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

Image processing method and device, equipment and readable storage medium

An image processing and image technology, applied in the field of machine learning, can solve problems such as image structure errors, low accuracy of image content filling, and inconformity with user content filling methods, etc., to achieve the effect of improving processing efficiency and accuracy

Pending Publication Date: 2021-01-22
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, when the image content is filled in the above-mentioned way, because the semantic information is generated through the advanced guidance information, and the generation of the advanced guidance information is likely to cause errors with the image structure that the user needs to generate, resulting in a low accuracy rate of the image content filling, Filling content that doesn't meet user expectations

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 and device, equipment and readable storage medium
  • Image processing method and device, equipment and readable storage medium
  • Image processing method and device, equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0033] First, a brief introduction to the nouns involved in the embodiments of this application:

[0034] Artificial Intelligence (AI): It is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the nature of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods ...

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 invention discloses an image processing method and device, equipment and a readable storage medium, and relates to the field of machine learning. The method comprises the steps: acquiring an inputimage group and visual guidance data, wherein the input image group comprises a hole image, and the visual guidance data are used for guiding content filling of a hole area; extracting semantic features of the visual guidance data to obtain a semantic feature map; extracting texture features of the input image group to obtain a texture feature map; and filling the hole area in the hole image according to the semantic feature map and the texture feature map to obtain a target image. The semantic feature map is determined through the visual guidance data, and the texture feature map is extracted from the input image group, so that the semantic feature map and the texture feature map are combined to obtain the target image, the visual guidance data expected by a user is contained in the target image, and the texture features deserved by the hole image can also be reserved; and the image processing accuracy of the hole image containing the hole area is improved.

Description

technical field [0001] The embodiments of the present application relate to the field of machine learning, and in particular to an image processing method, device, device, and readable storage medium. Background technique [0002] In the field of image processing, it is usually necessary to fill or modify the image content. Schematically, the removal of the image watermark is taken as an example. Fill the image in the cut out hole area. [0003] In related technologies, some advanced guidance information is used to generate semantic content, such as: semantic analysis map, image attributes, latent space, text description and other information to generate semantic content, and content is filled in the hole area of ​​​​the image according to the semantic content, so as to be filled after the image. [0004] However, when the image content is filled in the above-mentioned way, because the semantic information is generated through the advanced guidance information, and the gen...

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): G06T11/40G06T11/20G06T1/00
CPCG06T11/40G06T11/203G06T1/0021G06T2201/0203
Inventor 宋奕兵刘虹雨刘威
Owner TENCENT TECH (SHENZHEN) CO LTD