A novel ray analogy for enrolment of ear biometrics

The ear is a maturing biometric with qualities that give it superiority over other biometrics in a number of situations; in particular the ear is relatively immune to variation due to ageing. Successful ear biometrics rely upon a well enrolled dataset, with ears normalised for position, scale and rotation. We present a novel ear enrolment technique using the image ray transform, based upon an analogy to light rays. The transform is capable of highlighting tubular structures such as the helix of the ear and spectacle frames and, by exploiting the elliptical shape of the helix, can be used as the basis of a method for enrolment for ear biometrics. The presented technique achieves 99.6% success at enrolment across 252 images of the XM2VTS database, displaying a resistance to confusion with hair and spectacles. These results show great potential for enhancing many other already existing enrolment methods through use of the image ray transform at a preprocessing stage.