Benefits/Restrictions
1 Konecny et al. 2018 Point-to-point Scan
Matching algorithm
based on cross-
correlation
EER 5.1% Enhances the degree of match
between two fingerprint
images/computationally
intensive
2 Liu et al. 2012 The cross-correlation-
based image
matching
EER – 2.0% Robust for low quality
fingerprint
images/effective
use only for
verification units
3 Konecny et al. 2016 Scan cross-
correlation method
EER – 1.90% The localization of mobile
robots in outdoor and indoor
environments
4 Zhao et al. 2010 Multiscale oriented
corner correlation
(MOCC)
A scale
changes up to
a factor of 7
The method is rotation
invariant and capable of
matching image pairs
5 Akinyele et al. 2018 Automated
Fingerprint
Verification System
simulating both
Minutiae Based
Matching and Cross-
Correlation
Coefficient Matching
A matching
score above
80% threshold
for Matching
Pair and
below 80%
threshold for
Non-Matching
Pair.
The method used MATLAB
simulation to align the
minutiae of the two-
fingerprint image and stored
templates
6 Luo et al. 2018 Scan cross-
correlation method
EER 2.98%
Average
matching
Simple and robust for the low
quality image, direct grayscale
matching/not invariant to
rotation.
2.1.2. Minutiae-based matching
Fingerprint biometric technology has been widely used since its discovery in the late
19th century and first made commercially available in the 1970s, as noted by Zaeri (2011).
The distinctiveness and long term invariance of fingerprints, except in cases of bruises and
cuts, makes this technology reliable. With the advent of computers, the development of
automated fingerprint technology took effect. The first step of fingerprint authentication
7

process involves the acquisition of fingerprint impression by use of an inkless scanner ( Liu,
Yang, Yin, & Wang, 2014). There are various types of scanners, including capacitive, optical,
thermal, and ultrasound sensors used to collect a digital image of the surface of a fingerprint.
According to the National Science and Technology Council, optical sensors are the most
commonly used today. The collected image would be digitized at typically 500 dots per inch
and with 256 gray levels per pixel. The digital image captures unique features of minutiae
comprising of ridge endings and bifurcations (Le, Nguyen, & Nguyen, 2018). An automated
feature extraction algorithm then locates these features from the fingerprint image with each
feature represented by its respective location and direction. The ridges would normally be
further enhanced to nullify the effect of noise. Finally, the matcher subsystem would attempt
to match these sets of features and would be expressed as a score from where a decision of
matching would be made. A decision threshold would normally be selected prior to this and
scores below the threshold would be a mismatch while those above the threshold lead to the
declaration of a correct match (Kanchana & Balakrishnan, 2015).
Consequently, fingerprint biometrics faces user acceptance challenges with the public
further raising concerns on privacy which involves the protection of their personal data
against any form of misuse including identity theft, loss of anonymity and the possibility of
obtained data revealing medical information (Peralta, García, Benitez, & Herrera, 2017).
Lerner argues that with mass biometric identification, “the big brother” would always be
watching and would use such opportunities to track dissidents and make resistance more
difficult as it happened in the 1960s and 1970s with the COINTELPRO program by the FBI
(Fu & Feng, 2015). The researcher cites the US as an example of a government that has
access to the universal biometric identifier, also used for commercial transactions like
banking (Kai Cao et al., 2012).
Similarly, fingerprints could be lifted off surfaces of glass, even from fingerprint
scanners by use of a cube of gelatin and graphite powder and used to fool scanners elsewhere.
But Chaudhari and Patil (2014) argue that the Privacy Act 1974 prohibits federal agencies
from collecting, using, or disclosing personal information, including fingerprints.
Accordingly, this act protects personal biometric information from being used by federal
agencies. Hygiene issues have also been cited with fingerprint biometric technology as those
whose identities are being identified have to place their fingers on scanners shared by all such
persons(Hajare, 2016). Diseases could be transmitted through contact in such cases. But
opponents of this argument claim the risk, in this case, to be insignificantly minimal.
Otherwise, humans would fall sick by everyday use of doorknobs at homes, workplaces, and
vehicles since the risk involved are similar (Bahaa, 2013a).
Table 2: Performance Analysis of minutiae-based fingerprint matching
S
No.
Author Year Method Accuracy/
performance
Benefits/Restrictions
1 Le et al., 2018 Fingerprint matching
algorithm based on
Minutia Cylinder-Code
on Graphics Processing
EER - 1.96% Suitable for a real-time
identification application
8

Units
2 Liu et al. 2014 A singular value
decomposition (SVD)-
based minutiae matching
method
EER – 2.25% Stage I discovers minutia
pairs via SVD-based
decomposition of the
correlation-weighted
proximity matrix. Stage II
removes false pairs based
on the local extensive
binary pattern (LEBP) for
increasing the reliability of
the correspondences.
3 Kanchana &
Balakrishnan
2015 Minutia tensor
matrix (MTM),
Spectral
Matching.
EER – 1.98 % Efficient representation
of fingerprints, Invariant
to rotation and small
distortions, Simplifies
the computational
complexity
4 Peralta et al. 2017 Generic decomposition
methodology for
minutiae-based matching
algorithms
EER – 1.16 % Splits the calculation of the
matching scores into lower
level steps that can be
carried out in parallel in a
flexible manner.
5 Akinyele et al. 2018 Automated Fingerprint
Verification System
simulating both
Minutiae Based
Matching and Cross-
Correlation Coefficient
Matching
A matching score
above 80%
threshold for
Matching Pair
and below 80%
threshold for
Non-Matching
Pair.
The method used
MATLAB simulation to
align the minutiae of the
two-fingerprint image and
stored templates
6 Zaeri 2011 Minutiae-based
Fingerprint Extraction
and Recognition
EER – 1.18% Pre-alignment phase not
required, Invariant to
distortions such as
rotation and translation,
Low computational
complexity
7 Fu & Feng 2015 Minutia Tensor Matrix
(MTM)
EER – 2.10% The proposed method has
stronger description ability
and better robustness to
noise and nonlinearity.
8 Cao et al. 2012 Minutia handedness EER – 1.21 % Reference points are
detected, and additional
checking conditions are
added to ensure that
genuine and accurate
reference points can be
found.
9

9 Chaudhari &
Patil
2014 Crossing Number
Concept (CN)
EER – 1.32 % Performance of a
conventional fingerprint
recognition algorithm can
be improved by
incorporating minutia
handedness with a small
increment of template size.
10 Hajare 2016 Artificial Neural
Networks,
Backpropagation
algorithm
EER – 1.76 % For this system, some
methods at coding and
algorithm level used to
improve the performance
of the recognition system.
11 Bahaa 2013 A new thinning
algorithm, a new
features extraction and
representation, and a
novel feature distance
matching algorithm.
EER – 2.11 % The proposed algorithms
are optimized to be
executed on low resource
environments both in CPU
power and memory space
2.1.3. Non-Minutiae feature-based matching
An indispensable tool to the criminal justice system, to securities institutions
worldwide, is found on every human being and are unique to every human being:
fingerprints. Fingerprints are the result of the friction ridge skin of the fingers, sides of the
palms, and soles of the feet that leave almost invisible impressions when they come into
contact with surfaces. Described first by Nehemiah Grew in 1684, fingerprints have become a
cornerstone of evidence in the criminal justice system (Shashi, Raja, Chhotaray, & Pattanaik,
2011). The use of fingerprinting to solve criminal cases began almost 200 years ago in
Argentina with a Buenos Aires murder case. It would be 20 years before fingerprints would
prove to be a valuable source of evidence and verification for England by way of inspector
Charles Stockley Collins (Shashi et al., 2011). Systemic use of fingerprinting in the United
States actual began with civil service applicants. In 1902, Henry P. de Forest would collect
the fingerprints of men applying for civil service to prevent fraudulent applications from
being submitted. It would be a year later that fingerprinting would have a primary role in the
American criminal justice system through the American Classification System, a direct result
of the work of Captain James H. Park (Liu & Guo, 2014).
10

