Implementing Biometrics based Systems: Identifying Selection Criteria

/in /by

Following up from last week’s article, researchers from the Biometrics Research Laboratory, BRL, at Namibia Biometric Systems recommends that it is a good idea to establish what criteria make sense to use in selecting a biometric solution. There are quite a large number of biometric technologies and applications out there, so the first step has to be to establish what characteristics of the environment and the potential biometric solutions are of interest and useful in determining what to select.

At BRL we believe that it’s important to be familiar with the people who’ll be using the biometric solution. At the very least, you must ask and have answers to the following questions before implementing:

Ethnic Background – It is important to understand the ethnic background of who will be the users of the biometric system. For example, will the users be members of the general public with a mix of ethnic and education levels and a variety of attitudes? This will be vital in selecting which biometric system will be suitable for the ethnic background.

Employee Education – It is important to understand the technical background of the users. For example, will the users be employees in a high-tech firm or not? The higher the technological background of the users, the more likely that the users will be aware of biometric system and hence require more specialised training. It is vital to provide educational material suitable for the users.

Frequency of Use – It is important to understand that some biometric systems are more suitable for high frequency of usage than others. Therefore it is important to ask whether the biometric system will be used several times a day or just a couple of times each year?

User characteristics – It is important to understand who will be using the biometric system. For example, will the users be in a hurry and possibly be a little bit impatient (biometric controlled entry into a public restroom comes to mind just now)?

Researchers from the BRL show that it is vital to understand about who will be the users of the biometric system. The research further shows that most government and private organisations implementing biometric based solution under mine these criteria. For example, researchers at BRL believe that health care is an area where convenient reliable access to information isn’t just nice to have but it’s an absolute requirement with lives hanging in the balance. In addition, it happens to be a place where access control to extremely sensitive information is required by law and the expectation of patients, so biometric access controls are often considered for these environments.

 

More information on the implementation of biometrics based solutions can be requested from info@namibiabiometricsystems.com

Implementing Biometrics based Systems: Common Mistakes

/in , /by

Fraudsters have had years to mastered and fine tune their fraudulent methods on conventional means of identification such as passwords, secret codes and Personal Identification Numbers (PINs) which can easily be compromised, shared, observed, stolen or forgotten. Therefore, both governments and commercial sectors have turned to more secure Biometrics based solutions which automatically recognize an individual using distinguishing behavioural patterns such as gait, signature, keyboard typing, lip movement, hand-grip or physiological traits such as face, voice, iris, fingerprint and hand geometry. As a result, countries worldwide have opened tenders for Biometric based projects. This has led to a vast majority of industrialists to enter the market with very limited experts. Research analysts at Biometric Research Laboratory (BRL) have outlined the most common pitfalls when implementing biometrics based solutions. BRL is the research group at Namibia Biometric Systems (NBS) which conducts applied research in the implementation of Biometrics based solutions for both governments and commercial applications. Some of the common pitfalls highlighted by researchers at BRL are outlined below:

Consultation – Sufficient time for consultations with technical experts before, during and after implementation is critical to the success of the project. Generally, governments and commercial companies are not prepared for the complexities of implementing biometrics based solutions and either are not aware or lack the understanding of why consultation with a local specialist is critical. Consultation is also essential for successful project plan.

Project Management – Research conducted at BRL show that generally governments and commercial companies don’t have the technical expertise in-house to properly manage or oversee the implementation of the technology and lack essential the project management skills and resources. As a result, the project management team fails to realistically identify possible sources of risk, to consider any mitigating factors and provide appropriate responses. This can lead to the project being poorly managed, risking the safety of the biometrics data, risking the project completion timeframe and provide the vendors of the technology a central role in the implementation of the technology without proper oversight. The issue of identity management and protecting people’s identities is one of the core responsibilities that companies have when implementing biometrics based solution.

Tenders – Governments and private companies tend to place significant trust on tender winning companies which have very different priorities. These conflicting priorities can have dangerous implications for the implementation of the project. In additions, governments and private companies tend to lack the knowledge and understanding of the technology and therefore don’t have the skills and experts to eliminate tendering companies with limited or no experience with the technology.

More information on the implementation of biometrics based solutions can be requested at info@namibiabiometricsystems.com.

