Multi-factor verification

                       The global multi-factor verification market is expected to reach $5.45 billion by 2017, at a CAGR of 17.3% from 2012 to 2017, according to a newly published report.

The report, Multi-Factor Verification Market – By Model/Type, Application and Geography – Forecasts (2012-2107), notes biometric based multi-factor verification models are growing rapidly, contributing significantly to the growth of the overall market. It lists key developments in the verification space, and specially includes Apple’s authentic achievement as well as Morpho’s L1 purchase.

                       According to the report, two-factor verification is the most widely used model, mentioning smartcard with PIN and one-time passwords as the most popular technique. Smartcards gradually more can contain biometric data.

                     The report estimates the multi factor verification market, forecasts the size of MFA technologies by models, by applications, and by geography from 2012 to 2017. It talks about the latest events in the market under winning imperatives and “burning issues.”

The statement is now available in the Research and Markets catalogue. 

                       Research and Markets recently announced the addition of another report dealing with biometrics. Reported previously, the group has now published a report on the Russian biometrics market, which suggests it will reach US$398 million by 2018, owed largely to the forthcoming World Cup and Olympics to be held in the country.

New Biometric System

                             Access and Data Systems has launched its new Standalone Identity Access Management System – the AD102 — which now supports fingerprint biometrics.

                             According to the company, the new two-piece system is not networked and supports up to two entry points with a single reader. Part of the company’s I.AM Series Identity Access Management product line, the biometric access control application is embedded in the system.

                             “The AD102 Kit is the wonderful solution for inhabited or commercial applications, counting doors, gates, garages, warehouses, gun safes, jewelry cabinets, data rooms, inaccessible sites, and second properties,” Logan Stewart, product manager ADS Americas said. “And, even though the system is intended to contain smaller scale usage, the AD102 Kit can travel to work with an AM524 or AM300 Controller and its door unit, creating a full featured web-based system.”

                             Reported beforehand, the Swiss security firm behind Access and Data Systems launched a new division last year to combine sales and hold up operations throughout the Americas.

                           Last month, launched both the I.AM and AX.S access organize series. 

                         According to a recently available report on the electronic access control market – in which is a player — by 2017, the total market will reach $16.3 billion, at a 7% CAGR. Biometric technologies are a major supplier to this growth.

Heartbeat Biometrics

                                     Apple has filed a pair of motivating patent applications with the US patent and brand name office, in which detail possible future implementations of unreleased features which may appear in some of company’s future products.

The first patent permitted “Seamlessly Embedded Heart Rate Monitor” covers Heartbeat Biometrics, and directly relates to the actual biometric identification of users.

To determine the user’s heart rate, heartbeat, or other cardiac signals, the electronic device can include one or more sensors embedded in the device. The one or more sensors can include leads for receiving electrical signals from the user’s heart. . . . To provide an electrical signal from the user to the processing circuitry, the leads can be exposed such that the user may directly contact the leads, or may instead or in addition be coupled to an electrically conductive portion of the device enclosure (e.g., a metallic bezel or housing forming the exterior of the device).

The second patent filed entitled “Multidimensional Widgets” covers the company’s research into offering Mac OSX Dashboard widgets with multiple sides, allowing for the on-screen exploitation of these objects. The patent also references a “widget receptacle”, where multiple 3D widgets could be grouped together based on certain criteria.

For example, a three-dimensional widget with four or fewer functions can be of the form of a tetrahedron; a three-dimensional widget with five or six functions can be of the form of a hexahedron; a three-dimensional widget with seven or eight functions can be of the form of a octahedron; and a three-dimensional widget with nine functions can be of the form of a dodecahedron. Thus, if a user specifies ten stock tickers for quotes and technical’s, the widget 420 can expand from a hexahedron to a dodecahedron.

Two motivating patents I’m sure you’ll agree, and while in the past some of Apple’s patents have come to fruition in products we know and love today, the filing of these patents doesn’t necessarily mean we will see the technology or its accomplishment seen here, anytime soon.

