Data update method for face-to-unlock authentication, authentication device, and non-volatile storage medium

Patent metadata

Field	Value
Publication number	US-10867199-B2
Application number	US-201816147001-A
Country	US
Kind code	B2
Filing date	Sep 28, 2018
Priority date	Oct 11, 2017
Publication date	Dec 15, 2020
Grant date	Dec 15, 2020

Abstract

The application provides a data update method for face-to-unlock authentication, an authentication device and system, and a non-volatile storage medium. The data update method for face-to-unlock authentication includes: acquiring facial image data of a user to be unlock-authenticated; obtaining a plurality of candidate sets from the facial image data; determining whether there is target data satisfying a predetermined condition among the plurality of candidate sets; in the case where it is determined that there is target data satisfying the predetermined condition among the plurality of candidate sets, updating facial image data in a first set by using the target data, wherein a first unlock authentication is performed based on the facial image data in the first set.

First claim

What is claimed is:

1. A data update method for face-to-unlock authentication, comprising:
acquiring facial image data of a user to be unlock-authenticated;
obtaining a plurality of candidate sets from the facial image data;
determining whether there is target data satisfying a first predetermined condition among the plurality of candidate sets;
in the case where it is determined that there is target data satisfying the first predetermined condition among the plurality of candidate sets, updating facial image data in a first set by using the target data, wherein a first unlock authentication is performed based on the facial image data in the first set,
wherein the plurality of candidate sets include a third candidate set,
the third candidate set includes facial image data of the user to be unlock-authenticated as acquired under authentication failure of a second unlock authentication performed when the first unlock authentication performed based on acquired facial image data of the user to be unlock-authenticated and the facial image data in the first set fails;
it is determined whether there is target data satisfying a second predetermined condition in the third candidate set, the target data is added to a blacklist set in the case where it is determined that there is target data satisfying the second predetermined condition in the third candidate set.

2. The data update method according to claim 1 , wherein the plurality of candidate sets further include a first candidate set and a second candidate set,
the first candidate set includes facial image data of the user to be unlock-authenticated as acquired under authentication success of the first unlock authentication performed based on the acquired facial image data of the user to be unlock-authenticated and the facial image data in the first set;
the second candidate set includes facial image data of the user to be unlock-authenticated as acquired under authentication success of the second unlock authentication performed when the first unlock authentication performed based on the acquired facial image data of the user to be unlock-authenticated and the facial image data in the first set fails;
the first unlock authentication is different from the second unlock authentication.

3. The data update method according to claim 2 , wherein
it is determined whether there is target data satisfying the first predetermined condition in the first candidate set, facial image data in the first set and corresponding to the target data is replaced by using the target data in the case where it is determined that there is target data satisfying the first predetermined condition in the first candidate set;
it is determined whether there is target data satisfying the first predetermined condition in the second candidate set, the target data is added to the first set in the case where it is determined that there is target data satisfying the first predetermined condition in the second candidate set.

4. The data update method according to claim 2 , wherein the first unlock authentication is a facial image unlock authentication,
the second unlock authentication includes at least one of the following: fingerprint unlock authentication, password unlock authentication, iris unlock authentication, retina unlock authentication, voiceprint unlock authentication, and gesture unlock authentication.

5. The data update method according to claim 1 , further comprising:
determining whether there is target data satisfying the second predetermined condition among the plurality of candidate sets;
in the case where it is determined that there is target data satisfying the second predetermined condition among the plurality of candidate sets, updating facial image data in the blacklist set by using the target data, wherein the first unlock authentication is prohibited from being performed by using the facial image data in the blacklist set.

6. The data update method according to claim 5 , wherein
updating facial image data in the first set by using the target data comprises: adding the target data to the first set, or replacing facial image data in the first set and corresponding to the target data;
updating facial image data in the blacklist set by using the target data comprises: adding the target data to the blacklist set.

7. The data update method according to claim 5 , wherein determining whether there is target data satisfying the first predetermined condition among the plurality of candidate sets and determining whether there is target data satisfying the second predetermined condition among the plurality of candidate sets comprises:
determining respectively whether there are a plurality of facial image data belonging to the same face among the facial image data corresponding to a respective candidate set, and obtaining a determination result;
in the case where it is determined that there are a plurality of facial image data belonging to the same face among the facial image data corresponding to a candidate set, and an amount of the plurality of facial image data exceeds a first threshold, determining that there is target data satisfying the first predetermined condition or target data satisfying the second predetermined condition in the candidate set,
the target data is facial image data of the same face that exceeds the first threshold in the candidate set.

8. The data update method according to claim 7 , wherein in the case where it is determined that there is target data satisfying the first predetermined condition or target data satisfying the second predetermined condition in a candidate set, the method further comprising:
verifying whether the target data matches the facial image data in the first set or the blacklist set, and in the case where the verification successes, updating the facial image data in the first set or the blacklist set by using the target data.

9. The data update method according to claim 8 , wherein verifying whether the target data matches the facial image data in the first set or the blacklist set comprises:
matching the target data with the facial image data in the first set or the blacklist set to obtain a matching result;
in the case where the matching result indicates that the target data is consistent with a timeline change with respect to the facial image data in the first set or the blacklist set, the verification successes; or
in the case where the matching result indicates that the target data differs from the facial image data in the first set or the blacklist set in a specific region, the verification successes.

10. The data update method according to claim 9 , wherein in the case where the first unlock authentication is a facial image unlock authentication, matching the target data with the facial image data in the first set or the blacklist set comprises:
extracting texture features of a first region on a face from among the target data;
determining, via predetermined texture features of the facial image data in the first set, whether a similarity between the texture features of the first region on a face and the predetermined texture feature in the target data exceeds a second threshold;
in the case where it is determined that the similarity between the texture features of the first region on a face and the predetermined texture feature in the target data exceeds the second threshold, the matching result indicates that the target data is consistent with a timeline change with respect to the facial image data in the first set;
the first region includes at least one of a forehead, an eyelid, a cheek, a mouth corner, a beard, an eye corner, and a glabella or any combination thereof.

11. The data update met

Assignees

• Beijing Kuangshi Tech Co Ltd
• Megvii Beijing Technology Co Ltd

Inventors

• Chen Keqing

Classifications

• G06F21/32 Primary

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

• G06V40/168 Primary

  Feature extraction; Face representation · CPC title

• G06V40/50

  Maintenance of biometric data or enrolment thereof · CPC title

• G06V40/70 Primary

  Multimodal biometrics, e.g. combining information from different biometric modalities · CPC title

• G06V40/171

  Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships · CPC title