Dismiss
InnovationQ will be updated on Sunday, Jan. 21, from 9am - 11am ET. You may experience brief service interruptions during that time.
Browse Prior Art Database

# Signature Verifier

IP.com Disclosure Number: IPCOM000083461D
Original Publication Date: 1975-May-01
Included in the Prior Art Database: 2005-Mar-01
Document File: 3 page(s) / 87K

IBM

## Related People

Baker, CT: AUTHOR

## Abstract

Timing data is generated when a signature is written in order to verify validity of a signature and to detect forgery. The timing data are taken from the two x and y coordinate functions of time that are generated, as shown in Figs. 1, 2 and 3.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 56% of the total text.

Page 1 of 3

Signature Verifier

Timing data is generated when a signature is written in order to verify validity of a signature and to detect forgery. The timing data are taken from the two x and y coordinate functions of time that are generated, as shown in Figs. 1, 2 and
3.

The data used are taken from the extrema (peaks and valleys) of the x(t) and y(t) functions. For example, the coordinates of the y(t) function extrema may be represented as:

((y(1), t(1)), (y(2), t(2)),..., (y(k), t(k))).

The timing data that are used are:

(t(2) - t(1)), (t(3) - t(2)),..., (t(k) - t(k-1)).

The device uses the logic of correlation or similar methods to validate signatures and detect forgeries. Example - for two signatures S, S', there are timing sequences (as above) T and T'. Let T and T' be the corresponding sequences of timing variations about their respective averages. Then,

(Image Omitted)

calculating correlation between the timing data of S and S'. For perfect correlation r = 1, for no correlation r = 0. The data used are acquired from a data entry tablet and are processed by a digital computer.

The above procedure inherently eliminates problems of scaling and translation. A similar procedure of linear regression eliminates orientation problems due to rotation, or slanting, of a signature from the horizontal axis.

The method analyzes signatures for authentication of identity of an individual making a signature with a marking instrument. It includes measuring displacement of the marking instrument along a part...