printer friendly version

National biometric identity

When reviewing biometric-based citizen ID projects, great attention must be given to the importance of standards, interoperability, security and/or regulatory compliance goals. However, to be successful, it is also important that the biometric system performs reliably and successfully – under conditions that are representative of the target applications.

That is not easy when one remembers that large-scale, biometrics-based citizen ID projects must manage the availability of services across various sectors, including education, healthcare, pension providers, rural banking, and others where people come from different backgrounds, types of jobs and diverse environments.

Hope and vision are not enough. Several prestigious biometric pilots and projects, both national and international, failed to start or were later abandoned because they were not appropriately evaluated before deployment. Decision makers, giving priority to laboratory findings, forgot that there can be dynamic biometric reading differences between a doctor, a construction worker, a young person and a pensioner. The impacts of critical processes such as image acquisition, real world performance, ease of duplication and interoperability on the total system performance were never properly explored.

For instance, one requirement of citizen ID technology is that it be reliable and successful when used by the general citizenry. Thus, it is extremely important to understand the environmental and user challenges faced in the target deployment. Since the strongest predictor of biometric system performance is image quality measurement, has this been studied in the target environment with a representative population? Bottom line: can the solution read their fingers?

Here is why that is so important. The most commonly known fingerprint performance metrics are false reject rate (FRR) and false accept rate (FAR). Often, that is all that is studied. For those who are enrolled, can they get in or not? And, can others get in without being enrolled?

As importantly, though, are two other important criteria, FTE (failure to enrol) and FTA (failure to acquire), which come to the forefront throughout rural Africa and from the contrasting wet and dry locales in Africa. FTE refers to those people who could not be enrolled and hence cannot use the system at all (and, thus, do not show up in FRR and FAR statistics).

FTA refers to attempts by enrolled users to present their finger, but in which the sensor cannot acquire a good enough quality image to pass. In non-ideal real world conditions, such as African rural environments, FTE can easily exceed 10 or 20% with traditional fingerprint optical sensors. FTA is often in the 5 to 10% point range. This means that there are large portions of the intended users who simply cannot use the system at all plus many who cannot use it reliably.

What is their problem? Conventional optical fingerprint technologies depend on the condition of the fingerprint skin surface and its contact with the fingerprint sensor platen. And this creates a big problem for citizen ID projects. Real world conditions like dirt, dryness and humidity are prevalent with a rural user population. In addition, dry folds, wrinkled and problematic skin conditions are very common for senior citizens. Any one of these conditions leads to poor quality data capture with conventional optical sensors, resulting in the failure to acquire and failure to enrol problems.

Overcoming these common obstacles

Multispectral imaging is a sophisticated technology developed to overcome the fingerprint capture problems conventional imaging systems have in less-than-ideal conditions. This more effective solution is based on using multiple spectrums of light and advanced polarisation techniques to extract unique fingerprint characteristics from both the surface and subsurface of the skin. The nature of human skin physiology is such that this subsurface information is both relevant to fingerprint capture and unaffected by surface wear and other environmental factors.

The fingerprint ridges that we see on the surface of the finger have their foundation beneath the surface of the skin, in the capillary beds and other sub-dermal structures. The fingerprint ridges we see on our fingertips are merely an echo of the foundational inner fingerprint.

Unlike the surface fingerprint characteristics that can be obscured by moisture, dirt or wear, the inner fingerprint lies undisturbed and unaltered beneath the surface. When surface fingerprint information is combined with subsurface fingerprint information and reassembled in an intelligent and integrated manner, the results are more consistent, more inclusive and more tamper resistant.

Multispectral imaging technology can also detect living flesh from non-living flesh or other organic or synthetic materials used to duplicate fingerprints. Liveness detection is built from machine learning algorithms. Using these algorithms and the wealth of information available from multispectral fingerprint images, liveness detection capabilities can be updated if new spoofs are identified.

Unlike any other fingerprint technology, this learning capability allows multispectral imaging sensors to keep up with new threats. The inexpensive and readily available films and prostheses that easily defeat conventional fingerprint devices are rendered ineffective against this technology.

Successes around the world

Multispectral imaging has already demonstrated success in usability and scalability in both civil and commercial applications involving millions of users across the world. For example, more than 400 000 people pass through multispectral imaging sensors every day at the Hong Kong/Macau border crossings. The US government uses the technology in its Transportation Worker Identity Credential (TWIC).

In India, Analogics Tech India provides reliable fingerprint biometric solutions using multispectral imaging for prestigious customers, including TCS, Bartronics, ESSL, WIPRO, AGS and other. Their multispectral imaging sensor-based handheld readers are used in financial inclusion or rural banking applications where banking services such as opening savings accounts, transferring funds, making deposits, withdrawing cash and obtaining loans are taken to the poor and needy in remote rural areas, where citizens have no access to banks. Bank of India, Karnataka Bank, State Bank of Hyderabad and State Bank of Bikaner and Jaipur are all using the technology.

Multispectral imaging sensors are also used in biometric ATMs and handhelds that act like micro ATMs. These sensors are also used in rural employment guarantee programs where fingerprint-based biometric cards are used by beneficiaries to withdraw their weekly wages. Multispectral imaging-based handhelds are also used in public distribution systems and education projects, where the biometric is used by the citizens for collecting rations and for the authentication of students’ time and attendance reporting.

For a country in which the government is looking to provide services to its citizens and commercial entities want to reach out to the poor, especially those who, to date, have been excluded because of limited technology, multispectral imaging-based biometrics is turning visions into realities.

Share this article:

Further reading: