Share Email Print
cover

Proceedings Paper

Ensemble training to improve recognition using 2D ear
Author(s): Christopher Middendorff; Kevin W. Bowyer
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

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.

Paper Details

Date Published: 5 May 2009
PDF: 12 pages
Proc. SPIE 7306, Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI, 73061Z (5 May 2009); doi: 10.1117/12.818177
Show Author Affiliations
Christopher Middendorff, Univ. of Notre Dame (United States)
Kevin W. Bowyer, Univ. of Notre Dame (United States)


Published in SPIE Proceedings Vol. 7306:
Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI
B.V.K. Vijaya Kumar; Craig S. Halvorson; Šárka O. Southern; Salil Prabhakar; Arun A. Ross, Editor(s)

© SPIE. Terms of Use
Back to Top