Biometrics: much more than just fingerprint and facial recognition

Jan Tissler

Recognizing people by their fingerprints or facial geometry has become commonplace. At the same time, researchers are developing other methods to recognize people by the characteristics of their body or their behaviour. This can be useful, but also alarms data protectionists.

It wasn't so long ago that TV series and films in the action genre had to have an eye scanner at the entrance to every serious underground secret laboratory. And the on-board computer of the Starship Enterprise can not only understand speech, but also recognize the speakers by their voice alone. How futuristic!

What is biometrics actually?

All of these examples fall into the category of "biometric recognition methods". They use unique, unchangeable and easily measurable characteristics to identify people. The methods can be roughly divided into two groups, which are referred to as physiological/behavioral, passive/active or static/dynamic.

At the same time, biometrics is one of those science fiction ideas that have become commonplace these days. It is very likely that the readers of this article own at least one device that they log into using their fingerprint or a facial recognition function. And smart speakers bring the enterprise feeling into your home for less than 50 francs.

Biometric procedures have become established because they are so practical and the necessary technology has also become cheaper. They sometimes replace other security mechanisms such as passwords or access codes, for example when a smartphone recognizes our face and unlocks automatically. In other cases, they supplement ID cards, for example, to provide even better protection against forgery.

However, some detection methods can also be used for surveillance, even without the knowledge of the person concerned. More on these and other points of criticism in a moment.

Physiological, passive methods

The aforementioned fingerprint and facial recognition methods are physiological biometric variants: they measure something on our body. The "eye scan" already mentioned also belongs in this category: depending on the method, details of the iris, the blood vessels in the eye or on the retina are measured. Speaking of blood vessels: the vein structure in the hand or foot is also suitable for this.

Other methods analyze the hand geometry, the structure of the hand lines or the nail bed pattern. Even the shape of the ears is unique enough to recognize us.

And it may seem a little strange, but people can also be identified by their body odor.

Last but not least, our genetic material in the form of DNA is rightly known as our "genetic fingerprint". However, this requires a sample for examination. In this respect, this information is not as easy to obtain as, for example, the geometry of our face.

Signature and handwriting belong in this category, but also overlap with behavior-based methods.

Behavior-based, active methods

"Active" methods look at how we behave or move. In the signature and handwriting example just mentioned, it is not just the end result that is evaluated: rather, it takes into account in detail how we write - the pressure exerted, the tempo, the rhythm. And it's not just about manual writing: The typing behavior on a keyboard is also unique enough to be used for recognition.

Another example is voice recognition, which ideally not only examines the pitch, but also how the person speaks: pauses, intonation or pronunciation are further measuring points. Even lip movements are so different from person to person that they can at least serve as an additional means of identification.

Last but not least is the individual gait: We often recognize people from a distance if they are very familiar to us. A computer can do the same.

What do data protectionists criticize?

If recognition methods such as facial geometry or gait are combined with the now ubiquitous security cameras, people's movement profiles can be created. The potential misuse of these technologies is therefore a major point of criticism from data protectionists. For them, the line between "active protection of the population" and "mass surveillance without cause" is crossed too quickly. In an earlier article, we explained why automated facial recognition is so vehemently criticized for this very reason.

Experts also warn that other sensitive data, such as a person's gender or ethnicity, can also be collected using such identification methods. Furthermore, not all methods are as accurate as one would wish, which means that innocent people can be targeted by the authorities.

It is also pointed out that biometric features cannot be changed if the stored information falls into the wrong hands. If a password data leak occurs, you can always create a new one. However, your own fingerprint will always remain your own fingerprint.

Of course, biometric data can be stored securely. Various types of encryption are used here, among other things, to make the information as unusable as possible for data thieves. At the same time, the systems should be better able to recognize when they are dealing with forgeries, such as manipulated fingerprints.

Closing words

Like almost every technology, biometric recognition methods have two faces: on the one hand, they help to secure access to buildings or devices more easily and conveniently. They can also support the work of the police. On the other hand, these methods and the information they collect can be misused.

Therefore, these techniques should not be demonized across the board. Rather, it is important to use them consciously and conscientiously.

Reading tips

Biometrics Institute: Types of biometrics
Biometrics Institute: FAQs
Biometric Today: 21 Types of Biometrics with Detail Explanation