# US 2020/0394391 A1 · Face matching method and apparatus, storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0394391 A1
- Document ID: US20200394391A1
- Status: Published application
- Kind: A1
- Application number: 17/004,761
- Filed: 2020-08-27
- Published: 2020-12-17
- Earliest claimed: 2018-06-05
- Assignees: Beijing Sensetime Technology Development Co., Ltd.
- Applicants: Beijing Sensetime Technology Development Co., Ltd.
- Inventors: Fan ZHANG; Binxu Peng
- Web page: https://patentgrep.com/patent/US20200394391A1

## CPC

- G06V 40/172: {Classification, e.g. identification}
- G06V 10/757: {Matching configurations of points or features}
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06V 40/178: {estimating age from face image; using age information for improving recognition}
- G06V 40/179: {metadata assisted face recognition}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Examples of the present disclosure provide a face matching method and a face matching apparatus, and a storage medium. The face matching method includes: obtaining a first attribute of first face information which is to be matched; determining one or more preferential matching ranges based on the first attribute; and comparing the first face information with second face information in the one or more preferential matching ranges.

## Claims

### Claim 1

A face matching method, comprising:
obtaining a first attribute of first face information which is to be matched;
determining one or more preferential matching ranges based on the first attribute; and
comparing the first face information with second face information in the one or more preferential matching ranges.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
in response to a comparison result indicating that the first face information fails to match the second face information in the one or more preferential matching ranges, further comparing the first face information with second face information outside the one or more preferential matching ranges.

### Claim 3 (depends on 1)

The method of claim 1, wherein obtaining the first attribute of the first face information which is to be matched comprises at least one of:
obtaining a subject attribute of a first imaged subject based on the first face information; or
obtaining an imaging parameter for collecting the first face information.

### Claim 4 (depends on 3)

The method of claim 3, wherein obtaining the subject attribute of the first imaged subject based on the first face information comprises at least one of:
obtaining a gender of the first imaged subject based on the first face information;
obtaining an age of the first imaged subject based on the first face information;
obtaining a hair length of the first imaged subject based on the first face information; or
obtaining wear of the first imaged subject based on the first face information.

### Claim 5 (depends on 4)

The method of claim 4, wherein determining the one or more preferential matching ranges based on the first attribute comprises at least one of:
determining a first preferential matching range based on the gender of the first imaged subject, wherein a gender of a second imaged subject corresponding to second face information comprised in the first preferential matching range is the same as that of the first imaged subject;
determining a second preferential matching range based on the age of the first imaged subject, wherein an age of a second imaged subject corresponding to second face information comprised in the second preferential matching range is matchable with that of the first imaged subject;
determining a third preferential matching range based on the hair length of the first imaged subject, wherein a hair length of a second imaged subject corresponding to second face information comprised in the third preferential matching range is matchable with that of the first imaged subject; or
determining a fourth preferential matching range based on the wear of the first imaged subject, wherein particular wearing or accessories of a second imaged subject corresponding to second face information comprised in the fourth preferential matching range is the same as that of the first imaged subject.

### Claim 6 (depends on 4)

The method of claim 4, wherein the wear comprises at least one of:
glasses;
clothing;
accessories; or
a bag.

### Claim 7 (depends on 3)

The method of claim 3, wherein obtaining the imaging parameter for collecting the first face information comprises at least one of:
obtaining an imaging location for collecting the first face information; or
obtaining a spatial attribute of a space where the imaging location of the first face information is located.

### Claim 8 (depends on 7)

The method of claim 7, wherein determining the one or more preferential matching ranges based on the first attribute comprises at least one of:
determining a fifth preferential matching range based on the imaging location, wherein a distance between the imaging location and a recorded latest appearance location of a second imaged subject, which corresponds to second face information comprised in the fifth preferential matching range, is within a first distance range; or
determining a sixth preferential matching range based on an imaging location of a second imaged subject corresponding to the second face information comprised in the fifth preferential matching range, which comprises: a recorded residential address, a recorded office address, or a recorded location with an appearance frequency above a frequency threshold.

