Lumidigm is able to collect and process biometric images in a manner that makes fingerprint authentication and identification more robust, more inclusive and more reliable than other fingerprint sensors, which are vulnerable to a variety of conditions including the presence of topical contaminants, moisture, and bright ambient light. Simply stated, our sensors work where other technologies fail.

Lumidigm’s innovation is multispectral imaging, a technology that enables the measurement of fingerprint characteristics that are at and beneath the surface of the skin. This enhanced data capture mitigates traditional system vulnerabilities and makes Lumidigm sensors the most secure and convenient alternative for identity authentication.

Normal environmental and demographic real world conditions all represent significant challenges that have historically plagued the biometrics industry and have limited more widespread adoption. With multispectral imaging, these problems are solved. In major large-scale programs, pilot tests, field trials and evaluations, multispectral imaging from Lumidigm has proven to be the best technology in the biometrics industry.

Multispectral imaging also excels in liveness detection. Lumidigm technology is less susceptible to a wide range of well-known counterfeit attacks because its surface/subsurface capability can discriminate between real fingers and simulated fingerprint ridges. Multispectral imaging can quickly detect a fake by characterizing the subsurface data against the known characteristics of the human skin.

The ability to capture information from both the surface and subsurface of human skin forms the basis of Lumidigm’s distinct competitive advantage. Lumidigm was formed when a noninvasive glucose monitoring technology seemed to suggest a new approach to biometrics. We continue to direct resources into a strong research and development program that has already yielded a whole hand multi-biometric platform and a new direction in non-contact biometrics. Stay tuned!

The true test of any biometrics technology is not how it behaves in the lab or how it behaves under ideal conditions, but how it performs in the real world. For many years now, the promise of biometrics has not been fully realized in large part because performance in the lab is not representative of performance in the field.

When biometrics fail, for whatever reason, the technology becomes more of a barrier than an aide. The net result is user frustration, resistance to adoption, and an inability to justify costs. Regardless of which biometric technology is chosen, it must work reliably under real world conditions. The real world is not always ideal. The real world is wet, it is dry, it is not always clean and users are not all young office workers with great skin experienced at using the technology.

The Real World is Wet

It is typical for people going through security to be nervous — and to have sweaty hands. Multispectral imaging technology captures high-quality images even in wet conditions.

The Real World is Diverse

Biometrics work because people are unique — and yet diverse user populations are difficult for many fingerprint biometrics systems to handle. Multispectral imaging from Lumidigm is up to the challenge.

The Real World is Dry

Dry fingertips are common, caused by anything from climate conditions or natural skin characteristics to frequent hand-washing or air travel. Multispectral imaging technology captures high-quality images even when fingers are dry.

The Real World is Rough

People don’t have time to wash and lotion their hands when they use a fingerprint sensor. Multispectral sensors take you as you are — at the office, auto shop, or construction site.

The more effective solution was based on using 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 net result is that Lumidigm sidesteps the problems that conventional technologies face in real world conditions. Additionally, our subsurface capability allows us to discriminate a real finger from an imposter or “spoof” fingerprint, making Lumidigm a leader in liveness detection.

The Technology

Multispectral imaging looks at and beyond the skin surface to the subsurface foundation of the fingerprint ridges. Different wavelengths of visible light interact with the skin in different ways, enabling significantly enhanced data capture. The fingerprint pattern on the surface echoes the subsurface structures from which they arose during development. Multispectral imaging exploits the dependent relationship between surface and subsurface fingerprint patterns; subsurface data collected by multispectral imaging technology supports and augments surface data to create the highest-quality fingerprint image available.

Schematic of a multispectral imaging fingerprint biometric sensor

The basic operation of the multispectral sensor is straightforward. The sensor consists of two main components: a light source, which provides the light to illuminate the finger resting on a platen; and an imaging system, which images this region of the platen onto a digital imaging array. While these components are similar to those of a conventional optical fingerprint sensor, the configuration of the multispectral sensor is expressly designed to avoid the optical phenomenon of total internal reflectance (TIR) because it depends on unobstructed and complete contact between the fingerprint sensors and the platen to work.

The multispectral illumination system consists of a source of multiple illumination wavelengths rather than the quasi-monochromatic illumination commonly used for TIR imaging. Linear polarizers are used in the illumination and detection portions of the sensor. The polarizers are arranged in an orthogonal configuration (a.k.a. polarizer-analyzer) to emphasize the light that penetrates the surface of the skin and undergoes multiple scattering events before emerging from the skin toward the image array.

Surface fingerprint ridges form
when collagen pushes between the blood vessels. Credit: Simone Sangiogi, 2006.

Skin physiology

To more fully understand the significance of this technology’s subsurface imaging capability, it may help to examine the nature of how a human fingerprint is created. 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.

Unfortunately, conventional optical fingerprint sensors are easily circumvented. Based on total internal reflectance (TIR), they capture only the image of the fingerprint ridge surfaces that come into contact with the sensor. These ridges are easy to imitate using common household products and ingredients.

A variety of materials, from the inexpensive to the very sophisticated, can be used to circumvent traditional fingerprint identification systems. Some of these materials are so thin and colorless that they can even be used, undetected, in access control environments that have trained attendants. For example, a gummy bear candy that costs a few cents can make a very accurate fingerprint that will “spoof” a traditional fingerprint imaging device.

Lumidigm’s multispectral imaging technology uses multiple illumination wavelengths rather than the monochromatic illumination used in TIR imaging. In addition, polarizers may be used to emphasize the light that penetrates the surface of the skin and undergoes multiple scattering events before emerging from the skin toward the imaging array. This ability to detect subsurface features of the fingerprint enables Lumidigm technology to detect spoofs.

Lumidigm’s multispectral imaging technology can detect living flesh from non-living flesh or other organic or synthetic materials. The figure at the right shows an analysis of the surface and sub-surface spectral differences between a living finger and a prosthetic. These differences between the spectral characteristics are known and can be used to detect spoofs.

Further, since multispectral imaging technology observes the internal structures that conform to and dictate the external fingerprint ridge patterns, internal details can be compared to the surface pattern. Multispectral imaging technology from Lumidigm can verify that the “internal fingerprint” matches the external one.

Lumidigm liveness detection is built from cutting-edge machine learning algorithms. Using these algorithms and the wealth of information available from multispectral fingerprint images, Lumidigm’s liveness detection capabilities can be updated if new spoofs are identified. Unlike any other fingerprint technology, this “learning” capability allows Lumidigm fingerprint sensors to keep up with new threats.

Lumidigm’s multispectral imaging technology is hard to fool. The inexpensive and readily-available films and prostheses that easily defeat conventional fingerprint devices are rendered ineffective against Lumidigm technology.

Some of the R&D was performed under a range of different United States federal government programs, and some of the R&D was performed for commercial partners. Many of these development efforts led to new features and functionality in our products and those of our partners.

In the course of R&D efforts, Lumidigm has developed a significant patent portfolio, which today comprises of 14 U.S. patents granted, 16 foreign patents granted, and many more filings pending in the U.S. and internationally. Although these patents were developed to support Lumidigm’s product portfolio, we are also willing to discuss licensing of portions of our intellectual property under suitable terms.

Periodically Lumidigm publishes whitepapers on technologies that are in early-stage development. If any of these technologies are of interest for your application or if you have a commercial requirement that could benefit from any of Lumidigm’s core competencies, please click the “R&D Inquiries” button to submit a question or request by email. We will be happy to discuss your requirements and see if we can help solve your most vexing technical problems.

• Whole Hand Multimodal Biometric
• Non-Contact Fingerprint Sensor