Method and system for authenticating user of a mobile device via hybrid biometics information

• US 9,547,760 B2
• Filed: 02/22/2013
• Issued: 01/17/2017
• Est. Priority Date: 02/24/2012
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kang, Sangki, Kim, Kyungtae, Lee, Sanghoon, Kim, Yangwook, Lee, Chulhwan, Jung, Seokyeong
• Primary Examiner(s): AVERY, JEREMIAH L
• Application Number:
  US13/774,390
• Publication Number:
  US 20130227678A1
• Time in Patent Office: 1,425 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities
• CPC Class Codes: G10L 15/25 using position of the lips, movement of the lips or face analysis
• CPC Class Codes: G10L 17/10 Multimodal systems, i.e. based on the integration of multiple recognition engines or fusion of expert systems

Abstract

A system and method is provided that authenticates a user using hybrid biometrics information, such as a user'"'"'s image information, a user'"'"'s voice information, etc. The user authentication method includes: acquiring a number of biometrics information; generating a number of authentication information corresponding to the acquired biometrics information; and performing an integral user authentication based on the by generated authentication information.

Claims

1. A user authentication method comprising:

receiving by a camera or a microphone of electronic device at least one of image information or voice information, respectively;

identifying by a controller of the electronic device when only one of the at least one of image information and voice information has been received, whether another of the image information and voice information is received such that both image information and the voice information for authentication are received during a predetermined time period;

detecting, if both image information and voice information are received within the predetermined time period, an object feature vector value based on the image information and a voice feature vector value based on the voice information;

performing an integral user authentication for authentication by determining whether each of the detected feature vector values respectively matches with prestored information according to a respective user settable probability over a predetermined amount;

determining, by a synchronization detection unit, whether the object feature vector value and the voice feature vector value are synchronized with each other, and outputting synchronization information;

wherein when the synchronization information indicates that the object feature vector and the voice feature vector value are synchronized with each other, outputting information that the authentication is successful;

wherein when the synchronization information indicates that the object feature vector and the voice feature vector are not synchronized with each other, outputting information that the authentication has failed; and

outputting information indicating the user authentication has failed if the predetermined time period has elapsed and both image information and voice information have not been received.

2. The method of claim 1, wherein performing the integral user authentication comprises at least one of the following:

determining whether a value for a preset word matches the detected voice feature vector value;

determining whether a motion state of an object of the image information is synchronized with the received voice information; and

determining whether the motion state of the object of the image information matches a motion state of one or more preset objects.

3. The method of claim 1, wherein performing the integral user authentication comprises:

displaying, by a controller, a randomly selected word; and

determining whether the detected voice feature vector value matches a feature vector value of the selected word over the predetermined amount.

4. The method of claim 1, further comprising:

generating facial authentication information for a facial feature vector value, motion information for the object feature vector value, and voice authentication information for the voice feature vector value to perform the integral user authentication.

5. A user authentication method comprising:

acquiring by an electronic device at least a first type of biometrics information for authentication;

identifying by a controller, if only one type of biometrics information is received, whether a second type of biometrics information is additionally acquired during a predetermined time period;

generating, if the second type of biometric information is acquired within the predetermined time period, a plurality of authentication information corresponding to the acquired biometrics information respectively, and performing an integral user authentication for authentication based on the generated authentication information by determining whether feature values of generated information respectively matches with previously stored information by a respective user settable probability over a predetermined amount;

determining, by a synchronization detection unit, whether an object feature vector value and a voice feature vector value are synchronized with each other, and outputting synchronization information;

wherein when the synchronization information indicates that the object feature vector value and the voice feature vector value are synchronized with each other, outputting information that the authentication is successful;

wherein when the synchronization information indicates that the object feature vector value and the voice feature vector value are not synchronized with each other, outputting information that the authentication has failed; and

outputting information indicating the user authentication has failed if the predetermined time period has elapsed without receiving at least two types of biometrics information.

6. The method of claim 5, wherein the acquiring comprises:

acquiring image information via a camera module; and

acquiring voice information via a microphone.

7. The method of claim 6, wherein the generating comprises:

detecting a facial feature vector value and the object feature vector value based on the image information, and the voice feature value based on the voice information;

generating facial authentication information using the facial feature vector value;

generating voice authentication information using the voice feature vector value; and

generating motion information using the object feature vector value.

8. The method of claim 7, wherein the motion information comprises:

information regarding a motion state of a preset object.

9. The method of claim 7, wherein performing the integral user authentication comprises:

determining whether the authentication is successful based on the facial authentication information, the voice authentication information, and the motion information by determining whether the detected feature vector values match prestored information over a predetermined amount.

