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

Picture processing method, computer device and storage medium

A technology of image processing, computer program, applied in the field of image processing

Active Publication Date: 2019-02-15
SHENZHEN UNIV
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to address the problem that the image processing method in the prior art can only handle the texture synthesis with regular structure, and provide a kind of image processing method, computer equipment and storage medium

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
  • Picture processing method, computer device and storage medium
  • Picture processing method, computer device and storage medium
  • Picture processing method, computer device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0041] This application provides a picture processing method, such as figure 1 As shown, steps S110 to S130 are included.

[0042] Step S110, acquiring texture images to be synthesized.

[0043] Wherein, the texture picture to be synthesized is a picture with a texture structure input by the user and wishes to be synthesized, and the texture picture to be synthesized can be of uniform texture or non-uniform texture.

[0044] Among them, texture is a visual feature that reflects the homogeneity phenomenon in the image, and it reflects the slow-changing or periodic-changi...

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 relates to a picture processing method, which comprises the following steps of obtaining a texture picture to be synthesized; inputting the texture picture to be synthesized into a texture synthesis model; determining the texture synthesis model based on sample texture picture training; obtaining a texture synthesis picture output from the texture synthesis model. In the method, since the texture synthesis model is a texture synthesis model trained based on sample texture pictures, wherein the sample texture pictures can be uniform texture or non-uniform texture, the texture synthesis processing can be carried out on the uniform texture pictures and the non-uniform texture pictures by the method, and the texture synthesis processing can be performed on the uniform texture pictures and the non-uniform texture pictures.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to an image processing method, computer equipment and storage media. Background technique [0002] With the development of deep learning technology, it has achieved great success in the field of computer vision, bringing new ideas to texture synthesis. Periodic spatial generation confrontation networks and deep correlation methods have emerged, which are currently two representatives in this field. method. [0003] However, the current periodic spatial generative adversarial network expands the structure of the input noise distribution by constructing tensors with different sizes to achieve the purpose of extending and synthesizing high-quality periodic textures, but this method can only deal with static periodic textures. The deep correlation method uses the pre-trained image classification network to extract the result matrix from a specific convolutional layer...

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
IPC IPC(8): G06T11/00G06N3/04G06N3/08
CPCG06N3/08G06T11/001G06N3/045
Inventor 黄惠周漾
Owner SHENZHEN UNIV