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 this work, we introduce a
method of modifying the ensemble shapes to improve performance. We determine how different properties of
an ensemble training system can affect overall performance. We 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.