That said, these patents are attractive as they show both the research going on over at and the potential future roadmap of Apple.

Biometrics Next-Gen i-Phone

                            By far the biggest story this revolves around claims that iOS 7 (Beta 4)– seeded to developers just last night – may in fact contain references to a ‘Biometrics UIKit,’ which could (in turn) suggest that Apple may introduce biometrics into the next description of its iPhone.

Biometrics (or biometric verification) refers to the classification of humans by their distinctiveness or traits. Biometrics is used in computer science as a form of classification and access control. It is also used to identify individuals in groups that are under examination.

First noted by Twitter user @hamzasood, Soon claims that the result could translate into the next iPhone‘s home button “[containing a] fingerprint sensor.” In order for that to come about, Apple would have to replace its physical home button with a “capacitive” touch area.

Capacitive sensing technology has been around for a while, and we’ve talked about it many times before in relation to the different patents which have surfaced, and additional seem to corroborate that Apple may be looking to go down this path with its mobile devices. The method, (based on capacitive coupling), takes human body capacitance as input. Capacitive sensors perceive anything that is conductive or has a dielectric special from that of air.

According to Mac Rumors (via 9to5Mac), the bundle features a number of files which may relate to future biometric-based actions in iOS, that could include:

- [Taking a] photo of a person holding an iPhone with their left hand while touching the Home button with their thumb
- [Taking a] photo of a person holding an iPhone with their right hand while touching the Home button with their thumb
- A fingerprint that changes colour during the setup development.

… And a success command, which reads: “Recognition is %@ complete.”

News that the latest iteration of Apple’s in-development mobile OS may contain references to a biometric-based security system follows on from Apple reportedly acquiring security firm Authentic, last year. Just last week, a report also surfaced which claimed Apple’s rival Samsung was forced to drop a similar feature in the development stages of its latest flagship handset, due to what the report refers to as an “unstable” supply of ‘fingerprint’ sensors available to the company at the time.

As for expected uses of this technology if these latest findings are accurate? – Well, Apple could essentially get rid of the need for you to input your Apple ID username and password, every time you wish to download an app, instead having iOS ask for your thumbprint to complete account “authentication.”

reliant on how advanced and “ready-to-go” the technology is possibly going to be at launch, we could also see this biometrics input system expand to online authentication, and perhaps even to developers with the availability of an SDK (Software Development Kit). In this instance, the possibilities of fingerprint authentication on the iPhone are pretty much endless.

Heck, Apple may even be planning to launch its own micro-payments system, with the iPhone acting as your digital wallet (attached to your iTunes account), and your ‘thumb’ acting as the tool for personal verification. We’re not saying that type of system wouldn’t come without user concerns, but the new findings certainly appear motivating.

Apple is currently expected to launch the next-generation iPhone at one of its special media events, set to be held towards the end of this year. The handset is reported to be both thinner and lighter than the iPhone 5 — might carry the name“iPhone 5C” (for branding purposes) — and may be set to arrive in a variety of colours.

The device is also expected to arrive with a slightly-bumped internal processor, and enhanced graphics architecture, to facilitate the running of more graphically-intensive content and games.

Adoption of Biometric Technology

                                    The continuing focus by businesses on safekeeping and the incorporation of systems to better protect possessions is driving adoption of biometric technology across the African and Southern African market.

Qualified professionals in this high-growth marketplace suggest as the demand for Human Capital Management (HCM) solutions increase (fueled by the cost saving element and the replacement of older card-based installations), so too will the opportunities to make volume for service providers – along with the heaviness to perform.

Guenter Nerlich, Founder and Managing Director, AWM360 Data Systems, says there is great possible for companies and corporations to save on payroll and other HCM-related costs.

“When we speak of credible biometric solutions, we immediately identify factors such as automation, accuracy, speed and meeting. These are elements that will improve HCM and workforce management in business. Cost-saving is connected with this technology because of the lessening in pressure on resources, a more streamlined, and efficient and more industrious way of managing resources. There is opportunity, but service providers will have to know what they are doing,” he says.

