Biometric Systems
Introduction
What Question Does It Ask?
Biometric systems recognize a person by physical and behavioral traits such as face, fingerprint, iris or voice. The course covers extracting a template from a sample, matching two templates and accepting or rejecting by a threshold; security and privacy are an inseparable part of that decision.
At a glance
matching and verification
face, fingerprint, iris, voice
identity decision
FAR, FRR, EER
medium
few samples per person
Introduction
A Short History
Galton publishes "Finger Prints": fingerprints are shown to be unique and permanent.
Scotland Yard starts using fingerprints with the Henry classification system.
Turk and Pentland publish eigenfaces for face recognition.
Daugman publishes his iris recognition method, the basis of today's iris systems.
Fingerprint sensors (Touch ID) start to spread in smartphones.
DeepFace and the deep networks after it approach human level in face verification.
The Course
Core Concepts
Extracting a template from a person's sample and storing it.
The feature vector stored instead of the raw image.
"Is this person who they claim to be?"
"Which enrolled person is this?"
False accept and false reject rates; the threshold trades them off.
The point where both errors are equal; comparing systems.
Catching attacks with photos, masks or fake fingers.
Combining face with voice, or fingerprint with iris.
The Course
A Typical Workflow
The Course
What Does the Course Cover?
- Biometric systems: enrol, verify, identify
- Measuring performance: FAR, FRR, ROC, DET, EER
- Fingerprints: preprocessing, minutiae, matching
- Face detection and alignment
- Face recognition: eigenfaces, LBP, deep embeddings
- Iris: segmentation, Daugman's code, Hamming distance
- Speaker verification from voice
- Behavioural biometrics: signature, gait, keystrokes
- Multimodal biometrics and score fusion
- Presentation attacks and liveness detection
- Template protection and cancellable biometrics
- Large-scale identification, indexing and standards
Skills you will gain
A typical semester; the order and coverage vary between universities.
Try It
Who Should the Gate Let In?
A face recognition gate gives each person a similarity score between 0 and 1; if the score passes the threshold, the gate opens. Move the threshold or pick a scenario to see the trade-off between accepting impostors and rejecting genuine users.
Context
Prerequisites
Courses worth knowing before this one, and why they are needed.
| Course | Why it is needed |
|---|---|
| Pattern Recognition | matching, verification and identification |
| Computer Vision | face recognition |
| Programming | reading images and working with vectors in Python |
| Data Structures | indexing to scan millions of templates quickly in 1:N search |
Context
Are You Ready for This Course?
Ask yourself; for every "no", the right-hand column shows where to start.
| Ask yourself | If not, start with |
|---|---|
| Can you load an image, crop it and convert it to greyscale? | Image Processing |
| Can you explain a classifier's ROC curve and false positive rate? | Pattern Recognition |
| Can you compute the cosine similarity between two vectors? | Linear Algebra |
| Can you process a folder of images with NumPy arrays in Python? | An intro programming course, then a short NumPy tutorial |
Context
Neighbouring Courses
Overlap
Overlapping Courses
| Relation | Course | Shared ground |
|---|---|---|
| application | This course applies the methods of Pattern Recognition | matching, verification and identification |
| application | This course applies the methods of Computer Vision | face recognition |
| shares methods | Shares methods with AI in Cybersecurity | authentication, spoof detection |
Differences
Where It Differs (1/2)
| Criterion | Biometrics | Pattern Recognition | Computer Vision |
|---|---|---|---|
| Core question | How is a person recognized from their face, fingerprint or voice? | How do we decide from measurements which class an object belongs to? | How does a computer understand what is in an image or a video? |
| Approach | matching and verification | statistical decision theory | extracting meaning from images |
| Input | face, fingerprint, iris, voice | measurement or feature vector | image or video |
| Output | identity decision | class label | label, box, depth, 3D structure |
| Success measure | FAR, FRR, EER | classification error | accuracy, mAP, IoU |
| Math load | medium | medium-high: probability, linear algebra | high: geometry, linear algebra |
| Data needs | few samples per person | labeled examples | many labeled images |
- Pattern Recognition: Pattern recognition assigns a sample to classes; biometrics recognizes people, with as many classes as people, always growing.
- Computer Vision: Computer vision tries to understand everything in an image; biometrics is a narrow, security-focused task that asks only identity.
Differences
Where It Differs (2/2)
| Criterion | Biometrics | AI in Cybersecurity | Speech and Audio |
|---|---|---|---|
| Core question | How is a person recognized from their face, fingerprint or voice? | How does AI catch attacks, and how is it attacked itself? | How are words, speakers and events extracted from a sound wave? |
| Approach | matching and verification | security knowledge plus ML | acoustic signal and language model |
| Input | face, fingerprint, iris, voice | network traffic, logs, files | audio waveform |
| Output | identity decision | alert, class, risk score | text, speaker, sound event |
| Success measure | FAR, FRR, EER | detection rate, false alarm rate | word error rate (WER) |
| Math load | medium | medium | medium-high |
| Data needs | few samples per person | imbalanced and constantly changing | many hours of recordings |
- AI in Cybersecurity: AI in cybersecurity catches attacks; biometrics is authentication itself and must resist spoofing attacks.
- Speech and Audio: Speech recognition finds what was said; speaker recognition, a biometric, finds who said it.
Practice
Applications
Unlocking devices by face and fingerprint.
Automated gates using e-passport photos.
Searching crime-scene prints in databases.
Remote customer verification, payment approval.
Building entry and staff time records.
Preventing duplicates in national ID systems.
Practice
Risks and Ethics
Real-time face recognition in public spaces makes it possible to track everyone without asking; many countries restrict it by law.
In the US there are documented cases of innocent people being detained on the strength of a false face recognition match.
Face or fingerprint data collected for door access can be reused for other purposes; GDPR and similar laws treat it as special data.
Holding millions of templates in one place exposes everyone at once; the 2015 US OPM breach leaked 5.6 million fingerprints.
In depth: Explainable AI and AI Ethics.
Practice
Tools and Datasets
Tools and libraries
Well-known datasets
Practice
Common Misconceptions
| Common belief | In fact |
|---|---|
| Biometric systems make no mistakes. | Every system makes false accepts and false rejects; the threshold chooses between them. |
| Biometric data can be changed like a password. | A face or fingerprint cannot be changed; a leaked template is a permanent risk, so templates need protection. |
| Accuracy is the same for everyone. | Performance can vary with age, skin tone and sensor; evaluation is done per group. |
| A match means the person is there. | Presentation attacks use photos, masks or recorded voice; liveness detection is needed. |
Next Steps
After This Course
Courses that build on or extend this one
Related careers
Next Steps
Further Reading
- Jain, Ross and Nandakumar, Introduction to Biometrics, Springer, 2011.
- Li and Jain (eds.), Handbook of Face Recognition, 2nd ed., Springer, 2011.
- Maltoni, Maio, Jain and Feng, Handbook of Fingerprint Recognition, 3rd ed., Springer, 2022.
- Daugman, "How Iris Recognition Works", IEEE Transactions on Circuits and Systems for Video Technology 14(1), 2004.