Method for determining expression model, electronic device and non-transient computer readable storage medium

Patent metadata

Field	Value
Publication number	US-12536835-B2
Application number	US-202218294433-A
Country	US
Kind code	B2
Filing date	Oct 17, 2022
Priority date	Dec 21, 2021
Publication date	Jan 27, 2026
Grant date	Jan 27, 2026

Abstract

A method for determining an expression model, an electronic device and a non-transient computer readable storage medium are provided. The method includes: acquiring a facial image and eyeball feature information of a user; determining a corresponding expression classification according to the facial image; determining a corresponding expression model to be adjusted based on the expression classification; adjusting corresponding parameters of the expression model to be adjusted by utilizing the facial image and the eyeball feature information to obtain a target expression model.

First claim

The invention claimed is:

1 . A method for determining an expression model, comprising:
acquiring a facial image and eyeball feature information of a user; determining a corresponding expression classification according to the facial image; determining a corresponding expression model to be adjusted based on the expression classification; adjusting corresponding parameters of the expression model to be adjusted by utilizing the facial image and the eyeball feature information to obtain a target expression model, wherein adjusting the corresponding parameters of the expression model to be adjusted by utilizing the facial image and the eyeball feature information to obtain the target expression model comprises: determining corresponding facial feature information according to the facial image, wherein the facial feature information includes any one or more of: information of a distance between angulus orises at two sides, and information of a vertical distance between an angulus oris at one side or angulus orises at two sides and a labial peak; adjusting the corresponding parameters of the expression model to be adjusted by utilizing the facial feature information and the eyeball feature information to obtain the target expression model.

2 . The method according to claim 1 , wherein determining the corresponding expression classification according to the facial image comprises:
inputting the facial image into a preset expression recognition model to determine the expression classification, wherein the expression recognition model is a neural network model.

3 . The method according to claim 1 , wherein adjusting the corresponding parameters of the expression model to be adjusted by utilizing the facial feature information and the eyeball feature information to obtain the target expression model comprises:
adjusting facial feature parameters to be adjusted of the expression model to be adjusted to match with the facial feature information, and adjusting eyeball feature parameters of the expression model to be adjusted to match with the eyeball feature information, to obtain the target expression model.

4 . The method according to claim 1 , wherein determining the corresponding expression model to be adjusted based on the expression classification comprises:
determining a plurality of corresponding selectable expression models by utilizing the expression classification; controlling to render the plurality of selectable expression models; acquiring a selecting instruction of the user for selecting the expression model to be adjusted from the plurality of selectable expression models; determining the expression model to be adjusted based on the selecting instruction.

5 . The method according to claim 4 , wherein determining the plurality of corresponding selectable expression models by utilizing the expression classification comprises:
determining corresponding facial proportion information according to the facial image; determining the plurality of selectable expression models according to the facial proportion information and an expression model library corresponding to the expression classification.

6 . An electronic device, comprising:
at least one processor; and a memory for storing executable instructions for the at least one processor; wherein the at least one processor is configured to perform a method by executing the executable instructions, wherein the method comprises: acquiring a facial image and eyeball feature information of a user; determining a corresponding expression classification according to the facial image; determining a corresponding expression model to be adjusted based on the expression classification; adjusting corresponding parameters of the expression model to be adjusted by utilizing the facial image and the eyeball feature information to obtain a target expression model, wherein adjusting the corresponding parameters of the expression model to be adjusted by utilizing the facial image and the eyeball feature information to obtain the target expression model comprises: determining corresponding facial feature information according to the facial image, wherein the facial feature information includes any one or more of: information of a distance between angulus orises at two sides, and information of a vertical distance between an angulus oris at one side or angulus orises at two sides and a labial peak; adjusting the corresponding parameters of the expression model to be adjusted by utilizing the facial feature information and the eyeball feature information to obtain the target expression model.

7 . The electronic device according to claim 6 , wherein determining the corresponding expression classification according to the facial image comprises:
inputting the facial image into a preset expression recognition model to determine the expression classification, wherein the expression recognition model is a neural network model.

8 . The electronic device according to claim 6 , wherein adjusting the corresponding parameters of the expression model to be adjusted by utilizing the facial feature information and the eyeball feature information to obtain the target expression model comprises:
adjusting facial feature parameters to be adjusted of the expression model to be adjusted to match with the facial feature information, and adjusting eyeball feature parameters of the expression model to be adjusted to match with the eyeball feature information, to obtain the target expression model.

9 . The electronic device according to claim 6 , wherein determining the corresponding expression model to be adjusted based on the expression classification comprises:
determining a plurality of corresponding selectable expression models by utilizing the expression classification; controlling to render the plurality of selectable expression models; acquiring a selecting instruction of the user for selecting the expression model to be adjusted from the plurality of selectable expression models; determining the expression model to be adjusted based on the selecting instruction.

10 . The electronic device according to claim 9 , wherein determining the plurality of corresponding selectable expression models by utilizing the expression classification comprises:
determining corresponding facial proportion information according to the facial image; determining the plurality of selectable expression models according to the facial proportion information and an expression model library corresponding to the expression classification.

11 . A non-transient computer-readable storage medium having stored thereon computer programs which, when executed by a processor, implement a method, the method comprises:
acquiring a facial image and eyeball feature information of a user; determining a corresponding expression classification according to the facial image; determining a corresponding expression model to be adjusted based on the expression classification; adjusting corresponding parameters of the expression model to be adjusted by utilizing the facial image and the eyeball feature information to obtain a target expression model, wherein adjusting the corresponding parameters of the expression model to be adjusted by utilizing the facial image and the eyeball feature information to obtain the target expression model comprises: determining corresponding facial feature information according to the facial image, wherein the facial feature information includes any one or more of: information of a distance between angulus orises at two sides, and information of a vertical distance between an angulus oris at one side or angulus orises at two sid

Assignees

• Beijing Zitiao Network Technology Co Ltd

Inventors

• Han Chen

Classifications

• G06V40/18

  Eye characteristics, e.g. of the iris · CPC title

• G06T13/40

  of characters, e.g. humans, animals or virtual beings · CPC title

• G06F3/011 Primary

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• G06V40/174 Primary

  Facial expression recognition · CPC title

• G06V40/171

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