Biometric Systems in Academia

/in /by

The deployment of biometric systems has increased significantly in academic institution for cashless catering system, automated system for recording attendance and automated biometric library systems. Biometric systems in academic institutions circumvent the limitations of traditional systems. Biometric systems in academic institutions are safe, secure and easy to use without using any password or secret codes to remember. The traditional security systems in schools may inconvenient staff and students as the student/staffs have to carry card at all times as required for the usage of the library, meals and record attendance which may be useful information for financial sponsors. In addition, traditional security systems using smartcard technology may prove to be very expensive as cards may be lost or damaged and require replacement while biometric solutions can not be lost. What is the annual cost for lost or damaged smartcards to your institution? Research analysts at Biometric Research Laboratory (BRL) have outlined three examples of biometrics in academic institutions. BRL is the research group at Namibia Biometric Systems (NBS) which conducts applied research in the implementation of Biometrics based solutions for both governments and commercial applications.

Cashless catering system: Financial sponsors pay in advance for students’ meals, crediting the students’ accounts with the amount paid in. The student or staffs then use this credit to pay for their meals on campus. Students or staffs can be identified at the till by an automated biometric system, with the cost of their meal being deducted from the credit paid in their account. There are several advantages to cashless catering. Students or staffs do not need cash to pay for their meals, reducing the opportunity for theft. Such systems can also speed up service in canteens and dining rooms.

Automated Biometric attendance and registration: Students register using an automated biometric system at the entrance of each lecturer. Entrance time and exit time is registered per students. Such systems can save considerable time and effort in taking registers. In addition, there is no opportunity for students to register absent students by using their smartcards or signing for them. Biometric systems can also help prevent unauthorised access to academic institutions. Attendance data can be used to help assess the impact of truancy on performance allowing any necessary steps to be implemented rapidly. This is an essential tool in performance management.

School library automation: An automated biometric system identifies and records the student’s name and the book/items they have borrowed or are returning. Thus giving staff more time to focus on other critical issues.

More information on the implementation of biometrics based solutions can be requested from info.@namibiabiometricsystems.com.

Biometric Payment System

/in /by

Biometric payment system uses biometric authentication to identify the user and authorize the deduction of funds from a bank account. Biometric payment system based on fingerscanning is the most common biometric payment method. Biometric payment system circumvents the limitations of traditional payment systems. Biometric payment system is much safe, secure and easy to use without using any password or secret codes to remember. The current traditional payment systems may inconvenient users as a person has to carry many cards, has to remember their passwords or secret codes and has to keep the cards and secret codes secure at all times. For example, a person may carry credit cards, store cards for shopping, student card for library and many other kinds of cards for other purposes.

Examples of the use of biometric technology in shopping- like any biometric based system, it starts with the registration of users. The shopper registers for biometric payment solutions by presenting a valid ID, bank account information and submit their biometric such as fingerprints for a scan. The biometric system extracts relevant features from the fingerprint and stores in a biometric database. Once the shopper has been registered in the system, he/she has the option of using the biometric payment system rather than using the credit card payment system or cash system. The biometric payment system operates by scanning the shopper’s biometric such as fingerprint, extract relevant biometric data and verify the shopper. If the shopper’s biometric, fingerprint, is authenticated using the biometric identity verification software, access is granted to that customer’s payment account. The system retrieves the customer’s bank account information, credit card details, and the shopping costs get deducted from their balance. The payment process is completed within a matter of seconds without the customer having to worry about looking in their wallet or her purse for cash or trying to cover their fingers as they types in their PIN number.

Biometric payment system makes it faster to complete the transactions, minimizes customer inconveniency as customers are only required to get their biometric scanned and the biometric system does all the work. The customer can not forget their biometric at home.

More information on the implementation of biometrics based solutions can be requested from info.@namibiabiometricsystems.com.

Enhanced Banking Solution by Namibia Biometric Systems, NBS

/in /by

The last article focused on biometric solution for online banking, new biometric Automated Teller Machines, ATMs. This article focuses on the limitations of online banking as it does not cater for offline banking services which are essential for good customer satisfaction and for a large segment of the population in 3rd world countries.

