A comparison of fingerprint recognition systems

With so many different types of fingerprint recognition system in the marketplace, how do you find the right biometric system for your business? Read on to find out more about how the main systems compare.

The first automatic biometric fingerprint recognition

Even though fingerprints were first used over 100 years ago to convict a criminal, the first generation of automatic fingerprint identification systems did not become available until the 1970s. Early biometric devices were primarily used in forensics and law enforcement. These systems were limited in their performance and interconnectivity. They were usually bulky, slow and required supervision during operation.

The second generation of biometric devices brought some improvements but was still expensive and had high failure rates. Finger preparation was required prior to scanning as sensors were not very advanced, and optical sensors were only available in recognition systems. These systems tended to be used for high-security computing and building access control.

Modern systems

Modern biometric systems are very sophisticated, using many different techniques to capture, store and process data. They can detect liveness, do not require manual calibration, are fast and integrate easily into computer systems. Mass production induced by an increasing adoption rate has lowered costs and encouraged their usage. Billions of people now use fingerprint authentication systems daily.

Human fingerprints are detailed, nearly unique, difficult to alter and durable over the lifetime of an individual, making them very suitable as a marker of personal identity. A wide range of fingerprint recognition systems, therefore, exists for use in high-security applications and automated identification. The convenience, security and performance of fingerprint recognition systems have made them the most widely used biometric system. There are four main types of fingerprint reader currently on the market:

Optical readers are the most common type of fingerprint readers. They acquire an optical image (essentially a photograph) and use algorithms to detect unique patterns on the surface of the fingerprint. Optical readers are cheap but unreliable, sensitive to contamination, bulky, insecure and very easy to spoof because they only capture 2D images.

Capacitive readers use arrays of tiny capacitor circuits to collect data about a fingerprint. Once captured, the data can be analysed to look for unique fingerprint attributes, which can be saved for comparison. Capacitive readers are much tougher to fool than an optical reader. The results can’t be replicated with an image and are incredibly tough to fool e.g. by using a prosthetic, as unconventional materials will record slightly different changes in charge at the capacitor. Capacitive readers are more costly than optical readers but offer excellent image quality, liveness detection, are small and compact, fast, durable and far less likely to be spoofed.

Ultrasound readers are a recent development. They use high-frequency sound waves to penetrate the epidermal (outer) layer of the skin reading the fingerprint on the dermal skin layer, which eliminates the need for a clean, unscarred surface. They are far more expensive than optical or CMOS readers and have yet to appear in commercial settings i.e. within mobile phones because they are slow, power-hungry, bulky and require a lot of processing power.

Thermal readers sense, on a contact surface, the difference of temperature in between fingerprint ridges and valleys. Thermal fingerprint readers have many disadvantages such as higher power consumption and performance that depends on the environment temperature.

Quality of images is key

The quality of an image generated by a fingerprint sensor is a fundamental and important parameter. High-quality images allow for a smaller sensor and a lower cost since more details are captured per area unit. The image quality depends on the sensors ability to detect weak signals and filter out undesired noise, without requiring too long and cumbersome exposure to the fingerprint. Ultrasonic and active capacitive sensors provide very high-quality images because they read the dermal skin layer, rather than the epidermal layer.

Different metrics can be used to rate the performance of a biometric factor, solution or application. The most common performance metrics are the False Acceptance Rate (FAR) and the False Rejection Rate (FRR).

 

FAR AND FRR

The False Acceptance rate (FAR) is the probability that the system incorrectly authorises a non-authorised person, due to incorrectly matching the biometric input with a template. The FAR is normally expressed as a percentage, following the FAR definition this is the percentage of invalid inputs which are incorrectly accepted.

The False Rejection Rate (FRR) is the probability that the system incorrectly rejects access to an authorised person, due to failing to match the biometric input with a template. The FRR is normally expressed as a percentage, following the FRR definition this is the percentage of valid inputs which are incorrectly rejected. FAR and FRR is very much dependent on the biometric factor that is used and on the technical implementation of the biometric solution.

FRR is strongly person dependent to the point at which a personal FRR can be determined for everyone. FRR might increase due to environmental conditions or incorrect use, for example when using dirty fingers on a fingerprint reader. Mostly FRR lowers when a user gains more experience in how to use the biometric device or software.

FRR and FAR are both important when comparing different types of fingerprint scanners but its application will dictate which metric is of more importance. For example, if a fingerprint scanner is used for physical access control, the objective of the application is to disallow access to unauthorised individuals under all circumstances. It is clear that a very low FAR is needed for such an application, even if it comes at the price of a higher FRR.

Capacitive and ultrasonic scanners are the most cost-efficient, flexible, secure and convenient technologies currently available. As market leaders, innovators, manufacturers and installers of fingerprint and vein technology systems, Almas Industries are well placed to help businesses with all aspects of biometric control and security. Our systems are effective, highly secure and easy to operate. You can arrange your free, no obligation security survey by calling us on 0333 567 6677. If you prefer, you can always send a confidential email via [email protected]