Similarity Measure Functions For Strategy-Based Biometrics

Roman V. Yampolskiy, Venu GovindarajuZenodo 2008 · DOI

Abstract

Functioning of a biometric system in large part depends on the performance of the similarity measure function. Frequently a generalized similarity distance measure function such as Euclidian distance or Mahalanobis distance is applied to the task of matching biometric feature vectors. However, often accuracy of a biometric system can be greatly improved by designing a customized matching algorithm optimized for a particular biometric application. In this paper we propose a tailored similarity measure function for behavioral biometric systems based on the expert knowledge of the feature level data in the domain. We compare performance of a proposed matching algorithm to that of other well known similarity distance functions and demonstrate its superiority with respect to the chosen domain.
BibTeX
@inproceedings{yampolskiy2008similarity,
  author = {Roman V. Yampolskiy and Venu Govindaraju},
  title = {{Similarity Measure Functions For Strategy-Based Biometrics}},
  booktitle = {Zenodo},
  year = {2008},
  doi = {10.5281/zenodo.1076062},
}

Loading related content...

Figure