Figure 1: Types of fingerprints used as evidence (Source: Yang, 2011).
Present day, fingerprints are an age-old method of identification and an accepted form
of evidence in criminal proceedings. The absolute nature of fingerprints is one reason for this.
No two people in the world have the same prints- not even those of identical twins. Because
of this, and the fact that fingerprints do not alter or change as one grows and ages,
fingerprints provide an infallible means of identifying a suspect (Yang, 2011). The physical
composition of one's fingerprints are the ridges on the fingers, hands, and feet. Ones “ridges”
can fall into any one of three classifications: arches, loops, and whirls. Some people have
more than one, all, or any combination of these classifications. These distinct classifications
provide scientists with a point of reference for comparison. Fingerprints from a crime scene
or evidence can be matched, or not, by identifying identical points. While experts may vary,
the most common range of acceptable points is somewhere between 12 and 20 points of
similarity (Jain & Feng, 2011).
For instance, England and Wales also use fingerprinting in their criminal justice
system for identification and evidentiary purposes. Their given standard is 16 to 20 points or
similarity. They call it the “16 point standard” because it is believed to be the minimum
compatibility needed to a zero rate of identification of fingerprints and a higher rate of court
quality identifications. Essentially, this standard prevents mistakes and provides the
prosecution with solid trace evidence that would be difficult to dispute (Zhao, Zhang, Zhang,
& Luo, 2010).
There are not many studies on fingerprinting error rates, but confidence in the
institution remains high. That, however, is not the issue, according to Kumar (2018), it is a
question raised by Dr. Jennifer Mnookin. “What matters here isn't, are your fingerprints
really different from that guy over there. The real question is, is some part of your fingerprint
sufficiently similar to some part of his that a competent examiner might mistake some part of
your print for a part of somebody else's print?” With respect to Dr. Mnookin, fingerprints as a
means of intimate description are unsurpassed by nothing short of DNA. Barring mutilation,
fingerprints cannot be changed by a person no matter what their crime or motivation (Zhao et
al., 2010). Fingerprints speak of physical presence in an environment where a crime was
committed or on the evidence used in the commission of a crime providing law enforcement
with the ability to link subjects to circumstances and the means to prove it.
Table 3: Performance Analysis of Nonminutiae feature-based fingerprint matching
S
No.
Author Year Method Accuracy/
performance
Benefits/Restrictions
1 Yang 2011 Pores, Difference of
Gaussian filtering,
pore–valley descriptor
EER – 1.18% Partial fingerprints can be
aligned/ suitable for high-
resolution fingerprints.
2 Liu & Guo 2014 Gabor filter, multi
association matching
features algorithm
82.3% Accuracy Improved accuracy for
Occluded fingerprint /
binarization and thinning
required
3 Shashi et al. 2011 DWT based Fingerprint EER – 2.28% The comparison of test
11

Recognition using Non-
Minutiae (DWTFR)
algorithm
fingerprint with database
fingerprint is decided
based on the Euclidean
Distance of all the
features. It is observed
that the values of FAR,
FRR, and TSR are
improved compared to the
existing algorithm.
4 Jain & Feng 2011 Poincare index method,
extended features,
neighboring minutiae-
based descriptor
82.9% Accuracy Improvement in the
matching accuracy for low
quality latent fingerprints,
robust to noise /accurate
estimation of extended
features is required.
5 Kumar, 2018 2018 Non-minutiae-based
features and machine-
learning-based
fingerprint matching
approaches
EER – 1.41% Robust against non-linear
deformation/improvement
in matching is needed for
low-quality images
6 Zhao et al. 2010 Pores, Difference of
Gaussian filtering,
pore– valley descriptor
Accuracy of
98%
Partial fingerprints can be
aligned/ suitable for high-
resolution fingerprints.
2.2. Performance Evaluation
Bose & Kabir (2017), point out at biometric identity verification as a radical
alternative to these traditional forms of identification and verification. Biometrics technology
employs behavioral or physiological traits to identify the identity of individuals, including
fingerprints, retinas, typing styles, teeth, and speech recognition and hand geometry. Since
the biometrics would be an individual’s intrinsic property, duplication, and sharing of user
identity become difficult. Furthermore, it would only take serious accidents and happenings
for these traits to be lost. But Kellman et al. (2014) point out the variability in performance,
capabilities, and complexity of each of the available biometric technologies. Hence, well-
informed decisions should be made on the type of biometrics appropriate for any given
circumstance. In most cases, a combination of several of these physiological and behavioral
traits would ensure the reliability of the obtained information.
2.3 Fingerprinting Errors
Fingerprint biometrics presents two kinds of recognition errors: false accept rate,
FAR, and false reject rate, FRR. While false accept occurs when a non-matching fingerprint
is accepted as a match, false reject occurs when the system rejects matching fingerprint. FAA
refers to these errors as false match rate, FMR, and false non-match rate, FNMR,
respectively, while Champod (2015) defines these using false positive and false negative,
respectively. These two errors are complementary such that with the lowering of one of them,
the other increases automatically. Operating at null error rates for both would not be possible.
12

Schultz, Wong, & Yu (2018), recommend operation at equal error rate, ERR, where both
error rates are equally citing the possibility of achieving error rates of 10-4 false reject and 10-6
false except for high-performance systems. Garrett, Mitchell, & Scurich (2018), notes that
fingerprint biometrics technology experiences lower accuracy than iris scans because of its
fewer degrees of freedom at 40 against that of irises at 200. Those with faint fingerprints and
without fingers do not qualify to use the automated fingerprint identification system. Poor
quality of input image would not be accepted by the system during enrollment and also
during authentication. These two deficiencies cause failure to enroll, FTE, error. According to
Liu, a failure in the biometric test could be an indication of “an impostor or an honest person
falsely rejected” (Bahaa, 2013b). Either way, the consequences remain undesirable, and the
action should be taken to limit such eventualities.
There are algorithms involved in matching the fingerprints. This is a vast system and
not that simple to use. Different kind of software is needed for this system to work. That
software needs to be installed before the automated fingerprint identification system can be
properly used. These finger matching algorithms can differ to a great extent due to the error
rates. There are two kinds of error rates, first is type 1, also called false positive, and the
second is type 2, also known as a false negative. There other things also in which they differ
from each other such as independence from the center of the fingerprint pattern and image
rotation invariance. There are many critical elements of this system which depend upon the
accuracy of the algorithm potency of image quality, the speed of the matching of the print in
the system and the features mentioned previously about this system (Probst & Reymond,
2018).
2.3.1. False Rejection Rate (FRR)
False Reject Rate is also known as Type I error or False Non- Match Rate. It is the
degree of probability that the biometric system will incorrectly reject the access of an
authorized person. This occurs when a biometric template does not tally with the person.
They become unidentified or unverified by the system. This, in a working environment, can
cause unnecessary frustration on the staff, logjams, thus reducing productivity (Young,
Byunggeun, Seok, & Jong, 2018).
There is special hardware available for the use of the system, and the usage of it
depends upon the work needed by it. Some of the large scale users of this system use this
hardware while others simply install the software required and make use of it. Large scale use
of it is mostly in the law enforcement departments who use this automated system of
fingerprint identification most frequently (Garrett et al., 2018). There is basically a two-stage
search system; the first one is conducted through global fingerprint characteristics, and the
second one is called the minutia matcher. These two stages are very much preferred for the
search procedure. All this is in return used to bring the matched result from the search
system. At times it is possible that more than one possible result comes out, and this is only
possible when numerous records of the same person are recorded in the database. These
searches conducted can bring up a lot of various results, so, in order to reduce the possibility
of error, a wide search is conducted by some organizations. The fingerprint searching system
has poor quality input data because of which a lot of results come out of one search. When
13

this system was first introduced, it was operated manually but nowadays through lights-out or
auto-confirm algorithms generate the matched result automatically without any human effort
put into it. There is a rapid increase in the use of this auto-confirm system, especially in the
identifications of people who are related to any kind of criminal activity (Kellman et al.,
2014).
Figure 2: Biometric Error Rates (Source: Yildiz et al., 2016).
The fingerprint authentication or recognition is done by various processes. The proper
study of the print patterns of the print is required in order to make a comparison between
different patterns. There are various patterns found within a fingerprint feature such as the
arch pattern, the loop pattern, and the whorl pattern. Basically, these patterns have
characteristics of that of ridges and minutia points. The knowledge about the human skin is a
necessity so that this technology can be used properly (Korolov, 2019). In an arch shape
pattern, the lines enter from one side and after making an arch shape ridge in the middle, exits
from the other side of the finger. The second pattern, the loop pattern is the one in which a
line enters and exits from the same side of the finger and makes a sideways tilting ridge in the
middle. All these three features are the ones that can also be seen by a naked eye. But the real
identification takes place when the minute features are studied and differentiated. This is
done through computer technology. There are three major kinds of minutia features: the short
ridge or dot, bifurcation, and ridge end. Now, these three features determine the difference
between the various fingerprints. The short ridge or dots are the ridges, which are the small
ones in the middle of the long ones. It can be as small as a dot or just a smaller line or ridge in
the pattern. The bifurcations are the ones in which one ridge is split into two ridges from a
point. Last but not least, the ridge ending is a point where a ridge is not going further or has
stopped growing. Nobody’s fingerprints are ever the same even if they are genetically related.
This thing has nothing to do with genetics because every person has their own set of
fingerprints (Byeong, Heo, Ji, Bien, & Park, 2018).
In order to get the image of the fingerprint, there are a number of ways to go through.
There are various methods to do this, including capacitance, which further has two forms;
active capacitance and passive capacitance, and then there are ultrasonic sensors, and lastly
there are optical sensors. All these methods have different ways of taking the image and
14

