# US 2022/0067350 A1 · Method and apparatus for identifying image and electronic device

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

- Number: US 2022/0067350 A1
- Document ID: US20220067350A1
- Status: Published application
- Kind: A1
- Application number: 17/454,472
- Filed: 2021-11-10
- Published: 2022-03-03
- Earliest claimed: 2020-11-17
- Assignees: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.
- Applicants: Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.
- Inventors: Guojing JIN; Yu LEI; Xingqi SHANG; Xiong ZUO; Yan CHEN; Sirui GAO; Yuantuo YU; Kangli JIANG; Yawei WANG
- Web page: https://patentgrep.com/patent/US20220067350A1

## CPC

- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06V 40/172: {Classification, e.g. identification}
- G06N 20/00: Machine learning
- G06T 7/50: Depth or shape recovery
- G06V 10/95: {structured as a network, e.g. client-server architectures}
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06V 10/82: using neural networks
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method and an apparatus for identifying an image and an electronic device are provided in the present application, which relates to the field of image recognition technology. The method for identifying the image is specifically implemented as follows: acquiring a first face image, where the first face image is one face image; acquiring face depth information about the first face image; and identifying whether a face in the first face image is masked in accordance with the face depth information. In this way, whether the face in the first face image is masked is identified in accordance with face depth information about the one face image, so as to improve the accuracy of identification.

## Claims

### Claim 1

A method for identifying an image, comprising:
acquiring a first face image, wherein the first face image is one face image;
acquiring face depth information about the first face image; and
identifying whether a face in the first face image is masked in accordance with the face depth information.

### Claim 2 (depends on 1)

The method according to claim 1, wherein subsequent to the identifying whether the face in the first face image is masked in accordance with the face depth information, the method further comprises:
when it is identified that the face in the first face image is not masked, acquiring a second face image, and performing facial recognition or face registration in accordance with the second face image, wherein the second face image comprises a face image captured after the first face image is captured.

### Claim 3 (depends on 1)

The method according to claim 1, wherein subsequent to the identifying whether the face in the first face image is masked in accordance with the face depth information, the method further comprises:
when it is identified that the face in the first face image is masked, outputting prompt information, wherein the prompt information is used to remind a user to remove a mask.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the acquiring the face depth information about the first face image comprises:
inputting the first face image into a first network model, to acquire the face depth information about the first face image; and
the identifying whether the face in the first face image is masked in accordance with the face depth information comprises:
inputting the first face image and the face depth information into a second network model, to acquire an identification result of whether the face in the first face image is masked.

### Claim 5 (depends on 2)

The method according to claim 2, wherein subsequent to the identifying whether the face in the first face image is masked in accordance with the face depth information, the method further comprises:
when it is identified that the face in the first face image is masked, outputting prompt information, wherein the prompt information is used to remind a user to remove a mask.

### Claim 6 (depends on 2)

The method according to claim 2, wherein the acquiring the face depth information about the first face image comprises:
inputting the first face image into a first network model, to acquire the face depth information about the first face image; and
the identifying whether the face in the first face image is masked in accordance with the face depth information comprises:
inputting the first face image and the face depth information into a second network model, to acquire an identification result of whether the face in the first face image is masked.

### Claim 7

An apparatus for identifying an image, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the memory stores thereon an instruction that is executable by the at least one processor, and when executing the instruction, the at least one processor is configured to:
acquire a first face image, wherein the first face image is one face image;
acquire face depth information about the first face image; and
identify whether a face in the first face image is masked in accordance with the face depth information.

### Claim 8 (depends on 7)

The apparatus according to claim 7, wherein the at least one processor is further configured to:
when it is identified that the face in the first face image is not masked, acquire a second face image, and perform facial recognition or face registration in accordance with the second face image, wherein the second face image comprises a face image captured after the first face image is captured.

### Claim 9 (depends on 7)

The apparatus according to claim 7, wherein the at least one processor is further configured to:
output prompt information when it is identified that that the face in the first face image is masked, wherein the prompt information is used to remind a user to remove a mask.

### Claim 10 (depends on 7)

The apparatus according to claim 7, wherein the at least one processor is further configured to:
input the first face image into a first network model, to acquire the face depth information about the first face image; and
input the first face image and the face depth information into a second network model, to acquire an identification result of whether the face in the first face image is masked.

### Claim 11 (depends on 8)

The apparatus according to claim 8, wherein the at least one processor is further configured to:
output prompt information when it is identified that that the face in the first face image is masked, wherein the prompt information is used to remind a user to remove a mask.

### Claim 12 (depends on 8)

The apparatus according to claim 8, wherein the at least one processor is further configured to:
input the first face image into a first network model, to acquire the face depth information about the first face image; and
input the first face image and the face depth information into a second network model, to acquire an identification result of whether the face in the first face image is masked.

### Claim 13

A non-transitory computer-readable storage medium having a computer instruction thereon, wherein the computer instruction is configured to be executed to cause a computer to perform following steps:
acquiring a first face image, wherein the first face image is one face image;
acquiring face depth information about the first face image; and
identifying whether a face in the first face image is masked in accordance with the face depth information.

### Claim 14 (depends on 13)

The non-transitory computer-readable storage medium according to claim 13, wherein subsequent to the identifying whether the face in the first face image is masked in accordance with the face depth information, the computer instruction is further configured to be executed to cause a computer to perform following steps:
when it is identified that the face in the first face image is not masked, acquiring a second face image, and performing facial recognition or face registration in accordance with the second face image, wherein the second face image comprises a face image captured after the first face image is captured.

### Claim 15 (depends on 13)

The non-transitory computer-readable storage medium according to claim 13, wherein subsequent to the identifying whether the face in the first face image is masked in accordance with the face depth information, the computer instruction is further configured to be executed to cause a computer to perform following steps:
when it is identified that the face in the first face image is masked, outputting prompt information, wherein the prompt information is used to remind a user to remove a mask.

### Claim 16 (depends on 13)

The non-transitory computer-readable storage medium according to claim 13, wherein when acquiring the face depth information about the first face image, the computer instruction is further configured to be executed to cause a computer to perform following steps:
inputting the first face image into a first network model, to acquire the face depth information about the first face image; and
when identifying whether the face in the first face image is masked in accordance with the face depth information, the computer instruction is further configured to be executed to cause a computer to perform following steps:
inputting the first face image and the face depth information into a second network model, to acquire an identification result of whether the face in the first face image is masked.

### Claim 17 (depends on 14)

The non-transitory computer-readable storage medium according to claim 14, wherein subsequent to the identifying whether the face in the first face image is masked in accordance with the face depth information, the computer instruction is further configured to be executed to cause a computer to perform following steps:
when it is identified that the face in the first face image is masked, outputting prompt information, wherein the prompt information is used to remind a user to remove a mask.

### Claim 18 (depends on 14)

The non-transitory computer-readable storage medium according to claim 14, wherein when acquiring the face depth information about the first face image, the computer instruction is further configured to be executed to cause a computer to perform following steps:
inputting the first face image into a first network model, to acquire the face depth information about the first face image; and
when identifying whether the face in the first face image is masked in accordance with the face depth information, the computer instruction is further configured to be executed to cause a computer to perform following steps:
inputting the first face image and the face depth information into a second network model, to acquire an identification result of whether the face in the first face image is masked.
