The outer ear is an emerging biometric trait that has drawn the attention of the research community for more than a decade. The unique structure of the auricle is long known among forensic scientists and has been used for the identification of suspects in many cases. The next logical step towards a broader application of ear biometrics is to create automatic ear recognition systems.
This work focuses on the usage of texture (2D) and depth (3D) data for improving the performance of ear recognition. It compares ear recognition systems using either texture or depth data with respect to segmentation and recognition accuracy, but also in the context of robustness to pose variations, signal degradation and throughput.
The proposed ear recognition system is integrated into a demonstrator system as a part of a novel identification system for forensics. The system is benchmarked against a number of different datasets that comprise of 3D head models, mugshots and CCTV videos from four different perspectives. As a result of this work, limitations of current ear recognition systems are outlined and possible directions for future applied research are provided.
First external opponent: Prof. Dr. Mark Nixon, School of Electronics and Computer Science University of Southampton
Second external opponent: Prof. Dr. Luuk Spreeuwers, University of Twente
Internal opponent: Prof. Dr. Katrin Franke, Gjøvik University College. Alternate for Katrin Franke for the trial lecture and public defense was Basel Katt, Gjøvik University College
Head of the committee and its administrator: Prof. Dr. Patrick Bours, Gjøvik University College
Principal supervisor was Professor Christoph Busch, GUC
Secondary supervisor was Professor Stephen Wolthusen, GUC
Head of section for NISlab, Laura Georg, conducted the public defense.