putting it into the database. Capacitance sensors basically work under the same principles as
that of capacitance; which is to store electric energy and use it further, to form an image.
There is an arrangement of sensor pixels which make up a parallel plate capacitor and a
dermal layer, which has an electric charge, performs the duties of the other plate and the last
epidermal layer acts as a dielectric as it is non-conductive. Now, the first type that uses this
method is passive capacitance (Byeong et al., 2018). The fingerprint pattern in the dermal
layer of the skin is formed by using this principle. The spaces between the ridges create an air
gap between them, hence, changing the volume of the between the sensor element and the
dermal layer of the skin. This changes the capacitance of these ridges and valleys that are in
our fingerprints. The known values are the dielectric constant and the area of sensing
elements which is found in the epidermis. Now, these measured values are used to
differentiate between different fingerprints (Jo, Jeon, Im, & Lee, 2016).
The second method that uses capacitance theory is active capacitance. In this method,
the first thing which is done is that voltage is applied to the skin via a charging cycle before
the measurements. This is done to charge the capacitor. Now the electric field that is built
between them and the sensor follows the path of the lines on the dermal layer of the skin. The
capacitance is then calculated by comparing the voltage in the dermal layer and the sensor
against the reference voltage. The image is then formed after calculating the distance between
these ridges (Jo et al., 2016).
Ultrasonic is the as that of medical ultrasounds. This makes use of high-frequency
sound waves to create an image of the fingerprint pattern. These high-frequency sound
waves can easily enter through the layer of the skin. The piezoelectric transducers are used to
produce these high-frequency sound waves, and the materials that collect the reflected sound
waves are also piezoelectric materials. The dermal layer of the skin has the same pattern as
that of the skin, so it means that the waves that are reflected can be measured and used to
make an image of the fingerprint (Jahan, Chowdhury, & Islam, 2019).
Lastly, there is optical imaging of the fingerprint pattern. It is the simplest method of
making an image. For this method, a fully specialized digital camera is required, which is a
sensor here. This is used to capture the digital image of the fingerprint by using visible light.
The finger is placed on the touch sensor, which has a light emitting phosphors underneath
that take the image (Jahan et al., 2019). Now, this light goes through the arrangements of
solid pixels, which is a charged coupled device and captures the image of the fingerprint.
This image is the visual one. There are a couple of disadvantages to this method as well. If
the finger is dirty or is damaged in any way, the picture was taken would be blurry and bad.
The quality of the skin really matters in this regard. Sometimes people can also use this to
manipulate law enforcement by damaging the part of the skin with fingerprint patterns. If the
touch sensor is also scratchy, it can also destroy the visual image formed. It can also work if
only the image of the print is showed in the sensor screen, and people can be fooled by this
(Rockwell, 2017).
15

2.3.2. False Acceptance Rate (FAR)
False Accept Rate also is known as Type II error or False Match Rate. It is the degree
of probability that the biometric system will incorrectly accept the input pattern of the
unauthorized persons to the non-matching template, thus, being identified by the system.
Figure 3: False Accept Rate (Source: (Muhtahir, Adeyinka, & Kayode, 2013).
The automated fingerprint identification system is mostly used by law enforcement
agencies. In order to check the fingerprints and compare them in the database, the fingerprint
of the suspect needs to be collected. This process of collection is mostly carried out by
investigators to solve a crime. There are different types of fingerprints that are left on the
crime scenes. Some of them can be seen by the naked eye others cannot. There are three
types of prints found by investigators at a crime scene; patent prints, plastic fingerprints, and
latent fingerprints (Muhtahir et al., 2013).
The first one is patent print. It is the simplest one. Patent prints are visible to the
naked eye and come about when there is some substance attached to the skin of the finger,
and that finger touches any other object with a smooth surface. When collecting patent prints,
the investigator should photograph the print, including the scale reference, and then transport
the object on which the print was found to the lab, where the print can easily be studied in a
controlled environment. When the finger touches that surface, an impression is left there,
which is exactly the copy of the fingerprint of that person. No technological equipment is
required to see that impression (Hern, 2018). This is a typical example of a crime scene
investigation. The marks that are left on the other object are due to the fact that dust particles
get attached to the fingers and hence, ridges are formed that in return, give fingerprint
impressions that are easily identifiable.
The second type is the plastic print, which is also visible to the naked eye. These
kinds of prints occur when a finger is touched to a soft surface, and a print is left there. The
surfaces that are mostly covered in these kinds of fingerprints are usually freshly painted.
16

Some of them also can be the ones which are made of wax or gums. Any substance which
when touched by hand or fingers is softened can carry this kind of fingerprints. These are
easily detectable by the naked eye because the ridges are very much visible, so in order to see
them, we do not need to magnify them (Chan, Kuo, Cheng, & Chen, 2018).
Thirdly there are latent prints which are usually invisible and cannot be seen by a
naked eye. Perspiration or sweat is one of the main reasons for this kind of fingerprints, and
this sweat comes from the sweat pores in the fingers. This can also occur when the oil,
grease, and moisture in the body get attached to the fingers when fingers touch them; and
when those fingers touch some other object the moisture on the ridges will leave a print on
that substance. This print has to be magnified in order for it to be visible to the naked eye.
This type of fingerprinting is very useful and important as well in the field of law
enforcement (Chan et al., 2018).
The fingerprint identification system is also known as dactyloscopy. In this process,
the fingerprints in question are compared to the ones already present in the database. The part
that is compared is the ridges, also called dermal skin. These ridges are different for every
person, which is why it is very easy to identify. These prints are not only taken from the
fingers but also from palms and toes. These ridges are also called friction ridges because they
create patterns of ridges which are easily detectable. The prints on two fingers or even palm
are not the same, and this is called the flexibility of friction ridge (Blanco, Lunerti, Sanchez,
& Guest, 2018).
2.3.3. Equal Error Rate
Cross Error Rate, also known as the Equal Error Rate (EER), is the point at which the
False Reject Rate and the False Accept Rate are equal. When the identifying device gets to be
more sensitive and accurate, the false accept rate (FAR) goes down, and the false reject rate
(FRR) goes up, hence, the intersection point.
Figure 4: Graph showing the relationship between errors (CER, FRR, and FAR) (Source:
Yildiz et al., 2016).
17

There was a time when digital technology was not introduced, and instead of using a
different kind of sensors to take the fingerprint, ink card was used. So as to do this, all the
fingers of the person were first thoroughly cleaned by the help of alcohol as to remove any
sweat or dust from the finger and then the fingers were dipped in the ink until the fingertip
area was fully covered with ink. After this, the fingers were rolled on the papers from one
side to another (Blanco et al., 2018).
There are two main principles upon which fingerprint identification works: first that
these patterns on the fingers do not alter throughout life, and second is that nobody has the
same friction ridges on their fingers. Friction ridges become visible because of the sweat
pores and other body oils that are secreted from the body (Yildiz et al., 2016). To make these
prints visible experts use chemicals and powders, but still, the visibility is very much
depended upon the surface from which it is being taken. This is also not a very big problem
because computers have made life much easier, so the prints that are not visible are enhanced
through the help of computers. The computer can help join in the fragments, and the laser
technology can help detect invisible markings. One thing that is not possible to tell is the
exact time when the fingerprint was made. There are many ways to recover fingerprints from
different surfaces. Scientists have invented a lot of different instruments for this purpose, and
through these instruments, fingerprint recovery has become very easy and convenient (Yildiz
et al., 2016).
One of the instruments used is an AccuTrans which resembles a caulking gun. In
order to use this gun put a double cartridge in it then insert a mixing tube in it and press the
trigger. When the trigger is pressed the compound polyvinylsiloxane, which is inside the tube
will come out and mix the two compounds. Now apply this on the area where the fingerprints
are present but make sure that the compound has no bubbles in it and to prevent this stir it
thoroughly. The time in which it dries out depends upon the temperature of the surface and
the air present. It will generate a very good result. While using it makes sure that the tip of
the gun does not touch the fingerprint because if it does the print will be damaged and not
produce a good result. The impressions made in the evidence field have always been very
important, but one thing that was very difficult was to test for prints in awkward places
(Yildiz et al., 2016). The AccuTrans gun helps greatly in this regard because it is a field
instrument and can easily be taken to the place the fingerprint has to be recovered from. It is
very easy to remove from the given surface as well.
18

