Determining a user based on features

Patent metadata

Field	Value
Publication number	US-9609511-B2
Application number	US-201214394513-A
Country	US
Kind code	B2
Filing date	Jul 31, 2012
Priority date	Jul 31, 2012
Publication date	Mar 28, 2017
Grant date	Mar 28, 2017

Abstract

A signal may be emitted by an emitter or transducer. The signal may be sensed by a sensor, such as an accelerometer. Features of a body part or portion may be one of detected, extracted, or constructed from the sensed signal. It may be determined whether the body part or portion matches that of a user, such as an authorized user, based on the features.

First claim

What is claimed is:

1. A computing device, comprising:
an emitter to emit an acoustic signal;
a sensor to sense the acoustic signal after the acoustic signal has passed through a portion of a user's body;
an extractor to extract multiple features of the portion of the user's body from the sensed acoustic signal; and
a classifier to determine, based on the extracted multiple features, whether the portion of the user's body corresponds to a model of the portion of the user's body used by the classifier.

2. The computing device of claim 1 , further comprising an authenticator to authenticate the user in response to the classifier determining the portion of the user's body corresponds to the model of the portion of the user's body used by the classifier.

3. The computing device of claim 1 , further comprising a communication interface, wherein the computing device is to cause the emitter to emit the acoustic signal in response to a message received by the communication interface from a second computing device requesting authentication of the user.

4. The computing device of claim 1 , further comprising a user interface to accept an input requesting access to a feature of the computing device, wherein the computing device is to cause the emitter to emit the acoustic signal in response to the input.

5. The computing device of claim 1 , wherein the classifier is configured to determine which user profile of a plurality of user profiles the user corresponds to based on the extracted multiple features.

6. The computing device of claim 5 , further comprising a personalization module to store settings for each of the plurality of user profiles, the personalization module configured to implement the settings of a respective user profile of the plurality of user profiles on the computing device in response to the classifier determining that the user corresponds to the respective user profile.

7. The computing device of claim 1 , wherein the portion of the user's body is a hand.

8. A method, comprising:
emitting a vibratory signal via a transducer of a portable device;
detecting features of a body part in contact with the portable device based on sensing the vibratory signal via an accelerometer; and
determining whether the body part in contact with the portable device matches a body part of an authorized person by inputting the detected features into a pattern recognition model.

9. The method of claim 8 , wherein the detecting comprises detecting features of plural body parts in contact with the portable device based on sensing the vibratory signal via the accelerometer, and wherein the determining comprises determining whether the plural body parts in contact with the portable device match plural body parts of the authorized person by inputting the detected features into respective pattern recognition models.

10. The method of claim 8 , further comprising:
receiving an instruction to emit the vibratory signal from another device; and
sending an indication to the another device that a user of the portable device matches the authorized person in response to determining that the body part in contact with the portable device matches the body part of the authorized person.

11. The method of claim 8 , further comprising granting access to a feature of the portable device in response to determining that the body part in contact with the portable device matches the body part of the authorized person.

12. The method of claim 8 , wherein the detected features are based on the vibratory signal after reflection from a physical structure of the body part.

13. The method of claim 8 , wherein the detected features are based on the vibratory signal after transmittance through a physical structure of the body part.

14. The method of claim 8 , wherein the pattern recognition model is a support vector machine.

15. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processor, cause the processor to:
instruct a transducer to emit an acoustic signal;
receive a sensed acoustic signal detected by an accelerometer in response to the acoustic signal after the acoustic signal has passed through a body part of an unidentified subject;
construct feature vectors representing the body part of the unidentified subject from the sensed acoustic signal; and
determine whether the unidentified subject matches a user based on the feature vectors.

16. The computing device of claim 1 , further comprising a housing, wherein the emitter and the sensor are contained in the housing.

17. The computing device of claim 1 , wherein the acoustic signal is a vibratory signal, and the sensor is to sense the vibratory signal after the vibratory signal has passed through the portion of the user's body, and the extracted multiple features are based on the sensed vibratory signal.

18. The computing device of claim 3 , wherein the communication interface is to send, to the second computing device in response to the message, an indication that the user has been authenticated based on determining by the classifier that the portion of the user's body corresponds to the model of the portion of the user's body.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the processor is contained in a housing of a portable device, and the transducer and the accelerometer are also contained in the housing.

20. The non-transitory computer-readable storage medium of claim 15 , wherein the acoustic signal is a vibratory signal, and the accelerometer is to sense the vibratory signal after the vibratory signal has passed through the body part, and the constructed feature vectors are based on the sensed vibratory signal.

Assignees

• Vural Esra
• Van Order Mark W
• Nyholm Peter S
• Schuckers Stephanie
• Hewlett Packard Development Co Lp

Inventors

• Vural Esra
• Van Order Mark W
• Nyholm Peter S
• Schuckers Stephanie

Classifications

• A61B5/0051 Primary

  by applying vibrations · CPC title

• A61B5/6898

  Portable consumer electronic devices, e.g. music players, telephones, tablet computers · CPC title

• H04W12/06 Primary

  Authentication · CPC title

• A61B5/1171

  based on the shapes or appearances of their bodies or parts thereof · CPC title

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title