AWM360 Data Systems was started in 2010 and is an well-known business technology partner and solution provider within the Southern African HCM and Workforce Management Solutions markets.

The company is focused on budding and established businesses that require service and support in order to leverage off pioneering and state-of-the-art Access-, Workforce Management- and Enterprise Data Collection solutions.

Guenter and his team compete at the forefront of biometric solution expansion and accomplishment, particularly that which effects Time & Attendance and Access Control.

Numerous providers have acknowledged the challenge to provide hardware and software solutions to these markets and there is a great range of products being introduced in order to secure a portion of the market and capitalize on growth.

“There are a variety of biometric-based solutions obtainable, which cover the entire spectrum of the market – from lower-end, security-minded to the full security-conscious user or company. Most successful and sustainable solutions are of higher quality and allow for deeper integration into obtainable ERP solutions,” he adds.

AWM360 Data Systems is a provider of such solutions and has implemented successfully in the retail industry as well as in mining.

Skeletons into Biometric Signatures

                           Gesture control is the new mouse, but Extreme Reality co-founder and CTO Door Given believe the underlying technology for tracking body motion could be a boon for security applications. The company, based in Herzelia, Israel, has patented software technology for enabling full-body, 3D motion control on any device via a standard 2D camera.

Unlike Microsoft's popular Kinect gesture controller, which requires a special camera and sensor, or Point Grab’s hand-gesture recognition software, Extreme Reality's Motion software recognizes and tracks the three dimensions of a user's skeletal joints and then converts the joint movement into a unremitting dynamic motion.

Some PC manufacturers, such as Samsung and NEC, are including Extreme Motion on some of their PCs, and video game developers are incorporating the technology into PC in addition to tablet games. Side-Kick Games' Top Smash Tennis, for example, uses Extreme Motion to let players use full-body motion to hit virtual tennis balls. Leading console makers Sony and Nintendo may adopt the technology, Givon said.

The company is now taking its Extreme Motion technology into the security field. "We are working with skeletal information in a way that enables differentiation between people," he said. "We can analyze skeletal data and generate a unique biometric signature, so it could recognize an individual when they want to log in to a device or enter a secured perimeter. It's the first technology that allows full-body 3D motion capture to recognize an individual's gait as a biometric signature."

Extreme Reality's software overlays a 3D engine on a 2D skeleton, creating a single highly accurate image, Givon said. It mathematically eliminates "noise," such as positions that are physically out of bounds for the range of human motion and joints. Unlike wireless infrared-based controllers, Extreme Reality's software technology can work in direct sunlight as well as low light conditions, Givon said.

Givon contends that gait analysis can provide much greater accuracy than face recognition. "Face-recognition technology is very imperfect. You have to be in a similar position every time for analysis. If someone wants to avoid face recognition they can just put on sunglasses or a beard. The way people walk is hard to change," he said.

He cautioned that the technology is not a standalone or bulletproof solution, and he expects that his company's technology will become available in third-party security products next year. "It's an additional set of alarms, not a replacement for the human eye detecting suspicious behavior in a crowd," Givon said. "It's accurate enough to be deployed as part of a holistic solution."

Tremendous Reality's technology could also be applied to augmented reality experiences and wearable devices. "We can change the environment from the moment you wake up in morning," Givon said. "The room knows it's you and can enhance the environment with augmented reality elements that let you control them with your body in the most natural way. It could be integrated with fitness apps and simulators for activities like golf. This can be deployed in every moment in our life."

NEURAL-NETWORKS IN MULTI-MODAL BIOMETRICS

Dimensionality lessening methods convert the data in the high-dimensional space to a space of fewer magnitude. The data transformation may be linear, as in principal components analysis, or non-linear. Many biometric spaces, such as facial biometrics, comprised of a large number of facial appearance which causes difficulties in scholarship and recognition process.