A review of the banking solution technology by researcher at BRL highlights that debit and credit cards used to be magnetic-stripe cards in compliance with the International Organization for Standardization and International Electrotechnical Commission, ISO, Magnetic Stripe Card Standards (ISO 7810, ISO 7811, and ISO 7813). Some of the limitations of magnetic-stripe cards are that:

Magnetic stripe cards have minimal security. The data on the card is easily read from and written to a magnetic stripe card, information can be easily stolen and a duplicate magnetic stripe card can be created.

Magnetic stripe cards have minimal data capacity – The data storage is very limited and thus providing significant constrains of what can be stored on the cards.

Magnetic stripe cards have minimal authentication security – The cards payment methods require the cardholder to confirm the payment with a handwritten signature on a slip of paper.

To circumvent the limitations of magnetic stripe cards, hybrid smart cards consisting of both a microprocessor chip and a magnetic stripe were introduced. These hybrid banking cards significantly improves the authentication capability and enables new protocols for securing payment processes. In the absence of an online connection to the issuing bank’s network, the card is able to represent the card issuing bank and to authorise payments on the behalf of the bank by verifying a Personal Identification Number, PIN, entered by the customer against the PIN stored in the chip of the smart card. However, our researchers at BRL are keen to highlight that Biometric based solutions have been introduced to overcome the limitations of traditional authentication methods such as PIN and password based.

Therefore, a modern banking solution must overcome the limitations of traditional authentication methods while utilising the benefits of both offline and online banking. A modern banking solution must not depend on the cashier’s ability to visually compare the image of a given signature with the signature image on the back of the card. Therefore, researchers at BRL are keen to highlight some of the requirements for a modern banking solution:

  • It must meet the latest 2011 EMV 4.3 Specifications (named after the organisations Europay, Mastercard, and Visa, who created the first version).
  • It must meet the latest ISO/IEC 7816 requirements and building blocks for smart-card based payment systems.
  • It must meet the latest on-card biometric standards such as ISO/IEC 7816-11 & ISO/IEC 24787 specifying several approaches on how to achieve personal verification through biometric methods.

BRL researchers within NBS continue to work with vendors and independently review the optimal banking solution which is suitable for online services, offline services and suitable for both traditional and biometric authentication methods providing banks with customisation capabilities as required. Researchers at BRL with doctorates in Biometrics, PhD degrees, view the banking solution as an optimisation problem and therefore apply advanced mathematics for a solution which minimises the costs to the financial institution (including over consultation costs), minimise the costs to customers, minimise the impact to the nation while maximising the Return on Investment, ROI. In additions, NBS’s solution is designed to minimise over consultation and avoid reputational costs from multinational companies monopolising the biometrics market. It is essential for 3rd world countries to obtain biometric solutions characterised by high accuracy and speed while minimising the cost which is independent of reputation.

In summary, the banking solution by researcher at BRL and NBS technicians has the capabilities to effectively operate online or offline as an individual bank account for all types of transactions such as Salary Payments, Third Party Money Transfers, Third Party Bill Payments, Salary Advances or Loan Registration to Cards, Social Grant Benefit Payments & Pension Collection & Distribution, Transacting at Retail Merchants, Pre-paid Airtime and Electricity, Insurance, National ID & Voting, Driver’s License, National Health Insurance and Medical & Patient Management.

More information on the implementation of biometric based solution for banking can be obtained via a requested from info.@namibiabiometricsystems.com.

Namibia Biometric Systems’ Banking Solution

/in /by

This article is motivated by the work conducted by researchers within Biometric Research Laboratory, BRL, at Namibia Biometric Systems on biometric solution for banking. The work is motivated by the growing interest in the deployment of biometric solution in banking and to minimize error rates during the implementation phase. Researchers at BRL discovers interesting results in the deployment of biometrics in banking: cash machine cards are becoming a thing of the past following the launch of new biometric Automated Teller Machines, ATMs, which let users withdraw money simply by pressing their biometrics that identifies them from the unique biometric pattern. The research conducted by BRL makes the days of fumbling with desktop card readers, phone authentication and PIN codes a thing of the past. The biometric solution can incorporate a suitable personal biometric scanner to keep your internet banking security firmly under your biometrics which you will never forget. The aim of the research at BRL is to replace the costly chip in bank cards with an individual’s biometrics and eliminates the following limitations:

Card chip production – It costs banks a significant amount of money to pay for the chips used in the current bank cards. The cost of chip production is generally passed down to customers in various ways. Banks have to buy chip from chips manufacturing companies who also need to make a profit.

