Information Fusion For Multimodal Biometrics

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

How Automated Border Control (ABC) Works

As outlined in the previous article, Automated Border Control (ABC) is defined as the use of automated or semi-automated systems which can verify the identity of travellers at border crossing points (BCPs), without the need for human intervention. Automated border process is conducted as follows:

  • The traveller inserts the biographical data page of the passport into the passport reader.
  • The passport reader checks security features, extracts information in the Machine Readable Zone (MRZ) and communicates with the chip in the e-Passport to verify the genuineness of the document. The aim of this process is to check that the traveller is carrying a genuine and valid travel document. This is referred to as the Document authentication process.
  • Capture a live biometric image of the traveller, extract relevant features and then compare with the biometric data stored in the chip. This process is similar as in the manual border control where an officer compares the traveller’s face to the picture in the old picture in the passport. The aim of this process is to verify by using biometrics that the travel document belongs to the traveller. This process is referred to identity verification process.
  • The system checks if the traveller is indeed entitled/authorized to cross the border. The biographic data may be checked against available watch list databases. If there is a potential match then the traveller should be directed to an officer. The exact process will depend on the procedures in place within each border management authority.
  • If the verification is successful the E-Gate allows the traveller to cross the border. Otherwise, the traveller is referred to manual control. Therefore, the process must be supervised by qualified border guards. The decision to allow/deny access is based on pre-defined logic, sometimes requiring the intervention of the border guard operating the system. Some ABC systems may allow the recording of traveller’s Entry/Exit data.

In general, an ABC system consists of the following equipments:

  • One or two physical barriers (e-Gates).
  • E-Passport readers: optical recognition of the biographic data page, the MRZ and a radio frequency (RF) reader for communication with the chip.
  • A monitor for displaying instructions in a language understood by travellers.
  • Biometric capture device. This depends on the type of biometric been used.
  • System management hardware and software. Maintenance of both hardware and software are critical for operation of the system.

More information on this article or any of the previous articles can be requested from

Biometrics in Automated Border Control (ABC)

Border control plays a critical role in securing any Nation’s borders between Ports of Entry (POEs) against all threats. Research analysts at our Biometric Research Laboratory, BRL, approach border control from a risk-based orientation which allows the border control teams to apply Information, Integration and Rapid Response in the most targeted, effective, and efficient manner. Therefore, border control teams must be given the tools and resources to execute their jobs efficiently. Traditional border control methods require the border control officer to compare a picture in the passport to your face. Traditional methods have their limitations such as:

Exhaustion – Imagine being a border control officer comparing old passport photographs to a passenger’s faces all day in addition to checking other vital information. How long will it take before your concentration runs out? Analysts at BRL believe that most passengers are allowed through boarder control without being properly authenticated when staff have been working for a long period of time without sufficient breaks.

Nationality – Imagine being a border control officer analysing passport photographs of different nationalities all day in addition to checking other vital information. Which Nationality would you find easier to analyse? Analysts at BRL suggest that people find it easier to analyse photographs of people from the same nationality as themselves. Therefore, more passengers are likely to pass through border control without been properly authenticated if their being served by someone of different Nationality.

Image – Passport pictures are generally taken in a controlled environment. That is, the lightning and pose are controlled. Imagine being a border control officer analysing passport photographs of passengers with different hairstyles, facial wears and mark-ups all day in addition to checking other vital information. Analysts at BRL highlight that the ability of humans to recognize a human face is a function of hairstyles and facial wear. Therefore, more passengers are likely to pass through border control without been properly authenticated if the passenger’s hairstyle and facial wear are different from the picture in the passport.

The above limitations can be easily be resolved by biometrics at border control by using Automated Border Control (ABC). ABC is defined as the use of automated or semi-automated systems which can verify the identity of travellers at border crossing points (BCPs), without the need for human intervention. Generally, an ABC system consists of one or two physical barriers (e-Gates), document readers, a monitor displaying instructions, a biometric capture device and system management hardware and software.

More information on the implementation of biometrics based solutions can be requested from

Benefits of Electronic Voting

There are an increasing number of countries around the world that have implemented or piloted electronic voting (e-voting) and electronic counting (e-counting) systems. Although each country’s experience is different, the increasing adoption of these new technologies is due in part from the recognition that technology may offer benefits over traditional methods of voting and counting. Some of the benefits of e-voting and e-counting may include:

