Abstract
Handwritten signatures are considered as the
most natural method of authenticating a person’s identity
(compared to other biometric and cryptographic forms of
authentication). The learning process inherent in Neural
Networks (NN) can be applied to the process of verifying
handwritten signatures that are electronically captured via
a stylus. This paper presents a method for verifying handwritten
signatures by using a NN architecture. Various static
(e.g., height, slant, etc.) and dynamic (e.g., velocity, pen tip
pressure, etc.) signature features are extracted and used to
train the NN. Several Network topologies are tested and
their accuracy is compared. The resulting system performs
reasonably well with an overall error rate of 3.3% being
reported for the best case.
AbstractHandwritten signatures are considered as themost natural method of authenticating a person’s identity(compared to other biometric and cryptographic forms ofauthentication). The learning process inherent in NeuralNetworks (NN) can be applied to the process of verifyinghandwritten signatures that are electronically captured viaa stylus. This paper presents a method for verifying handwrittensignatures by using a NN architecture. Various static(e.g., height, slant, etc.) and dynamic (e.g., velocity, pen tippressure, etc.) signature features are extracted and used totrain the NN. Several Network topologies are tested andtheir accuracy is compared. The resulting system performsreasonably well with an overall error rate of 3.3% beingreported for the best case.
การแปล กรุณารอสักครู่..