One of the main linear techniques for dimensionality reduction is a Principal Components Analysis (PCA), which performs a linear mapping of the data to a lower dimensional space in such a way, that the individuality of the data in that low-dimensional space is maximized. However, the resulting dimensions might not be always efficient for biometric applications according to ambiguous subspaces problem. In this section, a survey on dimensionality reduction and methods of choosing proper feature subspaces has been provided. The argument to the use subspace-clustering dimensionality reduction is made based on wide-ranging survey.

To validate the network and dimensionality lessening method, we have to explain to overall model of multi-biometric structure. A multi biometric system uses multiple sensors for data acquisition. This allows capturing multiple samples of a single biometric trait (called multi-sample biometrics) and/or samples of multiple biometric traits (called multi source or multi-modal biometrics). This also allows the system to enroll and validate a user who does not acquire a specific biometric identifier.

One of the main problems faced by biometric community is the biometric system dependability and performance. Thus, the first goal is to find the principal mechanism of the distribution of biometric features, or the eigenvectors of the covariance matrix of the set of biometric images. These eigenvectors can be thought of as a set of features which together characterize the difference between biometric samples. As the primary biometric samples, we select fingerprints and face images, since they provide important unpredictability in quality and a large quantity of multi-dimensional vectors.

The suggested methodology was successfully tested on fingerprint matching problem. The minutia extraction method which consists of estimation of orientation field, ridge detection, and minutia detection was applied, with geometrical aspects of the new method and the Hopfield Neural Network which is used for identification process.

We now provide the experimental results to showcase advantages of chaotic neural network for fingerprint recognition in both accuracy and circumvention (resistance to errors). The test database contains both high and very low quality fingerprint images, thus if high level of accuracy is confirmed on those samples, the system possesses both precision and circumvention. The first task was to find the minutiae set based on the algorithm given in previous section. A binarized version of the input image is created next. The finding process is done based in the ridge with one pixel width, so the in the next process the thinning filter will be performed on the image.

BIOMETRICS NEURAL NETWORKS METHODOLOGY

We demoralized notion of multi-modal biometrics, particularly ranked-level combination approach to design of extremely dependable and accurate biometric system. We also looked at compensation which can be gained by utilizing supplementary information about a subject, such as height, age and gender, or so-called soft biometric patterns. We also looked at the new research domain combining behavioral and appearance-based individuality one example of artificial entities, such as robots, avatars and intellectual software agents.

In this section, we look at learning approach and try to bring benefits of utilizing and identifying most prominent/significant patterns in multitude of biometric data, which not essential originates from the same biometric. Features from different biometric sources can be combined at either before-matching or after-matching stages and then most significant traits can be recognized through dimensional decrease or adaptive knowledge approaches.

To further understand the main benefits of this idea, it is important to understand the general architecture of the neural network based biometric recognition system. An illustration of the proposed multi-modal biometric system can be viewed in presents a flowchart for creating templates for training biometric system data set  For each of system N users, their individual biometrics are being collected and then represented as a reduced-dimensional feature vector set. This feature vector set will be then given as an input to neural network based on chaotic associative memory to learn common patterns for subsequent user recognition.

Artificial neural networks are computational models, where dispensation is performed by solid processing units. They were popularized in the works by Hop field (1990) and Choi and Hubernam (1983). Since then, research and applications of this paradigm became abundant for linear and nonlinear, static and dynamic systems (Wang & Shi, 2006; Yamada, Aihara, & Kotani, 1993; Yao, Freeman, Burke, & Yang, 1991). The nature of the network allows for a natural parallel computation and makes them an excellent learner as opposite to other traditional methodologies.

Artificial neural networks idea can be associated with the key work of McCulloch and Pitts (McCulloch & Pitts, 1943), which was published in 1943 in Bulletin of Mathematical Biophysics. This work is now considered to be a classical work in cognitive computational sciences domain. In 1987, Lippmann described how variety of applied troubles can be solved with using neural nets.

Chaos Online Dictionary definition is “complete disorder or confusion” or “Behavior so unpredictable as to appear random, owing to great sensitivity to small changes in conditions.” In artificial neural network research, one of the first scientists to take a close look at chaos in biological patterns.

