P. Mautner, V. Matoušek, T. Maršálek, and M. Šoule
biometrics, signature verification, neural network, SOM,
BiSP, fast wavelet transform
The Kohonen Self-organizing Feature Map (SOFM) has
been developed for the clustering of input vectors and has
been commonly used as unsupervised learned classifiers.
In this paper we describe the use of the SOFM neural net
work model for signature verification. The biometric data
of all signatures were acquired by a special digital data ac
quisition pen and fast wavelet transformation was used for
feature extraction. Some of the authentic signature data
were used for training the SOFM signature verifier. The ar
chitecture of the verifier and achieved results are discussed
here and ideas for future research are also suggested.