Normalised Equi-angular Recognition Technique of Human Ear Signatures for use in Biometrics Applications
The human ear offers relatively promising features that can be used in biometrics applications. Hence, the aim of this work is to assess the validity of using human ear recognition in real biometrics applications. A proposed system for ear recognition is presented and experimentally tested. This employs equiangular ear signatures, in which the Cross Correlation Function (CCF) is employed to find the best angular match and apply angular shift to earsignatures accordingly. The image scene size problem is overcome by using normalised values of the earsignatures. Rearrangements of the ear-signature data set are applied using equiangular steps, where equally stepped size angles are used to acquire signature data sets of the same, fixed length array points; hence comparison and point to point matching can be readily applied. Two parameters to assess the signature similarities, namely error energy and Paretos-based indicator, are proposed and used in this investigation. Results show the validity of the approach and encourage the adopting of the developed technique in real applications.
component Human ear recognition Ear biometrics Ear matchings
Ghassan A. Al-Kindi Brian C. Lovell
Faculty of Engineering Sonar University Sonar, Oman School of Information Technology and Electrical Engineering, University of Queensland Brisbane, Aust
国际会议
2011 International Conference on Security Science and Technology(ICSST 2011) (2011年安全科学与技术国际会议)
重庆
英文
111-115
2011-01-21（万方平台首次上网日期，不代表论文的发表时间）