February 2011

How multispectral imaging makes citizen ID management possible

Views: 179

When designed properly with a reliable technology, identity management projects deliver reliable performance with enhanced security and convenience and a meaningful ROI

When reviewing biometrics 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 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?

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

Here’s why that is so important. The most commonly known fingerprint  performance metrics are false reject rate (FRR) and false accept rate (FAR).  Often, that’s all that 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  enroll) and FTA (failure to acquire) — which come to the forefront throughout  rural India. FTE refers to those people who could not be enrolled and hence  cannot use the system at all (and, by the way, do not show up in FRR and FAR  statistics). FTA refers occasions when a sensor cannot acquire an adequate  image from an enrolled user. In non-ideal, real world conditions such as Indian  rural environments, the FTE can easily exceed 10 or 20 percent with traditional  fingerprint optical sensors. The FTA is often in the 5 to 10 percent  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’s the 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 in India.  According to UN statistics, approximately 70 percent of the Indian population resides in rural areas. Real world conditions like dirt, dryness and humidity are  prevalent with a rural user population. In addition, dry folds, wrinkles 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- enroll problems.

Multispectral technology to get
over image capturing obstacles

Multispectral imaging is a sophisticated technology developed to overcome the  fingerprint capture problems that conventional imaging systems have in  less-than-ideal conditions. This more effective technology uses multiple spectrums of light and advanced polarization 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.”

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 in India

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 cutting-edge 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.

Success stories in India and around the World

Multispectral imaging has already demonstrated usability and scalability in successful civil and commercial applications involving millions of users across  the world. For example, more than 400 thousand 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). After an extensive industry-wide  evaluation of biometrics technology and devices, CareFusion selected multispectral imaging fingerprint sensors and software for integration into their  latest generation of drug dispensing cabinets. Multispectral imaging based  sensors are also used by the US military.

Here in India, Analogics Tech  India provides reliable fingerprint biometric solutions and leverages  multispectral imaging for prestigious customers including TCS, Bartronics,  ESSL, WIPRO, AGS and others. Analogics’ multispectral imaging sensor- based  handheld readers are used in financial inclusion or rural banking applications  where banking services, such as new savings accounts, funds transfers,  deposits, cash withdrawals, and loan applications, are taken to the poor and  needy in remote rural areas where citizens have no access to traditional banks.  The Bank of India, Karnataka Bank, State Bank of Hyderabad and State Bank of  Bikaner and Jaipur are all leveraging 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 being used in  the pilot of public distribution system projects, where the biometric is used to  collect rations.

For a country such as India, in which the government is looking  to provide services to the citizens of an entire sub-continent and commercial entities want to reach out to those who have been excluded because of limited  technology, multispectral imaging-based biometrics is turning visions into  realities.

Comments

comments

Click to comment

Leave a Reply

Your email address will not be published.

Latest News

To Top