  • E-voting eliminating the cost and logistics involved with paper ballots. The costs of paper ballots must not be undermined. E-voting machines can be used over many elections and therefore the cost is reduced costs significantly if well implemented.
  • E-voting can improve voter identification mechanisms compared to manual traditional methods of voter identification. Traditional methods of voter identification are labour intensive. Voting officials are faced with the monotonous task of manually verifying thousands of voters in challenging working environments. It is expected that the error rate in voter identification increases as the officials get tired. E-voting greatly reduces direct human control and influence in this process.
  • E-voting can make the conduction of complex elections easy and likely to increase voter turnout if implemented with strict guidelines. Introducing e-voting touches the core of the entire electoral process such as the casting and counting of the votes.
  • E-voting eliminating invalid ballots. Paper ballots can result in badly educated voters to cast invalid votes.
  • E-voting can result in faster, more accurate and standardized counting of ballots. In most African countries, the counting of thousands of paper votes is conducted by recent grade 12 graduates who lack the experience and skills required for such a vital national project. In addition, the recruitment process tends to lack strict essential security checks. Thus putting the elections at high risk.
  • E-voting can results in prevention of certain forms of fraud. Many National elections worldwide have been characterised with missing ballots, impersonation voters (where someone steals a voter’s identity and votes on their behalf), etc. On the other hand, fraud in e-voting systems can only be conducted by qualified individuals. The percentage of qualified individuals likely to conduct fraud in e-voting is much smaller compared to the percentage of both qualified and unqualified individual likely to perform fraud on paper voting. The weaknesses of both voting systems must be fully understood in order to minimize fraud.

It is essential that E-voting is implemented with certain guidelines in order to maximise the election outcomes:

  • E-voting must be implemented in a transparent and verifiable manner. Access should be provided for observers in a manner that does not obstruct the electoral process.
  • E-voting and e-counting systems must be easy to understand and use. Stakeholders must be involved in the design of the e-voting and e-counting system.
  • E-voting and e-counting systems must be certified by a qualified, independent body before their use and periodically thereafter.
  • Security measures must be taken to ensure that data cannot be lost in the event of a breakdown, only authorized voters can use the machines, only authorized persons are allowed to access the machines.
  • E-voting and e-counting must be auditable so that it is possible to determine whether they operated correctly. It must be possible to conduct a recount votes. Vote recounts must involve accurate monitored manual recounts of votes cast electronically (e.g., with the paper record representing the basis for legal determination of the vote cast).

More information on the implementation of biometrics based solutions can be requested from

Levels of Fusion in Multimodal Biometric Systems

The previous articles on Multimodal biometrics had focused on data sources such as multi-sensor, multi-algorithm, multi-instance and multi-traits. This article will focus on the levels of fusion. The amount of information available to a biometric system drastically decreases as one proceeds from the sensor module to the decision module (matching module). In a multibiometric system, fusion can be accomplished by utilizing the information available in the sensor module, feature module, score module and decision module. The levels of fusion can be broadly classified as fusion prior to matching and fusion after matching.

Fusion prior to matching: This is the fusion of data prior to matching. The integration of information from multiple biometric sources can take place either at the sensor level or at the feature level. The raw data from the various sensors can be integrated or combined in sensor level fusion. Sensor level fusion can only be employed if the multiple sources represent samples of the same biometric characteristics obtained either using a single sensor or different compatible sensors. For example, 2D face images of an individual obtained from several cameras can be combined to form a 3D model of the face. While Feature level fusion refers to the integration of different feature sets extracted from multiple biometric sources. Biometric features used in the feature level fusion can be divided into two set, homogeneous and non-homogeneous. When the feature sets are homogeneous (e.g., multiple measurements of the same biometric characteristic such as a person’s hand geometry), a single resultant feature vector can be calculated as a weighted average of the individual feature vectors. While if the feature sets are non-homogeneous (e.g., features of different biometric modalities such as face and hand geometry), the features can be concatenated into a single feature vector. Feature selection schemes are employed to reduce the dimensionality of the ensuing feature vector. Concatenation is not possible when the feature sets are incompatible.

Fusion after matching: This is the fusion of data post matching. The integration of information after the matcher stage can be divided into four categories: dynamic classifier selection, fusion at the decision level, fusion at the rank level and fusion at the match score level. A dynamic classifier selection scheme chooses the results of that biometric source which is most likely to give the correct decision for the specific input pattern. This is also known as the winner-take-all approach within the biometrics world. Integration of information at the decision level can take place when each biometric system independently makes a decision about the identity of the user (in an identification system) or determines if the claimed identity is true or not (in a verification system). Since most commercial biometric systems provide access to only the final decision output by the system, fusion at the decision level is often the only viable option. When the output of each biometric system is a subset of possible matches (i.e., identities) sorted in decreasing order of confidence, the fusion can be done at the rank level. This is relevant in an identification system where a rank may be assigned to the top matching identities. When each biometric system outputs a match score indicating the proximity of the input data to a template, integration can be done at the match score level.

More information on the implementation of biometrics based solutions can be requested from