### Claim 9 (depends on 7)

The method of claim 7, wherein determining the one or more preferential matching ranges based on the first attribute comprises at least one of:
determining a sixth preferential matching range based on the spatial attribute, wherein at least one piece of identification information of a second imaged subject corresponding to second face information comprised in the sixth preferential matching range is associated with the spatial attribute; or
determining a seventh preferential matching range based on the space attribute, wherein device identification information of a device, which is held by a second imaged subject corresponding to second face information comprised in the seventh preferential matching range, is comprised in device identification information collected in the space corresponding to the spatial attribute.

### Claim 10 (depends on 1)

The method of claim 1, wherein comparing the first face information with the second face information in the one or more preferential matching ranges comprises:
in response to that there are at least two preferential matching ranges, determining an intersection of the at least two preferential matching ranges; and
comparing the first face information with second face information in the intersection.

### Claim 11 (depends on 1)

The method of claim 1, wherein comparing the first face information with the second face information in the one or more preferential matching ranges comprises:
obtaining a union of at least two preferential matching ranges by merging the at least two preferential matching ranges; and
comparing the first face information with second face information in the union.

### Claim 12 (depends on 1)

The method of claim 1, wherein comparing the first face information with the second face information in the one or more preferential matching ranges comprises:
in response to that there are at least two preferential matching ranges, determining an intersection of the at least two preferential matching ranges;
obtaining a union of the at least two preferential matching ranges by merging the at least two preferential matching ranges;
comparing the first face information with second face information in the intersection at a first priority level; and
comparing the first face information with second face information in the union at a second priority level lower than the first priority level.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
in response to that there are at least two pieces of second face information matched the first face information, obtaining a second attribute of the first face information;
comparing the second attribute with an attribute label of each piece of the second face information matched the first face information; and
selecting a piece of the second face information of which the attribute label has highest similarity to the second attribute.

### Claim 14

An electronic device, comprising:
a processor; and
a memory storing instructions executable by the processor,
wherein the processor is configured to:
obtain a first attribute of first face information which is to be matched;
determine one or more preferential matching ranges based on the first attribute; and
compare the first face information with second face information in the one or more preferential matching ranges.

### Claim 15 (depends on 14)

The electronic device of claim 14, wherein the processor is further configured to:
in response to a comparison result indicating that the first face information fails to match the second face information in the one or more preferential matching ranges, further compare the first face information with second face information outside the one or more preferential matching ranges.

### Claim 16 (depends on 14)

The electronic device of claim 14, wherein comparing the first face information with the second face information in the one or more preferential matching ranges comprises:
in response to that there are at least two preferential matching ranges, determining an intersection of the at least two preferential matching ranges; and
comparing the first face information with second face information in the intersection.

### Claim 17 (depends on 14)

The electronic device of claim 14, wherein comparing the first face information with the second face information in the one or more preferential matching ranges comprises:
obtaining a union of at least two preferential matching ranges by merging the at least two preferential matching ranges; and
comparing the first face information with second face information in the union.

### Claim 18 (depends on 14)

The electronic device of claim 14, wherein comparing the first face information with the second face information in the one or more preferential matching ranges comprises:
in response to that there are at least two preferential matching ranges, determining an intersection of the at least two preferential matching ranges;
obtaining a union of the at least two preferential matching ranges by merging the at least two preferential matching ranges;
comparing the first face information with second face information in the intersection at a first priority level; and
comparing the first face information with second face information in the union at a second priority level lower than the first priority level.

### Claim 19 (depends on 14)

The electronic device of claim 14, wherein the processor is further configured to:
in response to that there are at least two pieces of second face information matched the first face information, obtain a second attribute of the first face information;
compare the second attribute with an attribute label of each piece of the second face information matched the first face information; and
select a piece of the second face information of which the attribute label has highest similarity to the second attribute.

### Claim 20

A non-transitory computer storage medium storing computer executable instructions that, when executed, cause a processor to:
obtain a first attribute of first face information which is to be matched;
determine one or more preferential matching ranges based on the first attribute; and
compare the first face information with second face information in the one or more preferential matching ranges.
