Tiresias :: Design guidelines :: An introduction to biometrics

An Introduction to Biometrics - Dynamic Signature Recognition

What is dynamic signature recognition?
Dynamic signature recognition captures the distinct behavioural characteristics of an individual’s signature including shape, speed, stroke, pen pressure and timing information.

How does it work?
Signature recognition technology consists primarily of a pen and a specialized writing tablet, which are then connected to a local or central computer for template processing and verification. In order to start the data acquisition phase of the enrolment process, the individual must sign their name multiple times on the writing tablet. However, there are a number of constraints in the data acquisition phase. First, a signature cannot be too long or too short. If a signature is too long, there will be too much behavioral data presented, and as a result, it will be difficult for the signature recognition system to identify consistent and unique data points. If a signature is too short, there will not be enough data present, and as a result, this will lead to a higher False Accept Rate (for example, an impostor being authorized by the signature recognition system). Second, the individual must complete the enrolment and verification processes in the same type of environment and conditions. For example, if the individual was standing in the enrolment phase, but sitting in the verification phase, and resting their arm in one phase and not in the other phase while signing, can cause the enrolment and verification templates to be substantially different from each other.

After the data acquisition phase, the signature recognition system then extracts the unique features from the behavioral characteristics, which includes the time utilized by the individual to sign their name; the pressure applied from the pen to the writing tablet; the rate of speed in signing the signature; the overall size of the signature; and the quantity and the various directions of the strokes in the signature.

Since signature recognition is classified as a behavioural biometric, there are no actual images of the signature used in the template creation phase. With signature recognition templates, different values or “weights” are assigned to the unique features described. These templates can be as large as 3 kilobytes.

Applications
Some documented applications include the Chase Manhattan Bank (the first known bank to adopt signature recognition technology); the Internal Revenue Service for verification purposes in tax returns that have been filed online; and Charles Schwab & Company for new client applications.

Standards

Standards under development:

INCITS PN-1603-D: Information Technology-Signature/Sign Image Based Interchange Format
ISO/IEC 19794-11: Biometric interchange formats Part 11: Signature/Sign Processed Dynamic Data
ISO/IEC WD 19794-7: Information Technology-Biometric Data Interchange Formats-Part 7: Signature/Sign Behavioral Data

Further information

Das, R, HTG Advance Systems, An Application of Biometric Technology: Signature Recognition

Manufacturers/suppliers of dynamic signature recognition technologies:

Communication Intelligence Corp
DynaSig Corporation
onClick Corp
Secure Signature Systems
SOFTPRO GmbH
Valyd Inc
WonderNet Ltd

Acknowledgement

The information contained in this section was collected from the following source:

Ravi Das, HTG Advance Systems, An Application of Biometric Technology: Signature Recognition