BIOMETRICS AUTHENTICATION

In this section, we first remember techniques for collecting and classifying databases of avatars and bots, described in Gavril ova and Yampolskiy (2012), moving on to suggest a new way to fusion the new images through application of biometric synthesis methods based on arithmetical processing and multi-resolution techniques. We then study the two main types of verification in virtual world: visual and behavioral, and introduce the multi-modal system for improved presentation.

As was pointed out before in this book, there are mainly three dissimilar types of biometric databases: true database, practical database and artificial database. For unimodal biometrics, there is an great quantity of freely available datasets, with vendor competitions often being held and benchmarks on appreciation algorithm presentation being recognized. This is not the case in the area of practical reality. Labeled communal datasets of avatar faces, robot faces, or attributed conversations from unnaturally intelligent agents are presently engaged. Some recent papers attempted to tackle the problem by looking at applying methods for face production.

Cyber security, without a reservation, is one of the key concerns of many modern organizations as well as private citizens worldwide.

There have been a number of attempts by malicious intellectual software to obtain unlawful access to information or system resources. It affects security of fundamental communities, social networks, and government supported cyber-infrastructures. Employing new methods to counter those threats is one of the goals of biometric and cyber security.

Extensive research on behavior based profiling of software agents as an unobtrusive way of straightening out helpful bots from malware.  Additional research in art metrics is likely to produce more behavior-profiling methods specifically designed to take advantage of the unique construction of artificially intellectual programs.

This review chapter describes a new subfield of security research which transforms and expands the domain of biometrics beyond biological entities to include virtual reality entities, such as avatars, which are rapidly fetching a part of society. Art metrics research at Cyber safekeeping Lab, University of Louisville, USA and Biometric Technologies Lab, University of Calgary, Canada, builds on and expands such diverse fields of science as forensics, robotics, virtual worlds, computer graphics, biometrics and security. The chapter discusses how verification and appreciation of avatars can be ensured by analyzing their visual properties and behavioral profiling. It also introduces a multimodal system for artificial entities recognition, simultaneous.

SURVEY OF NON-BIOLOGICAL ENTITIES OF BIOMETRIC

Over the course of history, the maximum minds: scientists, philanthropists, educators, politicians, leaders, philosophers, were spellbound with the way human brain works. From Michelangelo to Lomonosov, from DaVinci to Einstein, there have been abundant attempts to reveal the mystery of human mind and to duplicate its working first through simple mechanical devices an later, in the 20^th century, through computing equipment, software and robots.

In Alan Turing’s 1950 work “Computing Machinery and cleverness,” Turing posed the question “can machines think?” In order to begin credible criteria to answer this inquiry, he planned a test, now known as “The Turing Test”—to appraise a machine’s capability to make obvious cleverness. At the core of the test is conversation in a natural language between the human judge and the adversary, who can be either human or a machine. If the judge cannot reliably tell the machine from the human, the machine is said to have approved the test. In the light of recent developments, it can be viewed as the ultimate multimodal behavioral biometric, which can detect differences between a man and the mechanism.

While automatic robot verification or performance analysis has not been closely investigated in literature, robot emotion gratitude has been studies to some degree. In addition to experiments on considerate of poignant states of robots, some work has been in progress on general analysis of avatar behavior, such as the project on Avatar DNA. Together, the segments define the makeup of an avatar. The genes of the avatar are exclusive and include user biometric data, public key information, personal information, verification information, creation data, etc. Verification modules in the virtual world collect information in a straight line from the avatar to establish the roles and rights that should be decided to this user.

There are three main types of non-biological entities that can be generally classified as Virtual Beings (avatars), intellectual Software Agents (bots), and Hardware Robots.