Figure 5: Biometrics Error Rates (Source: Yildiz et al., 2016).
Another thing used to recover fingerprints is Diff-lift tape. It is used when there is a
fingerprint u can see, but the only problem that arises is that the surface it is on is textured
and it is difficult to lift the print from there. This is where this tape comes handy. It is exactly
like normal tape, very soft. It is put on the surface where fingerprints are present, and the
powdered latent print sticks to this tape. The shape of the texture is filled by the tape, and all
the powdered print is lifted. When the tape sticks to the print gently press it with the index
finger. The tape, when removed, will show the latent fingerprint when putting into a
contrasting background (Storisteanu, Norman, Grigore, & Norman, 2015).
The third type of instrument is an extruder gun. It also a caulking gun like AccuTrans
gun. We need to put a double cartridge in the gun. After this, the special mixing tube is
inserted in it, and the trigger is pressed. The compound polyvinylsiloxane mixes with the
other compound as the mixing tube has veins that mix these two easily. This is then applied
to the place where the fingerprint is present and in order to make sure of that stir the mixture
with the tip. The extruder gun creates very good results. These guns are similar to the
AccuTrans guns, but these guns can also be used on textured and multi-contoured surfaces.
An example of this can be of Styrofoam on which has a shoe impression on it. This
impression can be lifted with the help of an extruder gun and easily compared with any other
shoe in question. The precautions for this gun are also similar to AccuTrans gun; make sure
that the tip does not touch the print in question as it can destroy the evidence for the case
(Storisteanu et al., 2015).
Other than instruments, there are many other techniques to recover the fingerprints as
well. One of them is goo print powder. Similar to the use of cellophane to lift the prints,
cellophane adhesive tapes are used to collect traces of minute particles from areas where
picking from hands is not possible. This is mainly used to develop the fingerprints on the
adhesive side of the tape (Jain & Nandakumar, 2012). This is one of the finest ways of
showing latent fingerprints on the side of the tape. To use this formula a proper kit is required
which has every relevant thing in it. A kit needed for this has to have these things: liquid
mixing bottles, bulb pipettes, mixing jars, mixing spoons, dispersing all-purpose solution
brush, and goo print powder. Proper steps need to be followed. Firstly, a tiny amount of goo
19

powder is put into the mixing jar. An equal amount of water and dispersing solution is used,
and this equal amount can be measured by the help of a bulb pipette. Now, to make a paint-
like think mixture add water and dispersing mixture in the goo powder and mix with the
mixing spoon. The mixture should be mix thoroughly so that it becomes a paint-like paste.
The solution can now be used by the help of an all-purpose brush. Use this brush to paint the
mixture on the adhesive side of the tape. Leave that solution on the tape for about 10 to 15
minutes and after this time wash it under running water. Make sure that the solution does not
stay on the tape for long because it has the tendency to stick to it, and due to this, the result
would be ruined. After the tape is cleaned by the help of water take a photograph of the latent
print visible on the tape (Jain & Nandakumar, 2012).
Another technique that is used is the Gun Blue Latent Development technique. This
helps in producing fingerprints that are on metallic objects like coins, keys, shell casing et
cetera. In most criminal cases what the police officials come across is a gunshot victim, and
what is left behind are cartridge casings. These cartridge casings are one of the very
important case evidence in the whole investigations and fingerprints on these cases can help
solve the case very easily. The casings which are recovered from the crime scene have to be
dipped into gun bluing, which can be either diluted or undiluted (Conti, 2017). This would
cause a chemical reaction to occur between the fingerprint residues and the chemical on the
cartridge casing. After the reaction has occurred, the print is visible to the naked eye.
Aluminum and nickel plated casings do not give as good result as the brass casings. This
reaction should be stopped by the help of water bath as the reaction is quite fast and tend to
overexpose the print if not stopped in time (Jiping, Yaoming, Zenggang, & Shouyin, 2014).
There are steps which need to be followed to apply this method. Firstly, we need to
use instruments that will not cause a reaction with the bluing. These instruments can be
terminal pliers, forceps, or tweezers. Mostly plastic tools should be used or dip metal ones are
also a good option. The casing should be handled by the base, not neck because the acid can
damage the primer. The substance should be dipped quickly and then pulled back up, and all
of this should be examined closely. Watch the reaction closely; it only takes a few seconds.
The observation should be quick because if the casing remains in the solution for too long, it
will turn black. To stop the reaction, the casing needs to be dipped in water. This is the only
way through which the reaction would stop (Jiping et al., 2014).
Mikrosil is yet another method to recover latent prints and tool marks. Mikrosil is
made in order to get a result from small prints; even microscopical observations are made
visible by this method. It uses very little time and has the fine releasing ability as well. This
method is mostly used when the marks are shallow or needs to be magnified in order to be
seen clearly. It is also suitable for extracting latent fingerprints from different surfaces or
objects. The best thing about mikrosil is that it comes in different colors; gray, white, black,
and brown. These colors are used in contrast to the powder that is used (Ju, Seo, Han, Ryou,
& Kwak, 2013). Brown is the color that is mostly used for tool marks. Using this tube is very
easy. Mikrosil is available in the form of a tube that can be squeezed on the card in question.
Amount used should be according to the print card. The mixture should be mixed thoroughly
20

by sticks. After mixing all this apply it on the mark that has the print. Precaution should be
taken while applying that mixture so that the print is not damaged (Ju et al., 2013).
Pathfinder is yet another invention of the new century. It is dust lifting tool which
works on the wireless technology. It actually works with the help of electrostatic energy. The
good and convenient thing about this device is that it is not a conventional machine which has
connecting wires or leads. Instead, it uses a wireless system to operate. It can be easily used
on carpets, tiles, wooden windows and upholstery and other surfaces which have insulating
and conductive properties as well. Safety precautions are also taken when this device is made.
This machine can only work when it is placed near the earth plate or some conducting
material. It is very easy to use, as well. It is simply placed on the print, and the grounding
plate is placed around half an inch away from the lift (Prasad & Aithal, 2018). When the
machine is turned on, it takes only 5 to 10 seconds to suck all the dust after which it is
switched off. If bubbles are formed, it is important to remove them. These bubbles can be
removed by using a paintbrush to flatten them. Now the lifting film is removed, and dust print
can be seen by using the side lighting. An additional thing that is utilized for the purpose of
getting fingerprints is polyethylene tape. This tape is basically used to lift the visible latent
prints from the objects or surfaces. It is thought that dealing out items is the most
uncomplicated work in the entire method (Ju et al., 2013). All the previous techniques were
mainly focusing on how to make the latent prints visible to them, but this method of using
polyethylene tape is used to lift the latent prints already made visible to the eye. For flat and
smooth surfaces, standard tapes are used, but something more sophisticated is required to lift
marks from things that are not soft and are multi-contoured like a light bulb, doorknobs et
cetera. It stretches according to the need and does not spoil or damage the latent fingerprint
on the objects or substances (Ali, Mahale, Yannawar, & Gaikwad, 2016b).
One more device that is used to track dust prints is the stun gun. Tracking criminal by
identifying the footwear track is an essential part of an investigation in order to catch or
connect somebody for criminal activity. It is basically the work of the investigators or the
police officers to look for these prints to collect them to analyze. Whenever the footwear
tracks are visible photos are taken of them so that they can be analyzed afterward in the labs.
These track marks should be lifted by casting materials, lifters or lifting tapes as mentioned
earlier. Identification by photography can lack the element of accuracy, so the doubt always
remains as to whether the result is appropriate enough to use for identification purposes or
not. As mentioned earlier, their devices that help recover dust tracks from crime scenes (Ali
et al., 2016b). These machines are mostly known as electrostatic dust lifting devices as they
use electrostatic technology to operate. These machines can easily detect even small latent
prints in the dust tracks. Usually, these electrostatic dust lifting devices are very expensive,
but one of these devices is very affordable and is easy to use; it is also conveniently available
in the market, and the performance level is also excellent. This tool is the stun gun. Firstly, a
photograph is needed, and then the lift should be made. The metallic side of the film is placed
in the up direction over the duct mark. The outer contacts of the stun gun are then attached
with clips for attachment purposes. One thing that is very important to note is that the inner
contacts are not used. This stun gun is very easy to use, but a certain procedure should be
21