Bank Card Production – It is important for consumers to release that banks also have to pay card manufacturers for the production of the banking cards who also need to make a profit. It is not a surprise that the cost is passed down to the clients in various forms.

Bank Chip and card integration – the integration of the chip and bank card requires specialised skills to ensure the integrity of the card.

The Return On Investment, ROI, is substantial in banking for 3rd world countries if implemented within suitable guidelines and standards. However, researchers at BRL are keen to emphasise that in every country banks are different and may require specific consultation.

The proposed biometric solution for banking by BRL is characterised as follow:

  • It captures additional information such as demographic data like date of birth, present address, National Identification/ passport, marital status, education, etc.
  • It ensures that each customer has the relevant products such as saving accounts, fixed term deposits, etc.
  • It ensures accurate processing of salary and wage slips.
  • It ensures accurate processing of the senior citizen’s pensions.
  • It ensures a reduced monthly fee which is automatically deducted.

Researchers at BRL have independently identified and assessed the best biometrics for banking solutions using international standards from different vendors. Researchers at BRL are keen to stress the importance of utilizing biometric standards and the best practice when implementing biometric based solution.

More information on the implementation of biometric based solution for banking can be obtained via a requested from info@namibiabiometricsystems.com.

Multimodal Biometrics Fusion using Multi-Traits

/in /by

The articles on Multimodal biometrics have focused on data sources. The articles looked at multi-sensor fusion strategy, multi-algorithm strategies and multi-instance fusion. Multi-sensor fusion strategy utilises a single biometric trait captured using multiple sensors in order to extract diverse information from the image. While, multi-algorithm system uses only a single biometric capturing device (single sensor) to obtain raw data and then the raw biometric data is processed using multiple algorithms. It is clear that multi-algorithm systems are cheaper and more convenient for customers than multi-sensor as multi-algorithm systems do not require the use of additional biometric capturing devices. The customers are not required to interact with multiple capturing devices. However, multi-algorithm fusion requires the introduction of a new feature extractor and/or matcher modules which may increase the computational requirements of the system. Multi-instance fusion strategy utilises multiple instances of the same body trait such as the left and right index fingers of an individual may be used to verify an individual’s identity. Multi-instance fusion strategy overcome the limitations of both multi-sensor and multi-algorithms as Multi-instance does not introduce new sensors nor does it require the development of new feature extraction and matching algorithms.

In this article we introduce multi-traits fusion strategy. Multi-traits fusion strategy utilises multiple body trait to establish identity. For example, multi-traits biometric systems can utilize face and voice features to establish the identity of an individual. Uncorrected biometric characteristics are expected to result in better improvement in performance than correlated biometric traits. Voice and lip movement are example of correlated traits while fingerprint and iris are examples of uncorrelated biometric traits. The identification accuracy can be significantly improved by utilizing an increasing number of biometric characteristics. The number of biometric characteristics used in a specific application will be restricted by practical considerations such as the cost of deployment, enrollment time, throughput time, expected error rate, user habituation issues. Generally, the main limitations of multi-traits are cost and the development of appropriate user interfaces.

Other fields – Information fusion continue to be used in a diversity of scientific fields such as Land Mine detection. Several types of sensor technologies are being used to detect buried land mines. These include electromagnetic induction (EMI), ground penetrating radar (GPR), infra-red imaging (IR), quadrupole resonance (QR), chemical detectors and sensors of acoustically induced surface vibrations. In many cases, the data presented by these multiple sensors are concurrently used to improve the accuracy of land mine detection algorithms.

Our researchers within BRL at Namibia Biometric Systems will continue to examine the levels of fusion that are possible in a multimodal biometric system in the next article. In addition, our researchers at BRL would like to thank all the readers of the articles from Namibia, Africa and world wide.

More information on the implementation of biometrics based solutions can be requested from info@namibiabiometricsystems.com.

