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

An image segmentation method with neighborhood constraints, terminal equipment and storage medium

An image segmentation and neighborhood technology, applied in the field of image processing, can solve problems such as the inability to obtain the distance sign function and the blurred boundary.

Inactive Publication Date: 2020-01-24
MINNAN NORMAL UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In 1999, Sussman et al. completed the initialization process by using an iterative method to solve the initialization equation, but this method sometimes cannot obtain the desired distance sign function
In 2010, Zhang et al. proposed a process of adding a Gaussian filter after each evolution of the level set function to ensure the smoothness of the level set function without reinitialization, but this method is likely to cause blurred boundaries

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 with neighborhood constraints, terminal equipment and storage medium
  • An image segmentation method with neighborhood constraints, terminal equipment and storage medium
  • An image segmentation method with neighborhood constraints, terminal equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] refer to figure 1 As shown, the present invention provides a kind of image segmentation method that the self-adaptive fuzzy level set with neighborhood constraint has neighborhood constraint, comprises the following steps:

[0083] S1: Input the image to be segmented.

[0084] The image to be segmented selected in this embodiment is a brain MR image.

[0085] S2: Initialize model parameters: set neighborhood size, adjust parameter α, and stop iteration condition γ.

[0086] S3: In the image, select a neighborhood space according to the size of the neighborhood, and perform anisotropic weighting processing on each pixel in the neighborhood space.

[0087] Anisotropic weighting is used to add different weights to each pixel in the neighborhood, so that pixels with gray values ​​similar to the central pixel have larger weights, and vice versa.

[0088] Let the image processed by anisotropic weighting be I w (x), where x represents a pixel in the image.

[0089] For ea...

Embodiment 2

[0158] The present invention also provides an image segmentation terminal device with neighborhood constraints, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor executes the computer program The program realizes the steps in the above-mentioned method embodiment of Embodiment 1 of the present invention.

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 an image segmentation method with neighborhood constraint, a terminal device and a storage medium. According to the method, an anisotropic weighting weight capable of fully considering local space information is introduced into the neighborhood of each pixel, and the weight considers the action intensity on a central pixel from two aspects of a space distance and a gray level difference, so that the noise resistance robustness is improved. The distance regular item in the energy functional of the level set is redefined, so that the problem that the level set needs to be initialized in each iteration is solved, and the stability and the accuracy of the boundary diffusion rate are ensured. By combining the advantages of the fuzzy C-means clustering membership function, the evolution parameter lambda i of the control level set is fuzzified, that is, a constant parameter is changed into a self-adaptive parameter, so that the evolution of the function of the level set can be better controlled according to the target image.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image segmentation method with neighborhood constraints, a terminal device and a storage medium. Background technique [0002] Medical image segmentation plays a key role in the field of medical image analysis and processing, and improving its accuracy and computational efficiency is a complex and challenging task. The purpose of segmentation is to divide the acquired images into different anatomical tissues or regions with the same intrinsic properties. Many follow-up analyzes in clinical diagnosis and treatment are carried out based on the segmentation results of medical images. However, due to the inherent defects of imaging equipment and the spatial variation of radio frequency fields, medical images are often disturbed by noise and brightness inhomogeneity (biased). field shift), which can easily lead to errors in segmentation results. Therefore, in the case of...

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): G06T7/11
Inventor 宋建华张哲
Owner MINNAN NORMAL UNIV