Ergodic HMM-UBM System for On-Line Signature Verification

  title={Ergodic HMM-UBM System for On-Line Signature Verification},
  author={Enrique Argones-R{\'u}a and David P{\'e}rez-Pi{\~n}ar L{\'o}pez and Jos{\'e} Luis Alba-Castro},
  booktitle={COST 2101/2102 Conference},
We propose a novel approach for on-line signature verification based on building HMM user models by adapting an ergodic Universal Background Model (UBM). State initialization of this UBM is driven by a dynamic signature feature. This approach inherits the properties of the GMM-UBM mechanism, such as minimizing overfitting due to scarcity of user training data and allowing a world-model type of likelihood normalization. This system is experimentally compared to a baseline state-of-the-art HMM… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 17 references

The multi-scenario multi-environment biosecure multimodal database (bmdb)

J. O. et. al.
IEEE Transactions on Pattern Analysis and Machine Intelligence • 2009
View 2 Excerpts

Universal Background Models for Dynamic Signature Verification

2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems • 2007
View 1 Excerpt

Local and global feature selection for on-line signature verification

Eighth International Conference on Document Analysis and Recognition (ICDAR'05) • 2005
View 1 Excerpt

Using adapted Levenshtein distance for on-line signature authentication

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. • 2004
View 1 Excerpt

Similar Papers

Loading similar papers…