In this work, the authors introduce a method of modifying the ensemble shapes of the ear to improve biometric performance.
The ear has gained popularity as a biometric feature due to the robustness of the shape over time and across emotional expression. Popular methods of ear biometrics analyze the ear as a whole, leaving these methods vulnerable to error due to occlusion. Many researchers explore ear recognition using an ensemble, but none present a method for designing the individual parts that comprise the ensemble. In the current project, the authors determined how different properties of an ensemble training system can affect overall performance. They show that ensembles built from small parts will outperform ensembles built with larger parts, and that incorporating a large number of parts improves the performance of the ensemble. (Publisher abstract provided)