The study of biometrics in the IT technology area relates to authentication techniques – which means Keyless Entry Systems‘am I who I say I am?’

Biometrics looks for biological characteristics, for example a fingerprint that can be automatically referenced and validated from a database of fingerprints.

In over 140 years of fingerprint comparison worldwide, no two fingerprints have ever been found to be alike, including identical twins! And, our fingerprints remain unchanged throughout our life.

It’s all in the detail

Fingerprint identification involves comparing the pattern of ridges and furrows on the fingertips, as well as the minutiae points (ridge characteristics that occur when a ridge ends or splits into two) of a specimen print with a database of prints on file.

Fingerprint scanners use these features (pattern of ridges and furrows) to analyse the unique fingerprints of the users.

The processing has three primary roles: enrolment, searching and finally verification or acceptance of the fingerprint.

The capturing of the fingerprint image from the sensor is critical. This is because when a user places their finger on the scanner it has to be consistent.

The lighting needs to be right and the scanner has to be up to the task or the scan will be rejected.

Once your finger has been scanned the verification process has several techniques to match fingerprints, these include:

  • Correlation-based matching – in correlation-based fingerprint matching, the template and query fingerprint images are spatially correlated to estimate the degree of similarity between them.
  • Minutiae-based matching – each minutia is represented by a fixed number of attributes such as the location, orientation, type and other local information.
  • Pattern/Ridge feature-based matching – using the ridge features of your fingerprint it analyses the differences between the two and compares it to the database.

Want to know more?

Here’s how the process works with a simple optical scanner.

  1. A row of LEDs scans bright light onto the locks scanner surface that your finger is pressed onto.
  2. The quality of the image will vary according to how you’re pressing, how clean your fingers are, how clean the scanning surface is, the light level in the room and so on.
  3. Reflected light bounces back from your finger, onto a charge-coupled device (CCD) or complementary metal–oxide–semiconductor (CMOS) image sensor.
  4. The longer this image-capture process takes, the brighter the image formed on the image sensor.
  5. An algorithm tests whether the image is too light or too dark. If so, an audible beep or LED indicator alerts the user to try the scan again
  6. If the image is acceptable, another algorithm tests the level of detail, depending on the scan function outlined above (correlation, minutiae or ridged), typically by counting the number of ridges and making sure there are alternate light and dark. If the scanned image fails this test, the user will get an audible beep or LED indicator to try the scan again.
  7. If the image passes the two tests, the scanner signals that the image is recognized by the lock and the lock will retract the dead locks.