10. The method of claim 6, wherein the generating the plurality of authentication information corresponding to the acquired biometrics information comprises:

detecting a facial feature vector value and the object feature vector value based on the image information, and the voice feature vector value based on the voice information;

generating facial authentication information using the facial feature vector value;

generating voice authentication information using the voice feature vector value; and

generating synchronization information using the object feature vector value and the voice feature vector value.

11. The method of claim 10, wherein performing the integral user authentication comprises:

determining whether the authentication is successful based on the facial authentication information, the voice authentication information, and the synchronization information by determining whether the detected feature vector values match prestored information over a predetermined amount.

12. A mobile device comprising:

a camera module;

a microphone; and

a controller configured to;

acquire, via the camera module and the microphone, at least one of an image information and a voice information;

identify, if only one of the image information or the voice information is received, whether a the other of the image information and the voice information is additionally received during a predetermined time period;

detect, if another of the image information and voice information is received within the predetermined time period, an object feature vector value based on the acquired image information and a voice feature vector value based on the acquired voice information, and perform an integral user authentication for authentication by determining whether the detected feature vector values respectively match with prestored information over a predetermined amount;

a synchronization detection unit that determines whether the object feature vector value and the voice feature vector value are synchronized with each other, and outputs synchronization information;

wherein when the synchronization information indicates that the object feature vector value and the voice feature vector value are synchronized with each other, output information that the authentication is successful;

wherein when the synchronization information indicates that the object feature vector value and the voice feature vector value are not synchronized with each other, output information that the authentication has failed; and

output information indicating user authentication has failed if the predetermined time period has elapsed and both image information and voice information have not been received.

13. The mobile device of claim 12, wherein the controller performs at least one of the following:

determining whether a value for a preset word matches the voice feature vector value;

determining whether a motion state of an object is synchronized with the voice information; and

determining whether a motion state of the object matches a motion state of one or more preset objects.

14. The mobile device of claim 12, further comprising:

a display for displaying a randomly selected word,

wherein the controller determines whether the voice feature vector value matches a feature vector value of the selected word over the predetermined amount.

15. The mobile device of claim 12, wherein the controller:

generates facial authentication information for a facial feature vector value, motion information for the object feature vector value, and voice authentication information for the voice feature vector value; and

determines whether the generated authentication information matches preset authentication information.

16. The mobile device of claim 15, wherein the controller concludes that the authentication has failed when at least one of the facial authentication information, the voice authentication information, and the motion information is not authenticated.

17. A user device comprising:

a camera module;

a microphone; and

a controller configured to;

acquire at least one biometrics information of at least two types of biometrics information used for authentication;

identify, if only one of biometrics information is received, whether another of the at least two types of biometrics information is acquired such that the at least two types of biometrics information are acquired during a predetermined time period;

perform, if the at least two types of biometrics information are acquired within the predetermined time period, an integral user authentication using a plurality of authentication information that are generated based on the acquired biometrics information;

a synchronization detection unit that determines whether an object feature vector value and a voice feature vector value are synchronized with each other, and outputs synchronization information;

wherein when the synchronization information indicates that the object feature vector value and the voice feature vector value are synchronized with each other, output information that the authentication is successful;

wherein when the synchronization information indicates that the object feature vector value and the voice feature vector value are not synchronized with each other, output information that the authentication has failed; and

output information indicating user authentication has failed if the predetermined time period has elapsed.

18. The user device of claim 17, wherein the controller further configured to:

detect a facial feature vector value and the object feature vector value from an image acquired via the camera module;

detect a voice feature vector value from a voice acquired via the microphone; and

perform the integral user authentication based on the plural authentication information transferred from an image authentication processor and a voice authentication processor.

19. The user device of claim 18, wherein the controller further configured to:

detect a static, facial feature vector value based on a still image captured from the image and perform a facial authentication using the detected facial feature vector value; and

detect the object feature vector value representing a dynamic state of the object determined via the image and perform an object authentication using the detected object feature vector value.

20. The user device of claim 19, wherein the controller further configured to:

perform user authentication by identifying a motion of an object based on the object feature vector value; and

/or

determine whether the object feature vector value is synchronized with the voice feature vector value.

21. The user device of claim 20, wherein the controller determines whether the authentication is successful based on a facial authentication information output by a facial authentication processor, a voice authentication information output by the voice authentication processor, and a motion information output by a motion determining unit.

22. The user device of claim 20, wherein the controller determines whether the authentication is successful based on the facial authentication information output by a facial authentication processor, the voice authentication information output by the voice authentication processor, and the synchronization information output.

23. The user device of claim 17, further comprising:

a memory for storing statistic models for facial recognition and speech recognition.