Biometrics

There is a growing interest in biometric authentication, for use in such application areas as:

  • National ID cards
  • Airport security
  • Surveillance
  • Site access.
Biometrics that could potentially be used in these situations include:
  • Fingerprints.
  • Hand geometry.
  • Iris.
  • Retina.
  • Gait.
  • Voice.
  • Signature.
  • Vein patterns.
  • Face.
Face recognition methods generally fall into four main categories:
  • Neural networks.
  • Feature analysis.
  • Graph matching.
  • Information theory.

Face recognition has a number of advantages over some of the other biometrics used.  Firstly, it is non-intrusive.  Whereas many biometrics require the subjects co-operation and awareness in order to perform an identification or verification, such as looking into an eye scanner or placing their hand on a fingerprint reader, face recognition could be performed even without the subject's knowledge.  Secondly, the biometric data used to perform recognition is in a format that is readable and understood by humans.  This means that a potential face recognition system can always be backed up and verified by a human.  For example, supposing a person was falsely denied access to a site by a face recognition system.  That decision could easily be corrected by a security guard that would compare the subject's face with the stored image, whereas this would not be possible with other biometrics such as iris.  Other advantages are that there is no association with crime as with fingerprints (few people would object to looking at a camera) and many existing systems already store face images (such as police mug shots).


The term face recognition encompasses three main procedures.  The preliminary step of face detection (which may include some feature localisation) is often necessary if no manual (human) intervention is to be used.  Many methods have been used to accomplish this, including template based techniques, motion detection, skin tone segmentation, principal component analysis and classification by neural networks.  All of which present the difficult task of characterizing “non-face” images.  Also, many of the algorithms currently available are only applicable to specific situations: assumptions are made regarding the orientation and size of the face in the image, lighting conditions, background and subject's co-operation.  The next procedure is verification.  This describes the process by which two face images are compared, producing a result to indicate if the two images are of the same person.  Another (often more difficult) procedure is identification.  This requires a probe image, for which a matching image is searched for in a database of known people, thus identifying the probe image as a specific person.
 

Document Actions
Latest News

THE award

ACAG Wins Top Award

find out more

OPPORTUNITIES

Globe

PHD 

STUDENTSHIPS

Log in


Forgot your password?
INTRANET

Group Pages

 

Please refer to the legal disclaimer covering content on this site.