USER AUTHENTICATION METHOD AND APPARATUS BASED ON ELECTROCARDIOGRAM (ECG) SIGNAL

• US 20160063233A1
• Filed: 06/30/2015
• Published: 03/03/2016
• Est. Priority Date: 09/01/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kim, Sang Joon, Bae, Chisung
• Granted Patent: US 10,572,637 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/117 Identification of persons methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/725 using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04L 9/3231 Biological data, e.g. fingerprint, voice or retina network architectures or network communication protocols for supporting authentication of entities using biometrical features in a packet data network H04L63/0861

Abstract

A user authentication apparatus includes an electrocardiogram (ECG) waveform acquirer configured to acquire an authentication ECG waveform of a user to authenticate the user; a filter configured to filter the authentication ECG waveform using a Kalman filter by applying a reference model parameter extracted from a reference ECG waveform to the Kalman filter; and an authenticator configured to compare the filtered ECG waveform and the reference ECG waveform, and determine whether the filtered authentication ECG waveform corresponds to the reference ECG waveform based on a result of the comparing.

Claims

1. A user authentication apparatus comprising:

an electrocardiogram (ECG) waveform acquirer configured to acquire an authentication ECG waveform of a user to be authenticated;

a filter configured to filter the authentication ECG waveform using a Kalman filter by applying a reference model parameter extracted from a reference ECG waveform to the Kalman filter; and

an authenticator configured to compare the filtered authentication ECG waveform and the reference ECG waveform, and determine whether the filtered authentication ECG waveform corresponds to the reference ECG waveform based on a result of the comparing.

2. The apparatus of claim 1, wherein the authentication ECG waveform comprises a plurality of ECG waveforms;

and

the apparatus further comprises an ECG waveform extractor configured to align the plurality of ECG waveforms included in the authentication ECG waveform based on an R peak.

3. The apparatus of claim 1, wherein the reference model parameter comprises any one or any combination of a first amplitude parameter indicating an amplitude for each of a plurality of first Gaussian functions extracted from the reference ECG waveform, a first duration parameter indicating a duration for each of the first Gaussian functions, a first position parameter indicating a position for each of the first Gaussian functions, and a first angular velocity parameter indicating an angular velocity based on a change in a phase of the reference ECG waveform.

4. The apparatus of claim 3, wherein the filter is further configured to extract a predicted authentication ECG waveform by applying the reference model parameter to the authentication ECG waveform using the Kalman filter, and output the filtered authentication ECG waveform by combining the authentication ECG waveform and the predicted authentication ECG waveform.

5. The apparatus of claim 4, further comprising a feature point extractor configured to extract a plurality of feature points from the filtered authentication ECG waveform.

6. The apparatus of claim 5, wherein the feature point extractor is further configured to extract a plurality of second Gaussian functions from the filtered authentication ECG waveform, and extract any one or any combination of a second amplitude parameter indicating an amplitude for each of the second Gaussian functions, a second duration parameter indicating a duration for each of the second Gaussian functions, and a second position parameter indicating a position for each of the second Gaussian functions so that a distance between the filtered authentication ECG waveform and a sum of the second Gaussian functions is minimized.

7. The apparatus of claim 6, wherein the authenticator is further configured to extract a similarity between the filtered authentication ECG waveform and the reference ECG waveform, and determine whether the filtered authentication ECG waveform corresponds to the reference ECG waveform based on the similarity.

8. The apparatus of claim 7, wherein the authenticator is further configured to extract the similarity between a plurality of feature points in the filtered authentication ECG waveform and a plurality of feature points in the reference ECG waveform, and determine whether the filtered authentication ECG waveform corresponds to the reference ECG waveform based on the similarity.

9. The apparatus of claim 8, wherein the authenticator is further configured to determine the similarity based on any one or any combination of a distance between the first amplitude parameter and the second amplitude parameter, a distance between the first duration parameter and the second duration parameter, and a distance between the first position parameter and the second position parameter.

10. The apparatus of claim 9, wherein the authenticator is further configured to determine the similarity by applying a weight to each of the distance between the first amplitude parameter and the second amplitude parameter, the distance between the first duration parameter and the second duration parameter, and the distance between the first position parameter and the second position parameter.

11. The apparatus of claim 7, wherein the authenticator is further configured to determine the filtered authentication ECG waveform as corresponding to the reference ECG waveform, and authenticate the user as being a user of the reference ECG waveform, in response to the similarity being greater than a predetermined threshold.

12. The apparatus of claim 7, wherein the filter, the feature point extractor, and the authenticator are further configured to operate repetitively in response to the authenticator determining that the filtered authentication ECG waveform does not correspond to the reference ECG waveform.

13. The apparatus of claim 12, wherein the authenticator is further configured to determine that the user is not the user of the reference ECG waveform in response to a number of operations repetitively performed by the filter, the feature point extractor, and the authenticator being greater than a predetermined threshold.

14. The apparatus of claim 12, wherein the authenticator is further configured to authenticate the user as being the user of the reference ECG waveform in response to the similarity being greater than a predetermined threshold and increasing as the operations are repetitively performed by the filter, the feature point extractor, and the authenticator.

15. The apparatus of claim 5, wherein the feature point extractor is further configured to extract as the feature points any one or any combination of a PR interval, a PR segment, a QRS complex, an ST segment, an ST interval, a QT interval, an RR interval, an amplitude, a position, a noise power, and a predetermined statistical value of the filtered authentication ECG waveform.

