# US 10,482,316 B2 · Image information processing method and apparatus, and computer storage medium

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

- Number: US 10,482,316 B2
- Document ID: US10482316B2
- Status: Granted
- Kind: B2
- Application number: 15/815,457
- Filed: 2017-11-16
- Published: 2018-03-15
- Granted: 2019-11-19
- Earliest claimed: 2015-11-25
- Assignees: Tencent Technology (Shenzhen) Company Limited
- Applicants: Tencent Technology (Shenzhen) Company Limited
- Inventors: Zhenwei Zhang; Xinlei Zhang
- Web page: https://patentgrep.com/patent/US10482316B2

## CPC

- H04N 5/2621: {Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability}
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06V 10/776: Validation; Performance evaluation
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/165: {using facial parts and geometric relationships}
- H04L 51/046: Interoperability with other network applications or services
- H04L 51/10: Multimedia information
- H04L 51/18: Commands or executable codes
- H04N 23/611: where the recognised objects include parts of the human body
- G06V 40/166: {using acquisition arrangements}
- H04L 51/52: for supporting social networking services
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

An image processing method includes: locating respective image regions corresponding to one or more persons captured in a first image; extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image; identifying, from a plurality of image tiles, a first image tile that matches the respective facial portion of the first person in accordance with predefined correspondence between the feature information of the respective facial portion of the first person and pre-stored description information of the first image tile; and forming, by replacing the respective facial portion of the first person in the first image with the first image tile, a second image that includes at least a modified version of the respective image region corresponding to the first person of the one or more persons.

## Claims

### Claim 1

An image information processing method, comprising:
at a device having one or more processors and memory:
performing face recognition on a first image;
identifying one or more faces corresponding to one or more persons in a first image in accordance with result of the face recognition;
extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image;
receiving a first user comment including a first descriptive term for the first person identified in the first image;
in response to receiving the first user comment, displaying the first image that is modified with the respective facial portion of the first person replaced with a first image tile that matches the first descriptive term and the respective facial portion of the first person in accordance with predefined correspondence between the feature information of the respective facial portion of the first person and pre-stored description information of the first image tile;
while displaying the first image that is modified with the respective facial portion of the first person replaced with the first image tile, receiving a second user comment including a second descriptive term that is different from the first descriptive term for the first person identified in the first image; and
in response to receiving the second user comment, displaying the first image that is modified with the respective facial portion of the first person replaced with a second image tile that is different from the first image tile, and that matches the second descriptive term.

### Claim 2 (depends on 1)

The method of claim 1, wherein extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image includes:
determining one or more descriptive labels corresponding to the respective facial portion of the first person using a first machine learning model, wherein the first machine learning model is trained with the facial images and corresponding descriptive labels.

### Claim 3 (depends on 1)

The method of claim 1, wherein extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image includes:
determining an identity of the first person based on the respective facial portion of the first person;
locating respective profile information of the first person based on the determined identity of the first person; and
using one or more characteristics in the respective profile information of the first person as the one or more descriptive labels corresponding to the respective facial portion of the first person.

### Claim 4 (depends on 1)

The method of claim 1, wherein the first user comment and the second user comment are received from different users in a group chat session, and the first image is an image that is shared in the group chat session, and wherein the first image is displayed and updated on client device corresponding to the users from which the first user comment and the second user comment are received.

### Claim 5

A device for image information processing, comprising:
one or more processors; and
memory storing instructions which when executed by the one or more processors, cause the processors to perform operations comprising:
performing face recognition on a first image;
identifying one or more faces corresponding to one or more persons in a first image in accordance with result of the face recognition;
extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image;
receiving a first user comment including a first descriptive term for the first person identified in the first image;
in response to receiving the first user comment, displaying the first image that is modified with the respective facial portion of the first person replaced with a first image tile that matches the first descriptive term and the respective facial portion of the first person in accordance with predefined correspondence between the feature information of the respective facial portion of the first person and pre-stored description information of the first image tile;
while displaying the first image that is modified with the respective facial portion of the first person replaced with the first image tile, receiving a second user comment including a second descriptive term that is different from the first descriptive term for the first person identified in the first image; and
in response to receiving the second user comment, displaying the first image that is modified with the respective facial portion of the first person replaced with a second image tile that is different from the first image tile, and that matches the second descriptive term.

### Claim 6 (depends on 5)

The device of claim 5, wherein extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image includes:
determining one or more descriptive labels corresponding to the respective facial portion of the first person using a first machine learning model, wherein the first machine learning model is trained with the facial images and corresponding descriptive labels.

### Claim 7 (depends on 5)

The device of claim 5, wherein extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image includes:
determining an identity of the first person based on the respective facial portion of the first person;
locating respective profile information of the first person based on the determined identity of the first person; and
using one or more characteristics in the respective profile information of the first person as the one or more descriptive labels corresponding to the respective facial portion of the first person.

### Claim 8 (depends on 5)

The device of claim 5, wherein the first user comment and the second user comment are received from different users in a group chat session, and the first image is an image that is shared in the group chat session, and wherein the first image is displayed and updated on client device corresponding to the users from which the first user comment and the second user comment are received.

### Claim 9

A non-transitory computer-readable storage medium storing instructions which, when executed by one or more processors, cause the processors to perform operations comprising:
performing face recognition on a first image;
identifying one or more faces corresponding to one or more persons in a first image in accordance with result of the face recognition;
extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image;
receiving a first user comment including a first descriptive term for the first person identified in the first image;
in response to receiving the first user comment, displaying the first image that is modified with the respective facial portion of the first person replaced with a first image tile that matches the first descriptive term and the respective facial portion of the first person in accordance with predefined correspondence between the feature information of the respective facial portion of the first person and pre-stored description information of the first image tile;
while displaying the first image that is modified with the respective facial portion of the first person replaced with the first image tile, receiving a second user comment including a second descriptive term that is different from the first descriptive term for the first person identified in the first image; and
in response to receiving the second user comment, displaying the first image that is modified with the respective facial portion of the first person replaced with a second image tile that is different from the first image tile, and that matches the second descriptive term.

### Claim 10 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image includes:
determining one or more descriptive labels corresponding to the respective facial portion of the first person using a first machine learning model, wherein the first machine learning model is trained with the facial images and corresponding descriptive labels.

### Claim 11 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein extracting feature information of a respective facial portion of at least a first person of the one or more persons located in the first image includes:
determining an identity of the first person based on the respective facial portion of the first person;
locating respective profile information of the first person based on the determined identity of the first person; and
using one or more characteristics in the respective profile information of the first person as the one or more descriptive labels corresponding to the respective facial portion of the first person.