Biometrics is the science of recognizing individuals from their innate anthropometric (or zoometric in the case of animals) characteristics. It aims to offer high recognition accuracy while at the same time making the bearing of special identification equipment (such as cards) obsolete. The history of biometrics is long (e.g. fingerprint recognition) but it has received a huge amount of attention since about the year 2000, due to heightened security concerns as well as the application of visual computing techniques in the process.

A large number of anthropometric characteristics have been proposed, such as fingerprints, face, iris, voice and gait. We have been particularly active in 3D face recognition since the inception of the field.

Biometrics Research
3D Biometrics Achieviments

Automated Method for Human Face Modeling and Relighting with Application to Face Recognition, with Ioannis Kakadiaris (University of Houston), US patent 9.090.160.

The URxD 3D Face Recognition System took part in the US NIST Face Recognition Grand Challenge and Face Recognition Vendor Test 2006 where it achieved top accuracy in the Shape category.

3D Ear recognition can be achieved with methods very similar to 3D face recognition and we have shown that the combination of these 2 modalities can boost recognition performance while using the same capture device.

Unconventional biometric modalities are also being studied.

  • Transient biometrics makes sense for non-critical applications where subjects can offer transient biometric data with little hesitation. Transient means that the biometric is time-limited by nature and in this context we have studied the use of fingernail images.
  • ElectroEncephaloGraphy (EEG) signals is another biometric trait under study.


Sample publications:

Barbosa I.B., T. Theoharis & A.E. Abdallah, ‘On the use of fingernail images as transient biometric identifiers: Biometric recognition using fingernail images’, Machine Vision and Applications, 27, pp.65-76, 2016.

Perakis P., G. Passalis, T. Theoharis, I. A. Kakadiaris, ‘3D Facial Landmark Detection under Large Yaw and Expression Variations’ IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 35(7), pp. 1552-1564, July 2013.

Kakadiaris I.A., G. Passalis, G. Toderici, N. Murtuza, Y. Lu, N. Karampatziakis, and T. Theoharis, ‘3D face recognition in the presence of facial expressions: An annotated deformable model approach’, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 29(4), April 2007, pp. 640-649.