Method and apparatus for rolling enrollment for signature verification

Abstract

Improved techniques are disclosed for adapting signature verification systems to natural signature variations. For example, a technique for adapting a signature verification system to variations in a signature of a user includes the following steps / operations. One or more signature samples are obtained from the user. The one or more obtained signature samples are submitted by the user as part of a regular authentication procedure associated with the signature verification system. A reference set of signature samples for the user is updated through selection of one or more signature samples from the obtained signature samples, such that the updated reference set is usable by the signature verification system for verifying subsequent signature samples attributed to the user. The selection of the one or more signature samples used to update the reference set is conditioned on a false rejection rate of the user when at least one obtained signature sample of the user is authenticated and on an identification check when no obtained signature sample is authenticated.

Description

FIELD OF THE INVENTION [0001] This present invention generally relates to signature verification systems and, more particularly, to improved techniques for adapting such systems to natural signature variations. BACKGROUND OF THE INVENTION [0002] Signature verification is a commonly used biometric authentication method. Compared with other forms of biometric authentication such as fingerprint or iris verification, signature verification has the advantage that it is a historically well-established and well-accepted approbation method and is thus perceived to be less intrusive than modern alternatives. This property makes it particularly attractive to applications in banking, retail and hospitality industries. [0003] Signature verification is divided into two main areas: static (offline) signature verification where signature samples are optically scanned into image representations, and dynamic (online) signature verification where signature samples are collected from a digitizing tabl...

AI Technical Summary

Benefits of technology

[0010] Principles of the present invention are directed toward improved tech...

Problems solved by technology

However, there are a number of drawbacks with this scheme.

First, in some applications such as retail, collecting many samples during one enrollment session puts an undue burden on customers.

Second, even if more samples can be collected during enrollment, samples collected in one session are typically not very representative of the natural variation exhibited by most signers.

Furthermore, it is known that samples collected in one session can not capture the “drift” (i.e., a slow shifting of style over a period of time) which is also common among signers.

However, this is not very practical because of the extra burden placed on the customers.

However, this policy is not very effective since setting the threshold too high will only allow the addition of samples that are very close to the initial reference samples, thus defeating the purpose of capturing more variation; while setting it too low will increase the risk of adding forgeries, thus polluting the reference set.

Images