Checking identities quickly with face and iris capture using OneLook™ Gen2
Over the last few years, many government and private sector entities have been integrating biometric identification systems into their infrastructures. Biometrics are frequently used to unlock apps and devices, but they also help establish a person’s identity when applying for a passport, opening a bank account, boarding a plane, accessing services, or completing identity checks remotely.
Among the three most common biometric modalities of face, fingerprint, and iris recognition, the latter is considered the most stable. Unlike the face or hands, the iris is a protected internal organ, located behind the cornea and naturally shielded by our reflex to close our eyes. It is therefore less susceptible to damage or external alteration and can be used safely with children.
Iris recognition has been deployed at significant scale including, as part of the world’s largest biometric identification system, India’s Aadhaar program. Additionally, the technology is extensively deployed in border and travel environments, including at ports of entry in the United Arab Emirates. In Singapore, iris recognition is widely used as part of the country’s border clearance processes.
A camera captures photos of a person’s eyes and maps the unique iris pattern to verify their identity. State-of-the-art acquisition uses near-infrared illumination to reveal the details of the iris pattern, even in dark-colored irises. It also reduces reflections from the cornea, which is highly reflective under visible light but much less so in the near-infrared spectrum. The random texture of the iris is complex, distinctive, resistant to aging, and extremely difficult to replicate, enabling iris data to act as a unique identifier for each individual. The randomness of an iris pattern implies that it has very high dimensionality, supporting recognition decisions with a strong degree of confidence.
As previously stated, the iris is unique to each individual and remains stable over time. A well-known example is “Afghan Girl,” featured on the June 1985 cover of National Geographic. Eighteen years later, when photojournalist Steve McCurry set out to find her again, advanced iris recognition techniques developed by John Daugman confirmed that Sharbat Gula was indeed the same person.¹
Iris recognition can even distinguish between identical twins with remarkable accuracy, despite their identical DNA. Even the left and right eyes of the same person have different iris patterns. As a result, false acceptance rates are particularly low. Daugman’s IrisCode contains roughly 249 degrees of freedom, representing its effective discriminating capacity. By comparison, only around 33 bits of information would theoretically be sufficient to distinguish individuals within today’s global population. This substantial margin helps explain the exceptionally low false-match rates achievable with iris recognition.
Iris recognition analyzes only the texture patterns of the iris and is generally considered less sensitive to demographic variations than some other biometric modalities. Features surrounding the eye, such as eye shape or makeup, are not considered during verification in IDEMIA Public Security’s implementation of iris recognition. Since iris images are typically captured in infrared, eye color does not affect performance.
A person simply looks into a camera for a few seconds to complete the verification check. Glasses and corrective contact lenses typically do not interfere with iris recognition. The process consists of capturing a video image, which is non-invasive and inherently safe. Eyes are self-cleaning and image capture is performed without physical contact, making iris capture a hygienic option. Furthermore, people do not generally leave a physical or digital trace of their iris, which helps reduce spoofing and presentation attacks. Iris recognition systems can offer operational efficiency and scalability across many deployment environments. They have seamless interoperability between different hardware vendors and work well with a large range of applications.
Iris recognition systems have very low maintenance costs. They have seamless interoperability between different hardware vendors and work well with a wide range of applications.
IDEMIA Public Security developed OneLook™ Gen2: a non-intrusive solution designed for accurate iris and face capture at a distance, alongside rapid identity verification. Built for dynamic operational environments, OneLook™ Gen2 supports capture while users are moving and introduces advanced capabilities such as group capture and on-the-go identification.
Already supporting traveler clearance processes in Singapore as part of the ABCS program, with thousands of units currently deployed, OneLook™ Gen2 demonstrates IDEMIA Public Security’s continued commitment to innovation and leadership in biometric technologies.
IDEMIA Public Security’s algorithms rank top tier in the IREX 10 Identification Track of the National Institute of Standards and Technology benchmark assessing iris recognition performance for identification.
In addition, IDEMIA Public Security has developed a mobile biometric solution incorporating iris recognition capabilities in law enforcement and border control. The tablet supports high-speed authentication and multifactor verification through both on-device processing and secure connections to remote servers, helping authorities strengthen identity assurance and combat fraud.
Iris recognition continues to play an increasingly important role in trusted identity verification, especially in environments requiring high accuracy, operational efficiency, and strong resistance to fraud.
Latest News
Related Content