Trial raises questions over biometric technology

The government has published the results of a major trial of its biometric technology, showing significant failure rates and particular problems for disabled people in registering their identity.

And there are also doubts over the accuracy of the scheme, with figures showing that even the most effective technology failed to match a person to their recorded identities in four per cent of cases.

A trial involving more than 10,000 people has been conducted as officials and experts examine how the move towards secure identity cards could be implemented in practice.

The findings of the trial were released by the Home Office on Wednesday, providing more information on the use of three different biometric technologies that are being considered for use with ID cards.

The three forms of identity being electronically recorded were fingerprinting, iris recognition and facial recognition.

Facial recognition appeared to be most successful for registering, while fingerprints posed more problems.

But in subsequent attempts to match the recorded details back to the individuals, both fingerprints and facial recognition performed poorly, while iris recognition achieved a higher 96 per cent success rate.

However, there was a significant failure rate with each of the forms of technology.

And disabled people in particular faced a higher failure rate when it came to completing the tests.

Testing times

The trial study was not, however, designed primarily to test the technology.

Instead, the report said the aim was "to test and measure the processes around the recording and verification of biometrics through a simulation of an application process".

"The trial results... are specific to the particular software and hardware configurations used in the trial".

The trial databases were pre-loaded with 118,000 irises and one million fingerprints.

"Although the findings give results for each of the three biometrics, comparisons should be made within each biometric and not between biometrics," added the study.

"The trial was set up with no attempt to compare the accuracy of the different biometrics."

Facial recognition

The report revealed that with facial recognition, there was a near 100 per cent success rate for enrolment, falling to 98 per cent for disabled people.

Analysis showed that the factors which most affect the success rate are environmental, in particular the lighting conditions at different locations.

Maintaining the correct position for facial biometric enrolment was a problem for some disabled participants with a physical impairment or with learning disabilities, added the study.

Of the three biometric technologies, however, the lowest verification success rate occurred with the face.

The success rates were 69 per cent, falling to 48 per cent for disabled participants.

Changes in a participant's appearance also caused verification to fail.

Iris recognition

The study said that a majority of participants in all sample groups successfully enrolled their irises.

There were success rates of around 90 per cent, dropping to 61 per cent for disabled participants.

Iris enrolment success also varied according to the participant’s ethnic group and age.

Asian and white participants had higher success rates than black participants.

However, iris recognition was the most successful technology when it came to the verification of identity.

The success rate was 96 per cent, "significantly higher" than that the 91 per cent for disabled participants.

While many participants who wore glasses and who verified on iris did not have a problem, a small number of participants with glasses failed verification when they wore their glasses and passed when they took their glasses off, said the report.

Fingerprints

The majority of participants in all sample groups successfully enrolled their fingerprint biometric, with success rates of nearly 100 per cent and 96 per cent for disabled participants.

However,  participants achieved successful verification on just 81 per cent of occasions, and 80 per cent for disabled participants.

One of the factors influencing failure was said by the experts to be that the single fingerprint device used for verification occasionally did not record sufficient detail from the fingers.

Less concern

Following their participation in the trial, the testers were asked about their attitude towards the concept of biometrics as part of an individual’s passport, as well as the general concept of biometrics and their potential contribution to key national questions.

"Whilst the majority of participants were 'not very' or 'not at all' concerned about having their biometrics recorded prior to enrolment, there was more concern felt within disabled participants and in particular for the iris biometric," said the report.

"Across all three biometrics and all three groups, the total number of participants 'fairly' or 'very' concerned about having their biometrics recorded after enrolment dropped when compared with pre-enrolment.

"The majority of participants felt biometrics would help with passport security, preventing identity fraud, preventing illegal immigration and are not an infringement on their civil liberties."