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

Texture image segmentation method based on level set model

A texture image, level set technology, applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of uneven grayscale, difficult texture image segmentation, noise sensitivity, etc.

Active Publication Date: 2017-01-04
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to solve the defects that existing methods are difficult to segment texture images and are sensitive to uneven gray scale and noise, and propose a texture image segmentation method based on level set model

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
  • Texture image segmentation method based on level set model
  • Texture image segmentation method based on level set model
  • Texture image segmentation method based on level set model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0096] This embodiment describes the process of applying the "level set model-based texture image segmentation method" of the present invention to the image "Leopard1.bmp":

[0097] figure 1 For the algorithm flow of this method and this embodiment, from figure 1 It can be seen that the method includes the following steps:

[0098] Step A: Log-Gabor filtering;

[0099] Specifically in this embodiment, the input image I is "Leopard1.bmp", and Log-Gabor filtering is performed on I to obtain I G ;

[0100] In this embodiment, the Log-Gabor parameter is taken as: the filter frequency parameter σ f =k / w 0 =0.65, the angle parameter σ θ =0.52, the direction parameter θ is 0, and the wavelet scale S is 3;

[0101] Step B: extracting the LSS descriptor;

[0102] The specific process can refer to step 2. The area size N is set to 41, the small block size n is set to 5, and the number of blocks M is set to 40 (ρ is divided into 4 intervals, and θ is equally divided into 10 interva...

Embodiment 2

[0113] This embodiment specifically describes the segmentation results obtained by performing steps 1 to 6 of the present invention on 6 texture images (the segmentation results are represented by white lines), and compares them with existing image segmentation methods.

[0114] figure 2 and image 3 They are the segmentation results of 3 texture images and 3 texture images with noise / grayscale unevenness. These 6 texture images are the input images in step 1;

[0115] figure 2 Divided into 5 rows and 3 columns, each row represents the result obtained by using an image segmentation method (the first two rows are the standard results of the original image and manual segmentation), and each column represents a different original image. Among them, the comparison methods are: LGDF algorithm, ASLVD algorithm and this method; there are 3 original images, from left to right: "Leopard1.bmp", "Zebra1.bmp" and "Zebra2.png";

[0116] image 3 Divided into 4 rows and 3 columns, ea...

Embodiment 3

[0126] This embodiment is a comparison between the number of curve evolution iterations required by the method for image segmentation and the number of iterations when the LBM acceleration unit is removed. In both cases, the number of iterations required to process different images are shown in Table 2:

[0127] Table 2 Comparison of the number of iterations between this method and the case of removing the LBM unit

[0128]

[0129] It can be seen that when the LBM acceleration unit is removed, the number of iterations increases significantly; on the 6 images, the efficiency after acceleration is 2 to 6 times higher than that before acceleration, which shows the effectiveness of LBM acceleration. The introduction of LBM significantly reduces the number of iterations of curve evolution in this method, reduces the time required for evolution, and improves the efficiency of image segmentation.

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 provides a texture image segmentation method based on a level set model. The texture image segmentation method comprises following steps of: 1, carrying out Log-Gabor filtering on an input image and outputting the filtered image; 2, extracting an LSS descriptor from the filtered image so as to obtain an image formed by a descriptor component; 3, constructing a texture energy item on the image formed by the descriptor component; 4, constructing an LGDF energy item on the input image; 5, integrating the two kinds of energy items in steps 3 and 4 so as to form an energy function of the method; and 6, by maximizing the energy function in the step 5, solving a segmentation curve of the energy function and using a Lattice Boltzmann method to accelerating the solving process. According to the invention, based on the level set model, a new texture energy item is designed by use of the LSS descriptor and then is combined with a traditional LGDF energy item, a good segmentation effect is achieved for each kind of texture image, so the method has robustness for noise and uneven gray levels, and through optimization of the Lattice Boltzmann method, the image segmentation efficiency is improved.

Description

technical field [0001] The invention relates to a texture image segmentation method based on a level set model, and belongs to the technical field of image segmentation and image processing. Background technique [0002] Although image segmentation is one of the most basic problems in the field of image processing, it is only between the image processing and image analysis levels in the visual computing theory proposed by D.Marr, but image segmentation is still an extremely difficult task. One of the main reasons is because of the "morbid" characteristics of image segmentation, the accuracy of the segmentation results is uncertain and ambiguous, and is closely related to people's subjective feelings and psychological effects; the second is because the information in the image is very It is rich, and often has multiple components such as grayscale, color, and texture at the same time, and it is difficult to summarize and measure through a unified model. Therefore, researcher...

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): G06T7/00
CPCG06T2207/20021G06T2207/20024
Inventor 刘利雄范盛明宁小东廖乐健
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com