Image processing method and apparatus, computer-readable medium, and electronic device

Patent metadata

Field	Value
Publication number	US-11282182-B2
Application number	US-202016996145-A
Country	US
Kind code	B2
Filing date	Aug 18, 2020
Priority date	Jul 12, 2018
Publication date	Mar 22, 2022
Grant date	Mar 22, 2022

Abstract

Embodiments of this disclosure provide an image processing method and apparatus, a computer-readable medium, and an electronic device. The image processing method includes: obtaining a to-be-processed image; determining a to-be-processed object in the to-be-processed image, the to-be-processed object comprising at least one of a human face, an animal face, or a cartoon character face; selecting a reference animated image to be applied to the to-be-processed image; processing the to-be-processed image according to the reference animated image, to generate a plurality of frames of images, each frame of the plurality of frames of images comprising the to-be-processed object; and composing the plurality of frames of images into a target animated image.

First claim

What is claimed is:

1. A method for image processing, performed by an electronic device, comprising:
obtaining a to-be-processed image;
determining a to-be-processed object in the to-be-processed image, the to-be-processed object comprising at least one of a human face, an animal face, or a cartoon character face;
selecting a reference animated image to be applied to the to-be-processed image;
determining a maximum scaling ratio of a plurality of frames of images according to an original size of the to-be-processed object and an original size of the to-be-processed image;
determining an actual scaling ratio of each frame of the plurality of frames of images according to a scaling mode and a total frame quantity of the reference animated image, and the maximum scaling ratio;
generating the plurality of frames of images based on the to-be-processed image and the actual scaling ratio of each frame of the plurality of frames of images, each frame of the plurality of frames of images comprising the to-be-processed object; and
composing the plurality of frames of images into a target animated image.

2. The method according to claim 1 , wherein the scaling mode is a uniform speed scaling mode; and wherein determining the actual scaling ratio of each frame of the plurality of frames of images according to the scaling mode and the total frame quantity of the reference animated image, and the maximum scaling ratio comprises:
determining a first scaling ratio of each frame of the plurality of frames of images according to the maximum scaling ratio, and the total frame quantity;
decrementing the total frame quantity, when the first scaling ratio of each frame of the plurality of frames of images is less than a scaling threshold to obtain an updated total frame quantity, and determining the first scaling ratio according to the maximum scaling ratio, and the updated total frame quantity, until the first scaling ratio of each frame of the plurality of frames of images is not less than the scaling threshold; and
setting the actual scaling ratio to the first scaling ratio.

3. The method according to claim 1 , wherein generating the plurality of frames of images based on the to-be-processed image and the actual scaling ratio of each frame of the plurality of frames of images further comprises:
determining a total movement distance of the to-be-processed object according to an original position and a target position of the to-be-processed object in the to-be-processed image;
determining a movement distance of the to-be-processed object in each frame of the plurality of frames of images according to a movement mode of the reference animated image, the actual scaling ratio of each frame of the plurality of frames of images, and the total movement distance; and
generating the plurality of frames of images based on the to-be-processed image, the actual scaling ratio of each frame of the plurality of frames of images, and the movement distance of the to-be-processed object in each frame of the plurality of frames of images, each frame of the plurality of frames of images comprising the to-be-processed object.

4. The method according to claim 3 , wherein the movement mode comprises at least one of a rectilinear uniform speed movement mode, a rectilinear variable speed movement mode, a curvilinear uniform speed movement mode, or a curvilinear variable speed movement mode.

5. The method according to claim 1 , wherein generating the plurality of frames of images based on the to-be-processed image and the actual scaling ratio of each frame of the plurality of frames of images further comprises:
determining a rotation angle of each frame of the plurality of frames of images according to a total rotation angle of the reference animated image; and
generating the plurality of frames of images based on the to-be-processed image, the actual scaling ratio of each frame of the plurality of frames of images, and the rotation angle of each frame of the plurality of frames of images, each frame of the plurality of frames of images comprising the to-be-processed object.

6. The method according to claim 1 :
wherein the method further comprises:
obtaining an expression detection result of the to-be-processed object based on at least one frame of the plurality of frames of images; and
adding a corresponding text to the at least one frame of the plurality of frames of images according to the expression detection result, to generate at least one frame of image comprising the corresponding text; and

wherein composing the plurality of frames of images into the target animated image comprises:
composing the plurality of frames of images and the at least one frame of image comprising the corresponding text into the target animated image.

7. The method according to claim 6 , wherein selecting the reference animated image to be applied to the to-be-processed image comprises one of:
determining, in response to an operation for the reference animated image, the reference animated image to be applied to the to-be-processed image; or
recommending, according to the expression detection result, the reference animated image applied to the to-be-processed image.

8. A method for image processing, performed by an electronic device, comprising:
obtaining a to-be-processed image;
determining a to-be-processed object in the to-be-processed image, the to-be-processed object comprising at least one of a human face, an animal face, or a cartoon character face;
selecting a plurality of reference animated images to be applied to the to-be-processed image;
processing the to-be-processed image according to each of the plurality of reference animated images, to generate a first image sequence of a plurality of frames of images, each of the plurality of frames of images in the first image sequence comprising the to-be-processed object;
composing each of the plurality of frames of images in the first image sequence into a temporary animated image to obtain an animated image sequence; and
sequentially splicing each of the temporary animated image in the animated image sequence to obtain the target animated image.

9. The method according to claim 1 , further comprising:
performing an image definition evaluation on the to-be-processed image, to obtain an evaluation result; and
optimizing image definition of the to-be-processed image according to the evaluation result.

10. The method according to claim 9 , wherein optimizing the image definition of the to-be-processed image according to the evaluation result comprises:
optimizing the image definition of the to-be-processed image by using a super-resolution method based on deep machine learning.

11. The method according to claim 1 , wherein determining the to-be-processed object in the to-be-processed image comprises:
recognizing one or more objects in the to-be-processed image, to obtain an object quantity in the to-be-processed image;
using the one object in the to-be-processed image as the to-be-processed object when the object quantity is equal to one; and
determining, when the object quantity is greater than one, the to-be-processed object in response to an operation on the to-be-processed image.

12. An apparatus for image processing, comprising a memory for storing computer instructions and a processor in communication with the memory, wherein, when the processor executes the instructions, the processor is configured to cause the apparatus to:
obtain a to-be-processed image;
determine a to-be-processed object in the to-be-processed image, the to-be-processed object comprising at least one of a human face, an animal face, or a cartoon character face;

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Yu Le
• Liu Neng
• Zhu Huiying
• Hua Youwei

Classifications

• G06T3/40

  Scaling of whole images or parts thereof, e.g. expanding or contracting · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06T7/0002 Primary

  Inspection of images, e.g. flaw detection · CPC title

• G06T13/80 Primary

  Two-dimensional [2D] animation, e.g. using sprites · CPC title

• G06V40/174

  Facial expression recognition · CPC title