Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An image segmentation method, device, computer equipment and storage medium

An image segmentation and image technology, applied in the field of image processing, can solve problems such as low image segmentation efficiency and precision, single image features, and unsatisfactory segmentation results, so as to improve image segmentation efficiency, solve low efficiency and precision, and improve accuracy rate effect

Active Publication Date: 2022-07-08
上海硕恩网络科技股份有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventor found that the existing technology has the following defects: the image features involved in the existing random walk algorithm are relatively single, and the calculation is performed in units of each pixel, which often leads to inconsistent segmentation results. Ideal, the efficiency and accuracy of image segmentation are low

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
  • An image segmentation method, device, computer equipment and storage medium
  • An image segmentation method, device, computer equipment and storage medium
  • An image segmentation method, device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] figure 1 This is a flow chart of an image segmentation method provided by the first embodiment of the present invention. This embodiment can be applied to the situation where the random walk algorithm is used to efficiently segment the image. The method can be executed by an image segmentation device, which can be performed by software. and / or hardware, and can generally be integrated in computer equipment. correspondingly, as figure 1 As shown, the method includes the following operations:

[0036] S110. Acquire an image to be segmented.

[0037] The to-be-segmented image may be an image that needs to be segmented, as long as there is a need for segmentation, and the embodiment of the present invention does not limit relevant information such as the image type, size, and size of the to-be-segmented image.

[0038] S120. Perform cluster segmentation processing on the to-be-segmented image according to the image features to obtain a set number of initial cluster segme...

Embodiment 2

[0054] figure 2 This is a flowchart of an image segmentation method provided by the second embodiment of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiment. Specific optional implementation of class segmentation processing. correspondingly, as figure 2 As shown, the method of this embodiment may include:

[0055] S210. Acquire an image to be segmented.

[0056] S220. Perform cluster segmentation processing on the to-be-segmented image according to the image features to obtain a set number of initial cluster segmentation regions.

[0057] Correspondingly, S220 may specifically include the following operations:

[0058] S221. Divide the image to be divided evenly into divided regions of the same size.

[0059] Among them, a segmented region can be understood as a superpixel. Correspondingly, an initial cluster segmentation region can also be understood as a superpixel.

[0060] Before the initial cluster segmentation of the...

Embodiment 3

[0094] image 3 This is a flowchart of an image segmentation method provided in Embodiment 3 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiment. In this embodiment, the calculation between the initial cluster segmentation regions is given. The regional image similarity and the regional distance weight, calculate the undirected graph weight according to the regional image similarity and the regional distance weight, and calculate the node classification of the random walk algorithm according to the undirected graph weight Various concrete and optional implementations of probability. correspondingly, as image 3 As shown, the method of this embodiment may include:

[0095] S310. Acquire an image to be segmented.

[0096] S320. Perform cluster segmentation processing on the to-be-segmented image according to the image features to obtain a set number of initial cluster segmentation regions.

[0097] S330: Calculate the regional...

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

Embodiments of the present invention disclose an image segmentation method, device, computer equipment and storage medium. The method includes: acquiring an image to be segmented; performing cluster segmentation processing on the to-be-segmented image according to image features to obtain a set number of initial clusters. Class segmentation area; calculate the area image similarity and area distance weight between each of the initial cluster segmentation areas; calculate the undirected graph weight according to the area image similarity and the area distance weight; according to the The undirected graph weights calculate the node classification probability of the random walk algorithm; according to the node classification probability, the initial cluster segmentation area is divided again to obtain the target image segmentation result. The technical solutions of the embodiments of the present invention can improve the efficiency and accuracy of image segmentation.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to an image segmentation method, apparatus, computer equipment, and storage medium. Background technique [0002] Image segmentation is the technique and process of dividing an image into multiple regions with the same features and extracting objects of interest. Image segmentation is an important part of many image processing and computer vision systems, and it is a fundamental problem in image processing and analysis. [0003] The random walk algorithm is a semi-automatic image segmentation algorithm and has been successfully applied in the field of image segmentation. It divides the image by calculating the probability value of each pixel to a given pixel. [0004] In the process of realizing the present invention, the inventor found that the prior art has the following defects: the image features involved in the existing random walk algorithm...

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 Patents(China)
IPC IPC(8): G06K9/62G06V10/762G06T7/11G06T5/40
CPCG06T7/11G06T5/40G06F18/23213
Inventor 黄云
Owner 上海硕恩网络科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products