Online Signature Classification and its Verification System

This work presents experimental results on online recognition of handwritten signature. The system makes use of dynamic data such as trajectory, pen velocity, pen pressure, pen azimuth, and pen altitude collected at the time of signing. In order to evaluate the effectiveness of the system several experiments are carried out. Online signature database from signature verification competition (SVC) 2004 is used during all of the tests. The first series of experiments show the classification process - the questioned signature is compared with reference samples and the destination class is determined from the most similar reference. The second part involves verification - the questioned signature is recognized as belonging to a particular individual when the distance between the questioned and individual´s reference signature is below the threshold level.