Method and apparatus for multi-distant weighted scoring system

• US 20070234056A1
• Filed: 03/31/2006
• Published: 10/04/2007
• Est. Priority Date: 03/31/2006
• Status: Active Grant

• Current Assignee: Concentrix SREV Incorporated
• Original Assignee: Biopassword, LLC
• Inventors: Mani, Seshadri, Kellas-Dicks, Mechthild
• Granted Patent: US 7,526,412 B2
• Time in Patent Office: Days
• US Class Current: 713/172
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints

Abstract

Methods of comparing a plurality of measurements to a template are described. Measurements are compared piecewise (element-by-element) and a proportion of successful comparisons at each of a plurality of distance scaling factors is calculated. The proportions are subjected to a nonlinear transformation, then normalized and combined into a weighted sum. The weighted sum is compared with a threshold value to establish the result of the comparison. Software and systems to implement embodiments of the invention are also described and claimed.

Claims

1. A method comprising:

collecting a vector S of n measurements of a characteristic of a user;

computing a vector P as

$P_j=\frac{\underset{i=1}{\overset{n}{\sum <br><br>}}<br><br>\{\begin{array}{cc}1& \mathrm{if}<br><br>\text{\hspace{1em}<br><br>}<br><br><br><br>T_i-S_i<br><br><<br><br>d_j·<br><br>V_i\\ 0& \mathrm{otherwise}\end{array}}{n}$

wherein T is a vector of n template values, V is a corresponding vector of n variability values and d is a vector of m distance scaling factors;

computing a vector F as

$F_j=\frac{-1}{d_j}<br><br>\log <br><br>\left(1-P_j\right)$

computing a vector D as

D_j=A·

F_j+B

wherein A and B are constants;

computing a scalar W as

$W=\frac{\underset{j=1}{\overset{m}{\sum <br><br>}}<br><br>{\mathrm{WF}}_j·<br><br>D_j}{\underset{j=1}{\overset{m}{\sum <br><br>}}<br><br>{\mathrm{WF}}_j}$

wherein WF is a vector of m weight factors; and

comparing the scalar W to a predetermined value.

2. The method of claim 1 wherein m is 6.

3. The method of claim 1 wherein A is 1 and B is 0.

4. The method of claim 1 wherein d is {0.5, 1.0, 1.5, 1.7, 1.9, 2.0}.

5. The method of claim 1 wherein WF is {0.1, 0.1, 0.2, 0.25, 0.3, 0.05}.

6. The method of claim 1 wherein

7. A method comprising:

collecting a plurality of measurements of a user;

computing a proportion of the plurality of measurements that fall within a scaled range of a corresponding plurality of template measurements for a plurality of scale values;

applying a nonlinear transformation to each of the proportions;

normalizing the transformed proportions;

calculating a weighted sum of the normalized, transformed proportions; and

comparing the weighted sum to a threshold value.

8. The method of claim 7 wherein the plurality of measurements includes a plurality of keystroke timing values.

9. The method of claim 7 wherein the nonlinear transformation is a logarithmic transformation.

10. The method of claim 7 wherein normalizing comprises converting the transformed proportions to truncated linear scale.

11. The method of claim 7, further comprising:

granting access to a resource if the weighted sum exceeds the threshold value.

12. A machine-readable medium containing instructions to cause a programmable logic device to perform operations comprising:

collecting a plurality of sample measurements;

thresholding the sample measurements against a corresponding plurality of template measurements at a plurality of scales;

computing a proportion of successful measurements at each of the plurality of scales;

applying a nonlinear transformation to the plurality of proportions;

normalizing the transformed proportions;

calculating a weighted sum of the normalized, transformed proportions; and

comparing the weighted sum to a predetermined value.

13. The machine-readable medium of claim 12, containing additional instructions to cause the programmable logic device to perform further operations, including:

measuring at least one of a duration of a key press, a time between a key press and a subsequent key release, a time between a first key press and a second key press, or a pressure of a key press.

14. The machine-readable medium of claim 12 wherein thresholding comprises:

comparing a sample measurement against a template measurement to determine whether the sample measurement lies within a scaled variability range of the template measurement.

15. The machine-readable medium of claim 12 wherein the nonlinear transformation is a logarithmic transformation.

16. The machine-readable medium of claim 12, containing additional instructions to cause the programmable logic device to perform further operations, including:

granting access to a resource if the weighted sum exceeds the predetermined value.

17. The machine-readable medium of claim 12 wherein the plurality of scales comprises scaling factors between about 0.5 and about 2.0.

18. A system comprising:

a user entry device;

sampling logic to collect measurements from the user entry device;

comparison logic to prepare a weighted sum of transformed, thresholded measurements; and

access control logic to grant access to a resource if the weighted sum exceeds a predetermined value.

19. The system of claim 18 wherein the resource is use of the system.

20. The system of claim 18, further comprising:

a communication interface to exchange data with a network, wherein

the resource is data to be obtained through the network.