According to a dictionary, the word “Avatar” means: “embodiment: a new embodiment of a familiar idea”; or the demonstration of a Hindu deity (especially Vishnu) in human or superhuman or animal form. In an on-line the people, Avatar is a virtual representation of a player in an on-line world, a software creation that exists in virtual environment but is forbidden by a human player from the physical world. A comprehensive summary of avatar types is given in an on-line book by John Suler (2009). The book itself is not a typical publication – it exists only in the on-line form and evolves with time to reflect invariable changes in virtual gaming communities.

BIOMETRIC INFORMATION FUZZY FUSION

                      Now, let us take a quicker look at the way of how fuzzy logic can be utilized in biometric security domain, counting both conceptual and practical aspects of such incorporation. Shows a data flow chart for a sample fuzzy fusion module, which is a fuzzy rule-based possibility system. Similar to the experiments conducted for the evaluation of Markov chain based rank fusion method (Monwar & Gavril ova, 2011); this fuzzy fusion procedure also utilizes face, ear and iris biometric information. At first, the three matchers compare the three input biometric data with the stored templates and manufacture standing based on the similarity/distance scores. Markov chain based rank fusion come near only utilizes rank in progression of a multimodal biometric system, on the other hand fuzzy fusion based biometric rank fusion uses rank as well as match keep count for biometric information consolidation.

                     In the experimentation, the same two datasets which were used in the experiments involving Markov chain-based rank combination are used. Here, assessment has been made on fuzzy fusion move toward with unimodal matchers, with the rank fusion approaches and with Match score and decision fusion approaches

                     The fuzzy logic based fusion move toward for multimodal biometric system has been described. It is a influential intellectual tool used in many cognitive and decision-making systems. After discussing the basics of fuzzy logic, the fuzzy fusion instrument in the background of a multimodal biometric system has been illustrated. A brief conversation on the research conducted for fluffy logic based fusion in different submission domains has also been obtainable. The system indication and the choice of fuzzy rules to govern the system have been on hand. The biggest advantage of the system is that instead of binary Yes/No decision, the probability of a match and confidence level can now be obtained.

FUZZY LOGIC-BASED FUSION BIOMETRIC

In chapter six, the Markov chain based rank level fusion method has been introduced. The basics of Markov chain have been discussed and its structure mechanism in the context of multimodal biometric rank fusion has been shown. This method demonstrates a number of compensation over other rank fusion approaches in terms of acknowledgment presentation. Furthermore, this method satisfies the Condorcet measure, which is necessary in any fair rank information fusion process. In this chapter, another new biometric fusion approach based on fuzzy logic is discussed and hence named as fuzzy fusion for multibiometrics.

          Fuzzy fusion method is one of sub-branches of information fusion, which has lately emerged as information consolidation tool. Most fuzzy fusion methods reported in the journalism are residential for areas such as habitual target acknowledgment, biomedical image fusion and segmentation, gas turbine power plants fusion, weather forecasting, aerial image repossession and classification, vehicle detection and classification, and path planning. In the circumstance of biometric authentication, fuzzy logic based fusion approach has recently been used for superiority based biometric information consolidation process. In Monwar, Gavril ova, and Wang (2011), the fuzzy fusion method is utilized in multimodal biometric system.

         Fuzzy logic refers to the theories and technologies that employ fuzzy sets, which are classes with un-sharp limitations. The idea of fuzzy sets was introduced in 1965 by Professor Lotfi A. Zadeh from the University of California, Berkeley. The core technique of fuzzy logic is based on following four basic concepts:

·         Fuzzy Sets: A fuzzy set is a set with a smooth border line. Fuzzy set theory generalizes the classical set theory to allow fractional membership.

·         Linguistic Variable: A linguistic unpredictable in one which allows its value to be described both qualitatively by a linguistic term and quantitatively by a corresponding membership function (which represents the meaning of the fuzzy set).

         Fuzzy logic is indeed one of the fascinating areas on the edge stuck between cognitive science and decision making. Utilizing morality of fuzzy logic for information fusion allows emulating the abstract calculation and complex human intellect processes by the means of a range of values between yes or no, or true and false. In a machine language, it is a difference between 0 and 1, and in biometric terms—between accepted and refused individuality, or granted or denied access to a secure building or a facility.

