Multiple classifier combination for face-based identity verification

Czyz, J.;Kittler, J;Vandendorpe, Luc
(2004) Pattern Recognition — Vol. 37, n° 7, p. 1459-1469 (2004)

Files

pdfdocument.pdf
  • Restricted Access
  • Adobe PDF
  • 222.73 KB
Request a copy

Details

Authors
Abstract
When combining outputs from multiple classifiers, many combination rules are available. Although easy to implement, fixed combination rules are optimal only in restrictive conditions. We discuss and evaluate their performance when the optimality conditions are not fulfilled. Fixed combination rules are then compared with trainable combination rules on real data in the context of face-based identity verification. The face images are classified by combining the outputs of five different face verification experts. It is demonstrated that a reduction in the error rates of up to 50% over the best single expert is achieved on the XM2VTS database, using either fixed or trainable combination rules. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Czyz, J., Kittler, J., & Vandendorpe, L. (2004). Multiple classifier combination for face-based identity verification. Pattern Recognition, 37(7), 1459-1469. https://doi.org/10.1016/j.patcog.2004.01.008 (Original work published 2004)