followed before using it. The placement of the gun from the dust track and the distance
should be accurately measured (Ali et al., 2016b).
The wet print is another form of extracting fingerprints, but this is specifically used in
the case where there are wet surfaces. It is essentially more like a liquid fingerprint powder.
The method of using it is to spray it on a non-porous surface which has evidence on it. The
particles get attached to the latent print residue. The particles in question are very small
microfine particles. After helping this attachment of particles to the latent print, the excess
solution is easily removed from the surface as it runs off. When these prints are dried, they
are lifted by the help of lifting tape (Ali et al., 2016b).
2.3.4. Zero FMR
Uni-modal biometric technology-based systems carry out person identification
foundational on a single source of biometric or available information. Similar technology-
based systems are frequently influenced through some of the major issues, outlined below:
Noisy sensor data is one of the major reason that leads to higher issues in case of
facial detection. In this case, noise can be there in the obtained biometric data primarily
because of faulty or indecently handled detection sensors. For instance, the buildup of dirt or
the residual remains on a fingerprint sensor is able to present some of the noisy finger-print
images. Malfunction to spotlight the camera suitably is able to lead to blurring in iris or face
images (Yoon & Jain, 2015). The detection precision of a biometric technology-based system
that is extremely sensitive to the quality of the biometric input as well as noisy data is able to
outcome in a major decrease in the accurateness of the biometric detection system.
Non-universality is also one of the major issues in the detection system, where each
person in the target population is capable of offering the biometric trait intended for
detection, then the trait is outlined as universal. Universality is one of the fundamental needs
used for a biometric identifier based system. Though, not the entire biometric qualities are in
fact widespread. The NIST or National Institute of Standards and Technology has outlined
that it is not feasible to get a high-quality quality finger-print from about 2% of the populace.
Therefore, similar people are not able to be registered in a finger-print authentication
arrangement (Zhang, Jing, Chen, & Wang, 2013). Likewise, persons encompassing long
eyelashes plus those having some of the kind of eye based irregularity or diseases similar to
aniridia, glaucoma, cataract or nystagmus are not able to offer high-quality iris pictures used
for the automatic human detection system. Non-universality takes to Failure to Capture or
some kind of Failure to Enroll issues in a biometric detection based system (Zhang et al.,
2013).
Lack of individuality is also one of the major issues in detection based systems. For
example, in characteristics taken out as of biometric features of dissimilar people is able to be
quite analogous. For instance, appearance supported facial characteristics that are usually
employed in the majority of the present face recognition based technology of systems are
discovered to have partial bias ability. A little amount of the population is able to encompass
almost matching facial emergence because of genetic characteristics (for example, identical
22

twins, father, and son). This lack of distinctiveness augments the FMR or False Match Rate
of a biometric technology based detection system
Figure 6: An example of FMR(t) and FNMR(t) curves (Source: Erlikhman et al., 2013).
2.3.5. Zero FNMR
Lack of invariant representation: The biometric data obtained as of a client all-through
human authentication will not be matching to the data employed intended for producing the
client’s template al through the enrollment. This is recognized as “intraclass dissimilarity.
The differences can be because of inappropriate communication of the client by the sensor
(for example transformations because of translation, rotation as well as implemented pressure
when the client places his finger on a fingerprint sensor, transformations in pose as well as
appearance when the client stands in front of a camera), utilize of dissimilar sensors all
through the employment as well as authentication, transformations in the ambient
environmental circumstances (for example lighting transformation in a face detection system)
as well as intrinsic transformations in the biometric attribute (for example exterior of lines
because of presence of facial hair or aging changes in face images, existence of scars in a
fingerprint, etc.) (Ali, Mahale, Yannawar, & Gaikwad, 2016a).
Preferably, the characteristics taken out as of the biometric data have to be
comparatively invariant to these transformations. Though, in the majority of realistic
biometric technology-based systems, the characteristics are not invariant as well as
consequently complex matching algorithms are necessary to obtain these dissimilarities into
account. Huge intraclass differences typically augment the FNMR or False Non-Match Rate
of a biometric technology-based system (Ali et al., 2016a).
Vulnerability to circumvention is also the main aspects of such a system. Though it is
extremely hard to take someone’s biometric behavior, it is yet probably intended for an
impostor to keep away from a biometric system by means of spoofed behavior. It has been
exposed that it is probable to build gummy fingers by means of raised fingerprint imitations
as well as make use of them to avoid a biometric system. Behavioral qualities similar to the
signature as well as voice are more vulnerable to similar security-based attacks as compared
23

to physiological behavior. Other types of security-based attacks are able to be as well opened
to avoid a biometric system (Ali et al., 2016a).
Figure 7: Relation between FNMR and FMR (Source: Ali et al., 2016a).
Because of these realistic issues, the fault rates connected by uni-modal biometric
technology-based systems are fairly high that formulates them intolerable intended for
application in protection and safety-critical systems. A number of such issues that influence
uni-modal biometric systems are able to be ease through making use of integrated biometric
technology-based systems. Technology-based systems that combine signals attained as of two
or more biometric technology based sources for the reason of person detection are known as
integrated biometric systems. The new technology-based integrated biometric systems have
numerous benefits over uni-modal systems (Erlikhman et al., 2013).
Through the integration of Biometrics and Bio-information can considerably enhance
the general correctness of the biometric detection system. Integrated biometric systems are
able to decrease the FTE/FTC rates as well as offer more opposition beside spoofing for the
reason that it is hard to at the same time spoof numerous biometric detections and checking
sources. Integrated systems are able to offer as well the potential to investigate a huge
database in a well-organized as well as fast style. This is able to be attained through by means
of a comparatively straightforward however less precise modality to prune the database
previous to employing the more composite and precise modality on the continuing data to
carry out the ultimate recognition job (Faridah et al., 2016).
Though integrated biometric systems as well have a number of issues. They are more
costly as well as necessitate more resources intended for computation plus storage as
compared uni-modal biometric technology-based systems. Integrated technology-based
systems normally necessitate more time intended for authentication and enrollment reasoning
several problems to the client. Ultimately, the system accurateness is able to, in fact, degrade
contrast to the uni-modal system if a suitable method is not taken intended for uniting the
confirmation offered through the diverse modalities. Though the benefits of integrated
technology-based systems far balance the limits plus, therefore, similar arrangements are
24

being more and more applied in security-based significant implementations (Faridah et al.,
2016).
2.4 Transforming and integrating your biometrics capability
New technology base biometrics systems are transforming the simplicity of use,
exactness as well as the performance of customary biometrics technology-based solutions. It
is offering more dependable identity authentication in criminal justice and healthcare plus
facilitating in a great deal of efficient ways regarding well-organized immigration plus cross-
border travel. It is incorporating one more layer to police as well as defense security
procedures. This technology is also facilitating to fight against the more and more intelligent
illegal movements in regions, for example, economical services (Faridah et al., 2016). New
integrated biometrics technology is now working and operational in flowing major areas of
corporations:
a) Biometrics technology in business logic is able to define the workflow arrangement of
biometric solutions we require, making sure our implementations are employed as
successfully as possible.
b) Compliance: In this scenario, this technology is able for making sure that we have
technical potentials to broadcast information in line by means of international and
national technology necessities intended for transmitting as well as receiving data.
c) National, plus international policies: Offering workflow as well as data captures
recommendation on utilizing, capture as well as storage of biometric data and
information as of regulations leading human rights, confidentiality, data safety, etc.
d) Architecture: Biometrics technology offers support and leadership on the architectural
design of our technology solutions (Cao & Jain, 2019).
e) Integration: Biometrics technology and related integrating biometrics solutions by
means of our obtainable internal or 3rd party solutions plus handling huge verity of
interfaces by means of other organizations.
f) Operations: Biometrics technology offers support for maintenance as well as support
large plus difficult biometrics support.
2.4.1. Systems integration expertise
Biometrics technology offers power as a worldwide systems integrator is a serious
aspect in supporting to bring biometrics policies to life. Biometrics technology offers a deep
understanding of the difficult associations, interfaces as well as safety controls that facilitate
our clients to handle the real-time stream of biometric information countrywide as well as
across borders. For instance, as crime turns out to be more and more worldwide, we are able
to put together by obtainable technology to offer very fast identification and utilize of the iris,
face as well as other biometrics technology based data registered inside different databases,
comprising those managing criminal records as well as prisoner details (Bhairannawar, Raja,
& Venugopal, 2016). Other instances comprise:
a) EURODAC: it is a biometrics technology-based project. It is used or the border
controls; those are relaxed all through Europe, the job of policing prohibited
movement has developed in tandem. In this scenario, biometrics technology offered
support to ease this pressure. Through biometrics technology, there is the
25

