On Shape-Mediated Enrolment in Ear Biometrics

13 years 10 months ago

Download eprints.ecs.soton.ac.uk

Ears are a new biometric with major advantage in that they appear to maintain their shape with increased age. Any automatic biometric system needs enrolment to extract the target area from the background. In ear biometrics the inputs are often human head proﬁle images. Furthermore ear biometrics is concerned with the eﬀects of partial occlusion mostly caused by hair and earrings. We propose an ear enrolment algorithm based on ﬁnding the elliptical shape of the ear using a Hough Transform (HT) accruing tolerance to noise and occlusion. Robustness is improved further by enforcing some prior knowledge. We assess our enrolment on two face proﬁle datasets; as well as synthetic occlusion.

Banafshe Arbab-Zavar, Mark S. Nixon

Real-time Traffic