D. P. Troitsky, Dm. P. Troitsky, K.V. Chirkov
An intensive introduction of biometric technologies in many spheres of human life caused increase of re-quirements to a level of safety systems reliability and security, both a requirement for the tasks on information support of clients, buyers and visitors decision, recently. The granting processes optimization of services in the industry of electronic trade, hotel economy, public catering are provide a constant growth of demand in such technologies.
Dynamic signature analysis allows us to register individuals and their hidden human behaviour. Signature is a unique attribute of the person, as well as physiological characteristics. Signature identification can be used for access restriction to premises, in bank sphere, and everywhere where important documents registration is neces-sary. Check of signature correctness could become the most effective, easy and indispensable way.
Individual features can be identified by finding the discrete signature points like x,y-coordinates, pressure, time, pen velocity and topological invariants, such as connectivity, quantity and sequence of signature self-crossing points. Between signatures, the correlation measure is determined. The dynamic features are extracted from au-thentic and forged signatures. Experimental results show that measurement of dynamic features contains impor-tant information and could offer a high level of accuracy for signature verification.
Technical means used for implementation of this technology, are rather simple: an electronic digitizing tablet and a computer with installed software.
This paper presents a possible off-line approach to dynamic analysis of signature.