Biometrics analyze and measure specific biological characteristics of an individual to create a unique digital identifier which can be electronically stored and subsequently matched against to verify or determine a person’s identity.

Fingerprint Identification
Facial Recognition
Iris Scanning
Retinal Recognition
Hand Geometry
Vein Patterns
DNA Analysis
Other Biometrics
Fused Biometrics


Fingerprint Identification

Fingerprinting is the biometric that is by far the oldest (it’s been used within law enforcement for well over 100 years), and the best known to the general public. Fingerprint recognition uses the pattern of ridges, furrows, as well as the locations of ridge bifurcations and ridge endings to generate a code which is unlikely to be the same as anyone else’s. The codes are added to the individual’s record in the database so that a print taken subsequently can easily be run against it.

There are a variety of fingerprint readers available, many of which handle different environments, e.g. dirty/oily fingers, fingers where the fingerprint is no longer visible, wet fingers, 3D rather than 2D platens, etc.

Within the law enforcement community fingerprints are increasingly held within an Automated Fingerprint Identification System, or AFIS. An AFIS is a database which allows a print to be encoded and checked against existing records to determine whether they match any previously encoded prints. Rather than hold a single print, when an individual is arrested they will frequently have all ten fingers printed and encoded, with the details stored in the AFIS. This helps substantially in determining a match, particularly where only a partial print has been taken from a crime scene.

back to top

Facial Recognition

The example below shows the main steps in using facial recognition to identify an individual in a controlled environment:

Identification Steps:

  • Take a photo of the individual and encode it
  • Match the encoding against database and display possible matches
  • Select any matching image (in this case the closest match displayed at top left) and display the full record

Biometrics Consultancy
While different developers have used different approaches to developing facial recognition technology, the principle is the same as for other biometrics, i.e. the patterns within the object are identified and transformed mathematically into a code. In the case of a face, features such as the eyes and tip of the nose are used as anchor points, and the relative location of numerous other facial characteristics to them is determined. This information is then transformed into a digital string. This string can then be matched against pre-coded images in a database to determine if there’s a match. As the shot can be taken with a standard camera from a reasonable distance, facial recognition is the only biometric that does not require the cooperation or even knowledge of the individual for the process to work. However the implication of this is that the image is subject to external factors, particularly lighting and facial angles.

back to top

Iris Scanning

Iris patterns are, to all intents and purposes, unique to each individual. This makes them a particularly effective way to verify someone’s claimed identity, or to identify them if their identity is unknown. Iris scanning uses a special camera to illuminate and take a high-resolution shot of the iris. During the process the individual may be asked, automatically, to move their head to the optimal position for the shot. Once the shot has been taken the pattern is analyzed and encoded. This encoding will be unique to the individual, and can thus be matched against a database of previously-encoded individuals. Iris scanning is an ideal biometric where the individual is cooperative, the camera is no further than about two feet from them, and there is time to position the individual for the shot.

Biometrics Consultancy
The example above is of a High Speed, Fixed Focus, Two Eye Iris Recognition Camera, operating at 12-16″ (30-40 cm) from the subject.

back to top

Retinal Recognition

Retinal scanning analyses the layer of blood vessels at the back of the eye. The process involves using a low-intensity light source and an optical coupler to read the patterns. The user has to remove their glasses, place their eye close to the device, and focus on a certain point. They must keep their head still with their eye focused on the light for several seconds during which time the device will encode the retinal image and match this against the file record to verify their identity. This process takes about 10 to 15 seconds.

back to top

Hand Geometry

Hand geometry systems take a 3-dimensional view of the hand to determine overall metrics, finger length, height, etc. Up to 90 features can be identified. These are then processed using specific algorithms to produce a digital code. As with all other biometrics, this can be stored on the individual’s record and used for subsequent matches.

Biometrics Consultancy - Hand Geometry
back to top

Vein Patterns

Many biometrics are constrained in the way they can be used by the fact that there is no database record to match against unless the individual has agreed to have the biometric recorded in advance. This generally makes them more suitable for verification than identification.

The pictures below show a Fujitsu mouse incorporating vein pattern recognition, the part of the palm being used, and the resulting image which will be encoded.

Biometrics Consultancy - vein patterns
back to top

DNA Analysis

DNA is an abbreviation for deoxyribonucleic acid. It is a chromosome molecule which carries genetic coding unique to each person—the only exception being identical twins. DNA can be extracted from body tissue such as a strand of hair, semen, or blood and matched against DNA discovered at a crime scene or on a victim to scientifically implicate an accused. DNA is the most accurate biometric of all. Its downside is the length of time necessary to process the sample in the lab and determine whether there’s a match against a DNA database.

back to top

Other Biometrics

There are a range of different biometrics in addition to finger, face, iris, retina, handprint, and DNA. These include palm prints, keystrokes, signature verification, gait, and ear prints.

back to top

Fused Biometrics

The use of Fused Biometrics, where two or more biometrics are used together to verify an identity, can significantly increase the confidence factor of a match. For example, facial recognition cannot, by definition, distinguish between identical twins, while under certain circumstances fingerprints can be lifted and replicated. By using the two together each will offset the weakness of the other.

The use of Fused Biometrics, where two or more biometrics are used together to verify an identity, can significantly increase the confidence factor of a match. For example, facial recognition cannot, by definition, distinguish between identical twins, while under certain circumstances fingerprints can be lifted and replicated. By using the two together each will offset the weakness of the other.

back to top