Unlock instant, AI-driven research and patent intelligence for your innovation.

Image processing method, electronic equipment and computer storage medium

An image processing and image technology, which is applied in the computer field, can solve the problems of high difficulty in use, difficulty in popularization, and high cost of use, and achieve the effects of ensuring viewing effect, reducing resource occupation, and ensuring authenticity

Pending Publication Date: 2021-12-03
ALIBABA SINGAPORE HLDG PTE LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is difficult to use and difficult to popularize
[0003] To sum up, in the existing technology, the cost of processing images, videos, etc. based on deep learning technology is high.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing method, electronic equipment and computer storage medium
  • Image processing method, electronic equipment and computer storage medium
  • Image processing method, electronic equipment and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] In this embodiment, the method is applied to a smart terminal, such as a mobile terminal, a PC terminal, or a smart TV, a smart speaker, etc., as an example for illustration. In an exemplary architecture, the architecture includes the aforementioned smart terminal and server. The smart terminal can be used to process and display web pages, and receive user operations on the web pages. A deep learning model capable of action transfer can be configured on the server. Of course, in other examples, the architecture may be different, for example, a deep learning model capable of action transfer may be configured on a smart terminal, which is not limited in this embodiment.

[0022] In one example, the user can add images containing people or other target objects to be processed in the web page, and provide one or more execution parts (such as head, hand, leg) of at least one target object among them. etc.) to configure corresponding actions, and the subsequent server proce...

Embodiment 2

[0041] refer to Figure 2A , shows a flowchart of the steps of the image processing method according to Embodiment 2 of the present application.

[0042] The method of the present embodiment comprises the following steps:

[0043] Step S202: Obtain the first image and the information of the target object to be processed in the first image through a web page.

[0044] Figure 2B A schematic diagram of a web page in one example is shown. like Figure 2B As shown, the web page includes an adding control for the user to add the first image, a display area for displaying at least part of the first image, etc. In addition, it may also include an action configuration interface for the user to configure action information. Of course, in other embodiments, the web page may contain other controls or areas, which is not limited.

[0045] In a feasible manner, step S202 includes the following sub-steps:

[0046] Sub-step S2021: Obtain the first image through a web page, and display ...

Embodiment 3

[0087] refer to image 3 , shows a structural block diagram of the image processing apparatus according to Embodiment 3 of the present application.

[0088] In this embodiment, the image processing device includes:

[0089] The first acquiring module 302 is configured to acquire the first image and the information of the target object to be processed in the first image through a web page;

[0090] A determining module 304, configured to determine action information to be applied to the target object to be processed, where the action information is used to indicate an action to be performed and an execution site in the target object that executes the action to be performed;

[0091] The second acquiring module 306 is configured to perform structured processing on the information of the target object to be processed and the action information to obtain structured data;

[0092] The third obtaining module 308 is configured to obtain a second image sequence obtained by performin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention provides an image processing method, electronic equipment and a computer storage medium. The method comprises the steps of obtaining a first image and information of a to-be-processed target object in the first image through a web page; determining action information to be applied to the target object to be processed, wherein the action information is used for indicating an action to be executed and an execution part for executing the action to be executed in the target object; performing structured processing on the information of the target object to be processed and the action information to obtain structured data; and obtaining a second image sequence obtained by performing action migration based on the action information on the target object in the first image according to the structured data. The method is simple to operate and can reduce resource occupation so as to reduce waste.

Description

technical field [0001] The embodiments of the present application relate to the technical field of computers, and in particular, to an image processing method, electronic equipment, and computer storage media. Background technique [0002] With the development and maturity of deep learning technology, its application in computer vision is also increasing. A way to apply deep learning technology is to integrate it into an application (such as a mobile application or a PC application), which makes the application take up more space, not only wasting storage space, but also every user who uses the application The devices of the program must be downloaded, resulting in a large occupation and waste of bandwidth and other resources. Another way to apply deep learning technology is through API (Application Programming Interface) calls. This method is difficult to use and is difficult to popularize. [0003] To sum up, in the prior art, the cost of processing images, videos, etc....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/958G06F9/451G06N3/04G06N3/08
CPCG06F16/958G06F9/451G06N3/04G06N3/08
Inventor 吴翰清刘洋
Owner ALIBABA SINGAPORE HLDG PTE LTD