Limitations of using a Single Biometric in applications

/in , /by

In recent years, there has been a significant surge in the use of biometrics for user – authentication applications such as electronic passports, electronic voting, etc because biometrics-based authentication offers multiple benefits over knowledge and possession-based methods such as password and PIN based systems. It is crucial that such biometrics-based authentication systems are designed to resist different sources of attacks on the system when employed in security-critical applications. Therefore this article outlines some of the inherent limitations of using a single biometrics-based authentication scheme.

Biometric data capture device – The environment in which biometric data is captured during the enrolment phase is usually different from the environment in which the biometric data is captured during the identification or verification phase. The captured biometric data might be noisy or deformed. The source of noise can be due to the followings:

  • Captured voice data can be altered by cold, acute laryngitis viral infection that leads to swelling of the vocal cord, chronic laryngitis can be caused by acid reflux disease due to low grade infections such as infections of the vocal cords in people using inhalers for asthma, voice misuse and overuse as speaking is a physical task that requires coordination of breathing with the use of several muscle groups, etc.
  • Captured iris data can be altered by wearing glasses and various infections to the iris.
  • Captured fingerprint data can be altered by scars, oily fingers, dry, wet or damaged temporally or permanently. It is also important to realise that some people might just have poor fingerprint quality.
  • Face data can be altered by environmental conditions such as variations in light, pose or illumination.

It is not surprising that noisy captured biometric data may be false matched with templates in database resulting in a false rejection or false acceptance.

Distinctiveness – Previous articles outlined the characteristics of a good biometrics such as:

  • Distinctiveness: unique to every individual.
  • Universality: every individual must posses the biometric.
  • Permanence: invariant with time (hardly changes).
  • Collectable: the biometrics must be measurable.
  • Performance: high speed and accuracy.

It is easy to see how the performance of a biometric system can be degraded by noisy data and lack of distinctiveness.

Our researchers within Biometric Research Laboratory, BRL, at Namibia Biometric Systems will outline how a practical biometric system can overcome some of the limitations outlined above in the next article.

More information on the implementation of biometrics based solutions can be requested from info@namibiabiometricsystems.com.

Multimodal Biometrics Fusion using Multi-Instance

/in /by

The articles on Multimodal biometrics have focused on data sources. The articles looked at multi-sensor fusion strategy, multi-algorithm strategies and multi-instance fusion. Multi-sensor fusion strategy utilises a single biometric trait captured using multiple sensors in order to extract diverse information from the image. While, multi-algorithm system uses only a single biometric capturing device (single sensor) to obtain raw data and then the raw biometric data is processed using multiple algorithms. It is clear that multi-algorithm systems are cheaper and more convenient for customers than multi-sensor as multi-algorithm systems do not require the use of additional biometric capturing devices. The customers are not required to interact with multiple capturing devices. However, multi-algorithm fusion requires the introduction of a new feature extractor and/or matcher modules which may increase the computational requirements of the system. Multi-instance fusion strategy utilises multiple instances of the same body trait such as the left and right index fingers of an individual may be used to verify an individual’s identity. Multi-instance fusion strategy overcome the limitations of both multi-sensor and multi-algorithms as Multi-instance does not introduce new sensors nor does it require the development of new feature extraction and matching algorithms.

In this article we introduce multi-modal fusion strategy. Multi-modal fusion strategy utilises multiple body trait to establish identity. For example, multimodal biometric systems can utilize face and voice features to establish the identity of an individual. Uncorrected biometric characteristics are expected to result in better improvement in performance than correlated biometric traits. Voice and lip movement are example of correlated traits while fingerprint and iris are examples of uncorrelated biometric traits. The identification accuracy can be significantly improved by utilizing an increasing number of biometric characteristics. The number of biometric characteristics used in a specific application will be restricted by practical considerations such as the cost of deployment, enrollment time, throughput time, expected error rate, user habituation issues. Generally, the main limitations of multi-modal are cost and the development of appropriate user interfaces.

Multi-instance overcomes the limitations of both multi-sensor and multi-algorithms. Multi-instance fusion strategy has the limitations that it may be slow and may result in poor customer satisfaction. Researchers at BRL highlights that the limitations of multi-instances can be simply overcome by a new sensor arrangement in order to facilitate the simultaneous capture of the various units/instances. Multi-instance fusion strategy is advantageous for individuals whose biometric characteristics cannot be reliably captured due to inherent problems. For example, an Automated Fingerprint Identification Systems (AFIS), may benefit from sensors that are able to rapidly acquire impressions of all ten fingers. NBS researchers understand that a single finger may not be a sufficient discrirninator for a person having dry skin or bad fingerprints. Therefore, the integration of evidence across multiple fingers may serve as a good discriminator. Similarly, an iris system may not be able to image significant portions of a person’s iris due to drooping eyelids.

