Dynamic features extraction for on-line signature verification

The interest in developing a robust on-line signature verification system has greatly increased. Three kinds of forgeries, random forgery, simple forgery and expert forgery, must be considered. Dynamic features extraction for an on-line signature verification system is presented. The dynamic features are extracted from authentic and forged signatures with relatively low computational cost. All kind of forgeries, included expert forgeries, are considered for detection as forged signatures. Computer simulation results show a desirable performance of the proposed system.