Ensemble training to improve recognition using 2D ear

Christopher Middendorff; Kevin W. Bowyer

doi:10.1117/12.818177

5 May 2009 Ensemble training to improve recognition using 2D ear

Christopher Middendorff, Kevin W. Bowyer

Proceedings Volume 7306, Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI; 73061Z (2009) https://doi.org/10.1117/12.818177
Event: SPIE Defense, Security, and Sensing, 2009, Orlando, Florida, United States

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.

Citation Download Citation

Christopher Middendorff and Kevin W. Bowyer "Ensemble training to improve recognition using 2D ear", Proc. SPIE 7306, Optics and Photonics in Global Homeland Security V and Biometric Technology for Human Identification VI, 73061Z (5 May 2009); https://doi.org/10.1117/12.818177

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available