Other fields – Information fusion continue to be used in a diversity of scientific fields such as Object detection. Many applications attempt to detect and establish the trajectories of objects based on the evidence supplied by multiple image modalities. The fusion of visible and non-visible information pertaining to different wavelengths in the electromagnetic spectrum such as radar and infrared images, thermal and visible spectrum images may assist in estimating the location and kinematic features of objects such a squad of soldiers in a night-time battlefield. These applications rely on image fusion methodologies to combine multiple modalities.

Our researchers within BRL at Namibia Biometric Systems will continue to examine the levels of fusion that are possible in a multimodal biometric system in the next article. In addition, our researchers at BRL would like to thank all the readers of the articles from Namibia, Africa and world wide.

More information on the implementation of biometrics based solutions can be requested from info@namibiabiometricsystems.com.

Information Fusion For Multimodal Biometrics

/in /by

Multimodal biometric systems overcome limitations such as:

Noise in captured data – A voice sample can be altered by cold while a fingerprint image can be altered by a scar. Noise data can also be a result of defective or improper maintenance of the sensors. When the captured biometric data from a single trait is corrupted with noise, the availability of other (less noisy) biometric characteristics may aid in the reliable determination of identity.

Intra-class variation – This is typically due to an individual who incorrectly interacting with the sensor or due to changes in the biometric characteristics of a person over a period of time. Therefore, results in a variation of the biometric characteristic for the same individual. Intra-class variation can be handled by storing multiple templates for every user.

Inter-class similarities – This refers to the overlap of discriminating features corresponding to multiple individuals. Increasing the number of individuals enrolled in a biometric system, is likely to increase the inter-class similarities and false match rate of an identification system. Multimodal biometric increases the number of discriminatory features for every individual.

Non-universality – The biometric system may not be able to capture meaningful biometric data from a subset of users. A fingerprint system may extract incorrect minutia features from the fingerprint of certain individuals due to poor quality of the ridges. Multimodal can substantially improve the accuracy of a biometric system depending upon the information being combined and the fusion methodology.

Spoof attacks – This involves the deliberate manipulation of one’s biometric characteristic in order to avoid recognition or the creation of a fake biometric characteristic in order to take on the identity of another person. It becomes increasingly difficult for an impostor to spoof multiple biometric characteristics of a legitimately enrolled individual.

The inherent limitations of a single biometric system are alleviated by fusing the information presented by multiple sources. Fusion of biometric information results in increasing the number of discriminating features used to represent individuals. The magnitude of discriminatory information available in a biometric characteristic is restricted. Therefore, it increases the number of individuals who can be enrolled in the biometric system.

Humans recognize each other using multiple behavioural and physical biometric characteristics. Therefore, the recognition process may be viewed as the reconciliation of evidence from multiple modalities. Although humans can sometimes use a single modality to identify each other, it is not always used to reliable perform recognition.

Information fusion has also been used in a diversity of scientific fields such as weather forecasting. Weather forecasting system relies on evidence provided by diverse sources of information such as geostationary meteorological satellites, weather balloons/planes, ground stations, etc.

In this article we consider multi-sensor fusion strategy. Multi-sensor system uses a single biometric characteristic captured by multiple sensors in order to extract diverse information. For example, a system may capture the two dimensional texture content of a person’s face using a 2D camera and a three dimensional surface shape of the face using a 3D camera. The use of multiple sensors, in some instances, can result in the acquisition of complementary information that can enhance the recognition ability of the system. The performance of a 2D face matching system can be improved by utilizing the shape information presented by 3D range images.

Our researchers within Biometric Research Laboratory, BRL, at Namibia Biometric Systems will continue to examine the levels of fusion that are possible in a multimodal biometric system in the next article.

More information on the implementation of biometrics based solutions can be requested from info@namibiabiometricsystems.com.