implementation of the EURODAC (European fingerprint database intended for
identifying asylum seekers and irregular cross border travelers) biometry system on a
European scale intended for the European Commission. It practices immigration
system needs plus permits associate nations to ensure if refuge has previously been
sought in another associate country. A particular registration gets a small amount of
time is required for lengthy examinations each time asylum is sought (Bhairannawar
et al., 2016).
b) Norway: There is Biometra project intended for the Norwegian Police that offers a
fundamental communications server by means that numerous internal, as well as
outside applications, interface to provide numerous thousands of clients the ability to
download as well as utilize biometrics technology.
c) Biometrics technology-based project of European Union Visa Information
System (VIS): biometrics technology is primary the group is offering the Schengen
Visa European Database is comprising biometrics data, details, information that is
used for supporting member states to contribute Schengen visas as well as the fight
against visa fraud. By means of the support of Biometrics technology VIS, border
guards are capable of confirming whether the person presenting a visa is its legal
holder of it (Bhairannawar et al., 2016).
d) Belgium: Biometrics technology incorporation expertise was known as through the
Belgian Police intended for whom technology development industry incorporated an
AFIS solution by means of their obtainable systems.
2.4.2. Issues in Integrating Biometrics
Though the applicability of new technology of the biometric systems plus procedures
to huge scale issues has been extensively assessed for previous few years, the real service of
biometrics has been normally restricted to small-scale trial systems, and the small numbers of
large scale efforts have been fewer than overpoweringly flourishing. However yet, the
discussion of huge-scale biometric system persists in developing, immediately as the
biometric business itself.
Apart from fundamental problems of cost-per-checkpoint as well as Type-1/Type-2
performance, numerous difficult and consistent issues are concerned in the variety and
flourishing accomplishment of biometrics systems. Though these “Integration Problems” are
able to be recapitulated in an extremely a small number of constituents of concerns, the
problems themselves are able to simply be evaluated plus tackled by means of respect to the
explicit, comprehensive needs of a specific application (Ezhilmaran & Adhiyaman, 2017).
Biometric Integration Issues comes up since; normally, there is no totally “off-the-
shelf” explanation that a biometric potential will suit the entire areas of a particular system.
The procedure of integrating the biometric into a complete systems solution necessitates the
accomplishment of interfaces plus applications systems, as well as the incorporation of
together custom as well as commercial mechanisms into an exclusive application, that is
custom customized to convince the entire of the operational, functional and technical needs of
the system. When a biometric technology-based system has been chosen for a specific
application, a systematic evaluation of the biometric-based technology system and products
26

have to be formulated as explained in the previous sections, by means of respect to the
comprehensive necessities of the system. This procedure will recognize the needs intended
for custom system and structure development and incorporation. The integration of biometric
technology issues, then, is an evaluation of how to carry out the development plus
incorporation of custom abilities as well as to put together the application through the
arrangement of the obtainable system (AlShehri, Hussain, AboAlSamh, & AlZuair, 2018).
2.4.3. Integrated Biometric Technology Development
This section will present a deep and detailed analysis of some of the major areas and aspects
of the integrated biometric system development. Below are some of the major areas and
aspects of such system development major development structures.
2.4.3.1. Device Capabilities
a) API
b) Computer System Interfacing Capabilities
c) Built-in Applications
2.4.3.2. Development Issues
Below is an outline of some of the major issues and aspects regarding the development of the
integration of biometric technology:
a) Development of biometric technology systems and Tools
b) Source Code accessibility of the biometric technology
c) Technical OEM/Integrator-Level Documentation
2.4.3.3. Support Issues
Below is an outline of some of the major issues and aspects regarding support of the
integration of biometric technology:
a) Manufacturer Technical Support for biometric technology development and
application
b) Manufacturer Maintenance Support for biometric technology development and
application
c) Third Party Support for biometric technology development and application
2.4.4. Cost issues in Fingerprinting
Just like in all other information technology investments, there has to be a cost-benefit
analysis and assessment. As such, there would be a need for the development of a business
case that would identify organizational needs. This should aid in the formulation of system
goals that should address the expected outcomes of the system, including binding biometric
features to an appropriate identity or identifying undesirable individuals in the watch list.
Performance parameters should also be specified. This process enables the estimation of the
expected cost, both the initial and recurring. Initial costs include designing, developing and
testing, implementing the system; personnel training; the cost of hardware and software;
improvement of network infrastructure; and enrollment cost (AlShehri et al., 2018). On the
27

other hand, recurring costs include software and hardware maintenance, program
management costs, token cards issuance, and personnel training. Against these costs, the
benefits that accrue would be weighed
Despite allegations of computer power dropping the cost of acquiring fingerprint
biometric devices by Rockwell (2017), Hern (2018) notes the persistent substantial cost of
acquiring biometric systems and its recurring costs. The authors of the 9/11 Commission
recommendations give an example of the budget for US-VISIT during the 2004 financial year
that cost $328 million. Incorporating biometric technology into visas cost between $700
million and $ 1.5 billion annually as at 2002 depending on the type of technology and number
of applicants. The same would cost between $ 1.6 and 2.4 billion annually if implemented on
US passports. These costs are less fielding and planning costs. Research by Blanco et al.
(2018) also indicates the unavailability of fingerprint biometrics systems with the cost of
maintenance being too high. The hardware costs in the technology used in fingerprint
biometric technology could be several US dollars per match per second, according to
Rockwell (2017). There also arises the practical challenge of record keeping. More so,
operational costs for not only fingerprint biometrics systems but all the other biometric
systems, have proved to be high. Errors made during latent fingerprint identification have
also seen governments incur not an only monetary cost but also a cost on image and inability
to identify respective criminals. Still, so much of the budget goes into research and
development, not only to acquire more effective biometric technologies but to also
significantly reduce the associated costs.
Researchers in information technology and criminology have devised different
technologies that would be important in reducing the cost of fingerprint biometric
technologies. Rockwell (2017) proposed the replacement of the fingerprint biometrics
dedicated sensors with general purpose cameras found in cellular phones and laptops among
other devices. Unfortunately, images generated by such devices do not meet the quality of the
dedicated fingerprint sensors. As such, there would need to process the images obtained from
these devices to make them as much as possible similar to those obtained from fingerprint
dedicated sensors. Even with this innovation still under test, fingerprint biometric remains the
least costly method of biometrics identity and verification as compared to more sophisticated
technologies such as iris biometrics systems (Conti, 2017).
3. Proposed Method and Future Work
We can improve the results of the fingerprint methods that have been discussed in this
research paper by doing the following:
a) Enhancing the fingerprint image by completing the ridges
b) The methods of fingerprint discussed should be able to consider the average gauge
thickness
c) Also more robust algorithm 4minute imagine should be developed
d) It would also be a great improvement if the methods identified and discussed above
can be able to remove false many time and noise
28

