- What Makes This Book Different?
- The Structure of This Book
- Everything You Need to Know about Biometrics to Understand the First Three Chapters
- Who Should Read This Book?
- Conclusion
This chapter is from the book
This chapter is from the book
This chapter is from the book
Everything You Need to Know about Biometrics to Understand the First Three Chapters
Biometrics, like any other technology, have their own nomenclature and acronyms. While these are covered in great detail throughout the book, below is a primer on basic biometric technology and terminology to get you started. What is covered here will be just enough to get you going.
What Is a Biometric?
As mentioned earlier, a biometric is a physical or psychological trait that can be measured, recorded, and quantified. By doing this, we can use that trait to obtain a biometric enrollment. This way, we can say with a degree of certainty that someone is the same person in future biometric authentications based on their previous enrollment authentications. The degree of certainty will be discussed in greater detail in Section 2.
Enrollment, Template, Algorithm, and Verification
In a biometric system, a physical trait needs to be recorded. The recording is referred to as an enrollment. This enrollment is based on the creation of a template. A template is the digital representation of a physical trait. The template is normally a long string of alphanumeric characters that describe, based on a biometric algorithm, characteristics or features of the physical trait. The biometric algorithm can be viewed as the recipe for turning raw ingredients—like a physical trait—into a digital representation in the form of a template. The algorithm will also allow the matching of an enrolled template with a new template just created for verifying an identity, called a live template. When a stored template and a live template are compared, the system calculates how closely they match. If the match is close enough, a person will be verified. If the match is not close enough, a person will not be verified.
FAR, FRR, and FTE
As described above, when a stored and live template are compared, they either match or they do not match. What happens if it is not you who is trying to match to your template? In this case, someone else is trying to verify as you. If that person were to match as you, it would be classified as a false acceptance. The probability of this happening is referred to as the false acceptance rate, or FAR. The FAR normally states, either in a percentage or a fraction, the probability of someone else matching as you. Thus, the lower the probability, the less likely a match. That means that a match needs to be closer to the original template. As the closeness of a match increases, what does this mean for you when you try to verify as yourself? It means that your live template must match even closer to the enrolled template. If you fail to match against your own template, then you have been falsely rejected. The probability of this happening is referred to as the false rejection rate, or FRR. Thus, the higher the probability of false rejection, the greater the likelihood you will be rejected.
Lastly, when you are new to a biometric system and need to enroll but cannot, this is called a failure to enroll, or FTE. The FTE normally states, either in a percentage or a fraction, the possibility of someone failing to enroll in a system. A discussion in a later chapter will cover the relationship among FAR, FRR, and FTE as it relates to choosing a biometric device and algorithm.