TEMPLATE SYNTHESIS FOR ECG/PPG BASED BIOMETRICS

• US 20100090798A1
• Filed: 09/25/2007
• Published: 04/15/2010
• Est. Priority Date: 09/29/2006
• Status: Abandoned Application

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Bruekers, Alphons Antonius Maria Lambertus, Presura, Cristian, Damstra, Marijn Christian, Garcia Molina, Gary Nelson
• Application Number:
  US12/442,754
• Publication Number:
  US 20100090798A1
• Time in Patent Office: Days
• US Class Current: 340/5.53
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06F 2218/16 by matching signal segments
• CPC Class Codes: G06V 40/15 Biometric patterns based on physiological signals, e.g. heartbeat, blood flow

Abstract

The present invention relates to a method and a device for verifying identity of an individual by employing biometric data derived from a physical feature of the individual. A basic idea of the invention is that, rather than determining peak locations in cyclic signals such as ECG or PPG signals when using these signals as a representation of biometric data for verifying identity of an individual, shape or morphology of the signals is considered.

Claims

1. A method of verifying identity of an individual by employing biometric data derived from a physical feature of the individual, the method comprising the steps of:

acquiring a signal representing said biometric data;

normalizing the acquired signal using a value of at least one predetermined property of the signal as normalization parameter;

synthesizing a candidate signal using at least two signals selected from a group consisting of said normalized acquired signal and at least two different previously enrolled signals representing biometric data, which previously enrolled signals are normalized using said normalization parameter, by means of employing a function of a value of said predetermined property as a synthesis parameter; and

determining whether the synthesized candidate signal corresponds to any one of the remaining signals in said group, said normalized acquired signal either being used when synthesizing the candidate signal or constituting said remaining signal, wherein the identity of the individual is verified if there is correspondence between the synthesized candidate signal and said any one of the remaining signals.

2. The method of claim 1, wherein the synthesis of the candidate signal is performed by using at least two of the different previously enrolled signals and the identity of the individual is verified if there is correspondence between the synthesized candidate signal and the normalized acquired signal.

3. The method of claim 1, wherein the synthesis of the candidate signal is performed by using the normalized acquired signal and at least one of the different previously enrolled signals and the identity of the individual is verified if there is correspondence between the synthesized candidate signal and a remaining one of said at least two different previously enrolled signals.

4. The method of claim 1, wherein the normalization is achieved by means of curve fitting.

5. The method of claim 1, wherein the normalization is achieved by means of interpolation.

6. The method according to claim 1, wherein the signal representing biometric data comprises a cardiac signal.

7. The method according to claim 1, wherein a segment of the signal representing biometric data is acquired and a segment of the respective at least two enrolled signals are employed in the synthesis.

8. The method according to claim 7, wherein the segment of the signal is an R-R segment of a cardiac signal.

13. A computer program product comprising executable components for causing a device having computing capabilities to perform the steps recited in claim 1 when the components are executed in said device.

9. A device for verifying identity of an individual by employing biometric data derived from a physical feature of the individual, the device comprising:

means (104) for acquiring a signal representing said biometric data;

means (102) for normalizing the acquired signal using a value of at least one predetermined property of the signal as normalization parameter;

means (103) for synthesizing a candidate signal using at least two signals selected from a group consisting of said normalized acquired signal and at least two different previously enrolled signals representing biometric data, which previously enrolled signals are normalized using said normalization parameter, by means of employing a function of a value of said predetermined property as a synthesis parameter;

means (104) for storing the enrolled signals; and

means (105) for determining whether the synthesized candidate signal corresponds to any one of the remaining signals in said group, said normalized acquired signal either being used when synthesizing the candidate signal or constituting said remaining signal, wherein the identity of the individual is verified if there is correspondence between the synthesized candidate signal and said any one of the remaining signals.

10. The device of claim 9, wherein said means (103) for synthesizing the candidate signal uses at least two of the different previously enrolled signals and the identity of the individual is verified by the determining means (105) if there is correspondence between the synthesized candidate signal and the normalized acquired signal.

11. The device of claim 9, wherein said means (103) for synthesizing the candidate signal uses the normalized acquired signal and at least one of the different previously enrolled signals and the identity of the individual is verified the determining means (105) if there is correspondence between the synthesized candidate signal and a remaining one of said at least two different previously enrolled signals.

12. The device of claim 9, further comprising means (101) for segmenting the acquired signal and the storing means (104) comprises corresponding segments of the enrolled signals.