e) This research paper has concluded that fingerprinting methods cannot be able to attain
100% accuracy level. In regard, integration of fingerprint methods into other
biometric technologies would increase the accuracy and enhance the results of using
these fingerprint methods.
In spite of some few cases of inaccurate information, today, fingerprint biometric
technology has become a critical solution in tackling security challenges in government
agencies and private corporations. But even before implementation, well-informed decisions
should be made on the technology to use, and detailed cost-benefit analysis and assessment
conducted so as to ensure that the gains from such systems outweigh the incurred costs.
Those who remain skeptical about fingerprint biometrics technology for reasons like
performance, accuracy, and reliability should combine these security systems with other
available security measures such as smart cards. Fingerprint biometric technology would not
solely provide accurate information needed. Otherwise, innovation in this field is expected to
continue, and humans would always seek to come up with better foolproof techniques and
tools in fingerprint biometrics.
4. Conclusions
Though biometrics technology is turning out to be an essential fraction of the identity
management systems, present biometric technology-based systems do not have 100 percent
accuracy. A number of the aspects that influence the precision of biometric systems comprise
non-universality, noisy input, non-distinctiveness, and lack of invariant illustration.
Additional, biometric technology-based systems are as well vulnerable to security-based
attacks. A biometric technology-based system that incorporates numerous cues is able to beat
several of these boundaries and attain improved performance. Widespread research work has
been performed to recognize enhanced techniques to unite the information attained from
numerous sources. It is hard to carry out information incorporation at the beginning phases of
processing (feature and sensor levels). In several situations, a combination at the sensor as
well as feature levels cannot even be probable. Biometric technology Integration at the
decision level is too naive because of the partial information content accessible at this level.
Consequently, researchers have normally desired incorporation at the matching score level
that presents the most excellent compromise flanked by information content as well as
simplicity in integration.
One of the major issues in the score level integration of bio-metric is that the identical
scores generated through diverse biometric matches are not for all time analogous. These
scores are able to have diverse qualities as well as several normalization methods is essential
to formulate the arrangement of scores significant. One more limitation of the present
integration of bio-metric methods is their failure to manage soft biometric data and
information, particularly when the soft information is not extremely accurate. Despite the
drawbacks in using fingerprint biometrics for identification and verification, including its
high cost of acquisition and maintenance, its use keeps rising because of innovative
applications in place that seek to maintain high degrees of accuracy.
29

5. References
Akinyele, A. O., Sarumi, A. J., Abdulsamad, B., & Green, O. O. (2018). Fingerprint
Verification System Using Combined Minutiae and Cross Correlation Based Matching.
American Journal of Electrical and Computer Engineering, 2(2), 16.
https://doi.org/10.11648/j.ajece.20180202.12
Ali, M., Mahale, V., Yannawar, P., & Gaikwad, A. (2016a, February 1). Fingerprint
Recognition for Person Identification and Verification Based on Minutiae Matching. 332–
339. https://doi.org/10.1109/IACC.2016.69
Ali, M., Mahale, V., Yannawar, P., & Gaikwad, A. (2016b, March 3). Overview of
Fingerprint Recognition System. https://doi.org/10.1109/ICEEOT.2016.7754902
AlShehri, H., Hussain, M., AboAlSamh, H., & AlZuair, M. (2018). A Large-Scale Study of
Fingerprint Matching Systems for Sensor Interoperability Problem. Sensors (Basel,
Switzerland), 18(4). https://doi.org/10.3390/s18041008
Bahaa, A. M. (2013a). A medium resolution fingerprint matching system. Ain Shams
Engineering Journal, 4(3), 393–408. https://doi.org/10.1016/j.asej.2012.10.001
Bahaa, A. M. (2013b). A medium resolution fingerprint matching system. Ain Shams
Engineering Journal, 4. https://doi.org/10.1016/j.asej.2012.10.001
Bailey, M. (2018, April 27). The Hidden Data in Your Fingerprints. Retrieved May 27, 2019,
from Scientific American website: https://www.scientificamerican.com/article/the-hidden-
data-in-your-fingerprints/
Bhairannawar, S. S., Raja, K. B., & Venugopal, K. R. (2016). An Efficient Reconfigurable
Architecture for Fingerprint Recognition. VLSI Design, 2016, 1–22.
https://doi.org/10.1155/2016/9532762
Blanco, R., Lunerti, C., Sanchez, R., & Guest, R. M. (2018). Biometrics: Accessibility
challenge or opportunity? PLOS ONE, 13(3), e0194111.
https://doi.org/10.1371/journal.pone.0194111
Bose, P. K., & Kabir, M. J. (2017). Fingerprint: A Unique and Reliable Method for
Identification. Journal of Enam Medical College, 7(1), 29–34.
https://doi.org/10.3329/jemc.v7i1.30748
Byeong, W., Heo, S., Ji, S., Bien, F., & Park, J.-U. (2018). Transparent and flexible
fingerprint sensor array with multiplexed detection of tactile pressure and skin temperature.
Nature Communications, 9(1), 2458. https://doi.org/10.1038/s41467-018-04906-1
Cao, K., & Jain, A. K. (2019). Automated Latent Fingerprint Recognition. IEEE
Transactions on Pattern Analysis and Machine Intelligence, 41(4), 788–800.
https://doi.org/10.1109/TPAMI.2018.2818162
30

Cao, Kai, Yang, X., Chen, X., Tao, X., Zang, Y., Liang, J., & Tian, J. (2012). Minutia
handedness: A novel global feature for minutiae-based fingerprint matching. Pattern
Recognition Letters, 33(10), 1411–1421. https://doi.org/10.1016/j.patrec.2012.03.007
Champod, C. (2015). Fingerprint identification: advances since the 2009 National Research
Council report. Philosophical Transactions of the Royal Society B: Biological Sciences,
370(1674), 20140259. https://doi.org/10.1098/rstb.2014.0259
Chan, H.-L., Kuo, P.-C., Cheng, C.-Y., & Chen, Y.-S. (2018). Challenges and Future
Perspectives on Electroencephalogram-Based Biometrics in Person Recognition. Frontiers in
Neuroinformatics, 12, 66. https://doi.org/10.3389/fninf.2018.00066
Chaudhari, A. S., & Patil, S. (2014). Implementation of Minutiae Based Fingerprint
Identification System using Crossing Number Concept. International Journal of Computer
Trends and Technology, 8(4), 178–183. https://doi.org/10.14445/22312803/IJCTT-V8P133
Chen, T.-P. (2019, March 27). Workers Push Back as Companies Gather Fingerprints and
Retina Scans. Wall Street Journal. Retrieved from https://www.wsj.com/articles/workers-
push-back-as-companies-gather-fingerprints-and-retina-scans-11553698332
Conti, V. (2017). Biometric Authentication Overview: a Fingerprint Recognition Sensor
Description. International Journal of Biosensors & Bioelectronics, 2(1).
https://doi.org/10.15406/ijbsbe.2017.02.00011
Erlikhman, G., Ghose, T., Garrigan, P., Mnookin, J., Dror, I., Charleton, D., & Kellman, P.
(2013). Fingerprint Matching Expertise and its Determinants. Journal of Vision, 13(9), 51–
51. https://doi.org/10.1167/13.9.51
Ezhilmaran, D., & Adhiyaman, M. (2017). A review study on latent fingerprint recognition
techniques. Journal of Information and Optimization Sciences, 38(3–4), 501–516.
https://doi.org/10.1080/02522667.2016.1224468
Faridah, Y., Nasir, H., Kushsairy, A. K., Safie, S. I., Khan, S., & Gunawan, T. S. (2016).
Fingerprint Biometric Systems. Trends in Bioinformatics, 9(2), 52–58.
https://doi.org/10.3923/tb.2016.52.58
Fu, X., & Feng, J. (2015). Minutia Tensor Matrix: A New Strategy for Fingerprint Matching.
PLOS ONE, 10(3), e0118910. https://doi.org/10.1371/journal.pone.0118910
Garrett, B., Mitchell, G., & Scurich, N. (2018). Comparing Categorical and Probabilistic
Fingerprint Evidence. Journal of Forensic Sciences, 63(6), 1712–1717.
https://doi.org/10.1111/1556-4029.13797
Hajare, M. P. (2016). Fingerprint Recognition System. International Journal of Research and
Engineering, 3(11), 18–21.
Hern, A. (2018, November 15). Fake fingerprints can imitate real ones in biometric systems –
research. The Guardian. Retrieved from
https://www.theguardian.com/technology/2018/nov/15/fake-fingerprints-can-imitate-real-
fingerprints-in-biometric-systems-research
31

