Wavelet Based Representation for Online Signature Verification. Automatic Feature Selection vs. FHE’s Choice

PARODI, MARIANELA; GÓMEZ, JUAN CARLOS; LIWICKI, MARCUS; ALEWIJNSE, LINDA

Nara

Conferencia; 16th International Graphonomics Society Conference, IGS 2013; 2013

International Graphonomics Society

In this paper, the discriminative power of a set of features which seems to be relevant to signature analysis by Forensic Handwriting Experts (FHEs) is analysed and particularly compared to the discriminative power of automatically selected feature sets. This analysis could help FHEs to further understand the signatures and the writer behaviour. The coefficients in the wavelet decomposition of the different time functions associated with the signing process are used as features to model them. Two different signature styles are considered, namely, Western and Chinese, of one of the most recent publicly available Signature Databases. The experimental results are promising, specially for the features that seem to be relevant to the FHEs, since the obtained verification error rates are comparable to the ones reported in the state-of-the-art over the same datasets.