         One of the first works in this domain which has implication for decision-making is 1999 work by Solaiman et al. The authors projected a fuzzy-based multisensory data fusion classifier for to be used in a geo-spatial and remote sensing domain for land cover classification. Their classifier provided a tool for incorporation of multisensory and contextual information. The authors introduced the Fuzzy Membership Maps (FMMs) to represent different thematic classes based on a priori information obtained from sensors. The FMMs were next iteratively updated using spatial appropriate information. The fuzzy logic allowed their projected classifier to incorporate multisensory and a priori information.

FUZZY FUSION OF BIOMETRIC INFORMATION

              In the previous chapter, different methodologies for rank level fusion were obtainable. These methods included plurality voting method, highest rank method, Borda count method; logistic weakening method and quality based rank fusion method for multimodal biometric system. Among those methods, the logistic weakening method constantly provides high Performance, however it still has some drawbacks. The results obtained through this method can be varied considerably for different datasets due to their miscellaneous qualities. Logistic deterioration method for a multimodal dataset with the same image quality will produce results similar to Borda count method, as the assigned weights to different biometric matchers’ outputs will be the same.

MARKOV CHAIN

A Markov chain is named for the Russian mathematician Andrei Andreyevich Markov. It is a mathematical model that can be thought of a being in exactly one of a number of states at any time (Markov, 1906). A Markov chain has a set of states, S = {s₁; s₂;:::; s_r}. The process starts in one of these states and moves successively from one state to another (Kemeny, Snell, & Thompson, 1974). Each move is referred to as a step. If the chain is currently in state s_i, then it can move to state s_j with a probability p_ij. This probability is preset at the beginning of the process and does not depend on how the state was reached. The probability p_ij is referred to as transition probabilities. The process can remain in the same state with probability pii. The starting state is given by an initial probability distribution (Kemeny, Snell, & Thompson, 1974).

Markov chains are applied in a number of ways to many different fields. They can be either used as mathematical model equivalent to some random physical process, or to reproduce an abstract theoretical thought. Application areas of Markov chain include physics (thermodynamics, statistical mechanics), chemistry (enzyme activity), the expansion of copolymers, statistics (statistical testing, Bayesian inference, etc.), Internet applications (page rank, analyzing Web navigation behavior of users, etc.), economics, finance, information sciences (Hidden Markov Model for pattern acknowledgment, Viterbi algorithm for error correction), bioinformatics, social sciences education, stock market predictions, music, and sports (Grin stead & Snell, 1997).

In 2011, Monwar and Gavril ova (2011) utilized Markov chain as a method for biometric rank combination. This approach brought a new dimension to the current ways of biometric rank aggregation and can be effectively used by the homeland and border security forces and by other cleverness services.

They considered the biometric rank aggregation similar to a voting mechanism. In the multimodal biometric rank fusion process, the classifiers are considered as voters. So, if there are three biometric traits used in a multimodal biometric system, the number of voters in the system would be three. Those three voters or classifiers manufacture three ranking list based on the comparison or distance scores of test and template biometric data. The final process is to combine the ranking lists obtained from three classifiers or voters to make a consensus ranking lists to find out the preferred identity or alternative from the system.

The same two datasets which were used in the experiments involving Markov chain-based rank fusion are used. Here, comparison has been made on fuzzy fusion approach with unimodal matchers, with the rank fusion approaches and with Match score and decision fusion approaches which is shown in through Figures 6-11.

The fuzzy logic based fusion approach for multimodal biometric system has been described. It is a powerful intelligent tool used in many cognitive and decision-making systems. After discussing the basics of fuzzy logic, the fuzzy fusion mechanism in the context of a multimodal biometric system has been illustrated. A brief discussion on the research conducted for fuzzy logic based fusion in different application domains has also been presented. The system overview and the choice of fuzzy rules to govern the system have been presented. The biggest advantage of the system is that instead of binary Yes/No decision, the probability of a match and confidence level can now be obtained.