Hofer, U. (2018). HIV-1’s fingerprint. Nature Reviews Microbiology, 16(11), 658–659.
https://doi.org/10.1038/s41579-018-0086-0
Jahan, S., Chowdhury, M., & Islam, R. (2019). Robust user authentication model for securing
electronic healthcare system using fingerprint biometrics. International Journal of
Computers and Applications, 41(3), 233–242.
https://doi.org/10.1080/1206212X.2018.1437651
Jain, A. K., & Feng, J. (2011). Latent Fingerprint Matching. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 33(1), 88–100. https://doi.org/10.1109/TPAMI.2010.59
Jain, A. K., & Nandakumar, K. (2012). Biometric Authentication: System Security and User
Privacy. Computer, 45(11), 87–92. https://doi.org/10.1109/MC.2012.364
Jiping, L., Yaoming, D., Zenggang, X., & Shouyin, L. (2014). An Improved Biometric-Based
User Authentication Scheme for C/S System. International Journal of Distributed Sensor
Networks, 10(4), 275341. https://doi.org/10.1155/2014/275341
Jo, Y.-H., Jeon, S.-Y., Im, J.-H., & Lee, M.-K. (2016). Security Analysis and Improvement of
Fingerprint Authentication for Smartphones [Research article].
https://doi.org/10.1155/2016/8973828
Ju, S., Seo, H., Han, S., Ryou, J., & Kwak, J. (2013). A Study on User Authentication
Methodology Using Numeric Password and Fingerprint Biometric Information. BioMed
Research International, 2013. https://doi.org/10.1155/2013/427542
Kanchana, S., & Balakrishnan, G. (2015). Palm-Print Pattern Matching Based on Features
Using Rabin-Karp for Person Identification [Research article].
https://doi.org/10.1155/2015/382697
Kellman, P. J., Mnookin, J. L., Erlikhman, G., Garrigan, P., Ghose, T., Mettler, E., … Dror, I.
E. (2014). Forensic Comparison and Matching of Fingerprints: Using Quantitative Image
Measures for Estimating Error Rates through Understanding and Predicting Difficulty.
PLOS ONE, 9(5), e94617. https://doi.org/10.1371/journal.pone.0094617
Kioc, S., Maharjan, N., Adhikari, N., & Shrestha, P. (2018). Qualitative Analysis of Primary
Fingerprint Pattern in Different Blood Group and Gender in Nepalese. Anatomy Research
International, 2018, 1–7. https://doi.org/10.1155/2018/2848974
Konecny, J., Prauzek, M., Kromer, P., & Musilek, P. (2016). Novel Point-to-Point Scan
Matching Algorithm Based on Cross-Correlation [Research article].
https://doi.org/10.1155/2016/6463945
Konecny, J., Prauzek, M., Tran, A., Martinek, R., & Hlavica, J. (2018). Scan Matching
Cross-Correlation-Based Localization Algorithm: Embedded Systems Implementation
Perspective. IFAC-PapersOnLine, 51(6), 90–95. https://doi.org/10.1016/j.ifacol.2018.07.135
Korolov, M. (2019, February 12). What is biometrics? And why collecting biometric data is
risky. Retrieved May 28, 2019, from CSO Online website:
https://www.csoonline.com/article/3339565/what-is-biometrics-and-why-collecting-
biometric-data-is-risky.html
32

Kumar, R. (2018). A Review of Non-Minutiae Based Fingerprint Features. Int. J. Comput.
Vis. Image Process., 8(1), 32–58. https://doi.org/10.4018/IJCVIP.2018010103
Le, H. H., Nguyen, N. H., & Nguyen, T.-T. (2018). Speeding up and enhancing a large-scale
fingerprint identification system on GPU. Journal of Information and Telecommunication,
2(2), 147–162. https://doi.org/10.1080/24751839.2017.1404712
Liu, F., Yang, G., Yin, Y., & Wang, S. (2014). Singular value decomposition based minutiae
matching method for finger vein recognition. Neurocomputing, 145, 75–89.
https://doi.org/10.1016/j.neucom.2014.05.069
Liu, H., Wang, L., Tang, S.-J., & Jezek, K. C. (2012). Robust multi-scale image matching for
deriving ice surface velocity field from sequential satellite images. International Journal of
Remote Sensing, 33(6), 1799–1822. https://doi.org/10.1080/01431161.2011.602128
Liu, W.-C., & Guo, H. (2014). Occluded Fingerprint Recognition Algorithm Based on Multi
Association Features Match. Journal of Multimedia, 9, 910–917.
https://doi.org/10.4304/jmm.9.7.910-917
Luo, X., Lorentzen, R. J., Valestrand, R., & Evensen, G. (2018). Correlation-Based Adaptive
Localization for Ensemble-Based History Matching: Applied To the Norne Field Case Study.
SPE Reservoir Evaluation & Engineering. https://doi.org/10.2118/191305-PA
Muhtahir, O., Adeyinka, A., & Kayode, A. (2013). Fingerprint Biometric Authentication for
Enhancing Staff Attendance System. International Journal of Applied Information Systems,
5(3), 19–24. https://doi.org/10.5120/ijais12-450867
Peralta, D., García, S., Benitez, J. M., & Herrera, F. (2017). Minutiae-based fingerprint
matching decomposition: Methodology for big data frameworks. Information Sciences, 408,
198–212. https://doi.org/10.1016/j.ins.2017.05.001
Prasad, K., & Aithal, P. S. (2018). A Study on Multifactor Authentication Model Using
Fingerprint Hash Code, Password and OTP (SSRN Scholarly Paper No. ID 3097480).
Retrieved from Social Science Research Network website:
https://papers.ssrn.com/abstract=3097480
Probst, D., & Reymond, J.-L. (2018). A probabilistic molecular fingerprint for big data
settings. Journal of Cheminformatics, 10(1), 66. https://doi.org/10.1186/s13321-018-0321-8
Rockwell, M. (2017, January 26). Making fingerprints more reliable biometrics -. Retrieved
May 28, 2019, from GCN website: https://gcn.com/articles/2017/01/26/iarpa-
fingerprints.aspx
Schultz, C. W., Wong, J. X. H., & Yu, H.-Z. (2018). Fabrication of 3D Fingerprint Phantoms
via Unconventional Polycarbonate Molding. Scientific Reports, 8(1), 9613.
https://doi.org/10.1038/s41598-018-27885-1
Shashi, K., Raja, K., Chhotaray, R., & Pattanaik, S. (2011). DWT Based Fingerprint
Recognition using Non Minutiae Features.
33

Storisteanu, D. M. L., Norman, T. L., Grigore, A., & Norman, T. L. (2015). Biometric
Fingerprint System to Enable Rapid and Accurate Identification of Beneficiaries. Global
Health: Science and Practice, 3(1), 135–137. https://doi.org/10.9745/GHSP-D-15-00010
Yang, J. (2011). Non-minutiae based fingerprint descriptor. In J. Yang (Ed.), Biometrics.
https://doi.org/10.5772/21642
Yang, W., Wang, S., Hu, J., Zheng, G., & Valli, C. (2019). Security and Accuracy of
Fingerprint-Based Biometrics: A Review. Symmetry, 11(2), 141.
https://doi.org/10.3390/sym11020141
Yildiz, M., Yanikoğlu, B., Kholmatov, A., Kanak, A., Uludağ, U., & Erdoğan, H. (2016).
Biometric Layering with Fingerprints: Template Security and Privacy Through Multi-
Biometric Template Fusion. The Computer Journal, comjnl;bxw081v1.
https://doi.org/10.1093/comjnl/bxw081
Yoon, S., & Jain, A. K. (2015). Longitudinal study of fingerprint recognition. Proceedings of
the National Academy of Sciences, 112(28), 8555–8560.
Young, B., Byunggeun, K., Seok, K., & Jong, A. (2018). A study on slim optical fingerprint
sensor for fake fingerprint detection on mobile environment. IOP Conference Series:
Materials Science and Engineering, 383, 012016.
https://doi.org/10.1088/1757-899X/383/1/012016
Zaeri, N. (2011). Minutiae-based Fingerprint Extraction and Recognition. In J. Yang (Ed.),
Biometrics. https://doi.org/10.5772/17527
Zhang, J., Jing, X., Chen, N., & Wang, J. (2013). Incomplete fingerprint recognition based on
feature fusion and pattern entropy. The Journal of China Universities of Posts and
Telecommunications, 20(3), 121–128. https://doi.org/10.1016/S1005-8885(13)60060-6
Zhao, F., Huang, Q., Wang, H., & Gao, W. (2010). MOCC: A Fast and Robust Correlation-
Based Method for Interest Point Matching under Large Scale Changes. EURASIP Journal on
Advances in Signal Processing, 2010(1), 410628. https://doi.org/10.1155/2010/410628
Zhao, Q., Zhang, D., Zhang, L., & Luo, N. (2010). High Resolution Partial Fingerprint
Alignment Using Pore-valley Descriptors. Pattern Recogn., 43(3), 1050–1061.
https://doi.org/10.1016/j.patcog.2009.08.004
34