16. The apparatus of claim 1, wherein the authenticator is further configured to authenticate the user by determining whether the user is a user of the reference ECG waveform based on a result of the comparing;

and

the filter is further configured to reset a variable of the Kalman filter in response to the authenticator determining that the user is not the user of the reference ECG waveform.

17. A user registration apparatus comprising:

an electrocardiogram (ECG) waveform acquirer configured to acquire a registration ECG waveform of a user to register the user;

an ECG waveform extractor configured to extract a representative ECG waveform from the registration ECG waveform based on an R peak;

a model parameter extractor configured to extract a first model parameter by modeling the representative ECG waveform;

a filter configured to filter the registration ECG waveform using a Kalman filter by applying the first model parameter to the Kalman filter; and

a feature point extractor configured to extract a plurality of feature points from the filtered registration ECG waveform.

18. The apparatus of claim 17, wherein the model parameter extractor is further configured to extract a plurality of first Gaussian functions from the representative ECG waveform, and extract any one or any combination of a first amplitude parameter indicating an amplitude for each of the first Gaussian functions, a first duration parameter indicating a duration for each of the first Gaussian functions, and a first position parameter for each of the first Gaussian functions so that a distance between the representative ECG waveform and a sum of the first Gaussian functions is minimized.

19. The apparatus of claim 17, wherein the filter is further configured to extract a predicted registration ECG waveform by applying the first model parameter to the registration ECG waveform based on the first Gaussian functions using the Kalman filter, and output the filtered registration ECG waveform by combining the registration ECG waveform and the predicted registration ECG waveform.

20. The apparatus of claim 17, wherein the feature point extractor is further configured to extract a plurality of second Gaussian functions from the filtered registration ECG waveform, and extract any one or any combination of a second amplitude parameter indicating an amplitude for each of the second Gaussian functions, a second duration parameter indicating a duration for each of the second Gaussian functions, and a second position parameter indicating a position for each of the second Gaussian functions so that a distance between the filtered registration ECG waveform and a sum of the second Gaussian functions is minimized.

21. The apparatus of claim 17, wherein the feature point extractor is further configured to extract as the feature points any one or any combination of a PR interval, a PR segment, a QRS complex, an ST segment, an ST interval, a QT interval, an RR interval, an amplitude, a position, a noise power, and a predetermined statistic value of the filtered registration ECG waveform.

22. A user authentication apparatus comprising:

a register configured to extract a first model parameter by modeling a representative electrocardiogram (ECG) waveform extracted from a registration ECG waveform, filter the registration ECG waveform using a Kalman filter by applying the first model parameter to the Kalman filter, and extract a plurality of feature points from the filtered registration ECG waveform; and

an authenticator configured to filter an authentication ECG waveform using the Kalman filter by applying a second model parameter included in the feature points to the Kalman filter, compare the filtered authentication ECG waveform and the filtered registration ECG waveform, and determine whether the filtered authentication ECG waveform corresponds to the registration ECG waveform based on a result of the comparing.

23. A user authentication method comprising:

acquiring an authentication electrocardiogram (ECG) waveform of a user to be authenticated;

filtering the authentication ECG waveform using a Kalman filter by applying a reference model parameter extracted from a reference ECG waveform to the Kalman filter;

comparing the filtered authentication ECG waveform and the reference ECG waveform; and

determining whether the filtered authentication ECG waveform corresponds to the reference ECG waveform based on a result of the comparing.

24. A user registration method comprising:

acquiring a registration electrocardiogram (ECG) waveform of a user to be authenticated;

extracting a representative ECG waveform from the registration ECG waveform based on an R peak;

extracting a model parameter by modeling the representative ECG waveform;

filtering the registration ECG waveform using a Kalman filter by applying the model parameter to the Kalman filter; and

extracting a plurality of feature points from the filtered registration ECG waveform.

25. A user authentication method comprising:

extracting a first model parameter by modeling a representative electrocardiogram (ECG) waveform extracted from a registration ECG waveform;

filtering the registration ECG waveform using a Kalman filter by applying the first model parameter to the Kalman filter;

extracting a plurality of feature points from the filtered registration ECG waveform;

filtering an authentication ECG waveform using the Kalman filter by applying a second model parameter included in the feature points to the Kalman filter;

comparing the filtered authentication ECG waveform and the filtered registration ECG waveform; and

determining whether the filtered authentication ECG waveform corresponds to the filtered registration ECG waveform based on a result of the comparing.

26. A user authentication method comprising:

acquiring an authentication electrocardiogram (ECG) waveform of a user to be authenticated;

filtering the authentication ECG waveform using a predictive filter adjusted based on a characteristic extracted from a reference ECG waveform of a pre-registered user;

comparing the filtered authentication ECG waveform and the reference ECG waveform; and

determining whether the user is the pre-registered user based on a result of the comparing.

27. The method of claim 26, wherein the characteristic is a parameter of a Gaussian function modeling the reference ECG waveform.

28. The method of claim 26, further comprising:

extracting a plurality of first feature points from the filtered authentication ECG waveform; and

extracting a plurality of second feature points from the reference ECG waveform;

wherein the comparing comprises comparing the plurality of first feature points and the plurality of second feature points.