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

An image segmentation method based on local energy functional and non-convex regular term combined with local entropy

A local energy and image segmentation technology, applied in the field of image processing, can solve problems such as poor grayscale image segmentation effect

Active Publication Date: 2019-03-15
SHIJIAZHUANG UNIVERSITY
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the disadvantages of the above-mentioned prior art, such as poor segmentation effect on gray-scale uneven images, and propose an image segmentation method combining local energy functional of local entropy and non-convex regular term, so as to ensure Satisfactory segmentation results are obtained when the degree of unevenness of the image

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 based on local energy functional and non-convex regular term combined with local entropy
  • An image segmentation method based on local energy functional and non-convex regular term combined with local entropy
  • An image segmentation method based on local energy functional and non-convex regular term combined with local entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] The present invention is used to segment three artificially synthesized images, such as figure 2 As shown in (a), there are three artificially synthesized images with uneven gray levels. The first and second images contain multiple gray levels, and the third image has uneven gray levels from top to bottom. The parameter settings are respectively : α=0.9, β=0.1, σ=3 μ=0.002*255 2 . from figure 2 It can be seen from (b) that the present invention can achieve effective segmentation for all three images with uneven gray levels.

Embodiment 2

[0097]In order to verify the effectiveness of the present invention, three kinds of images with uneven gray levels are used for comparative experiments, and the comparative experiments are respectively CV model and LBF model.

[0098] In this embodiment, three initial contours of different shapes are used to verify the sensitivity of the algorithm to the initial contour and the processing of heterogeneous regions. The parameters of the algorithm are selected as follows: α=0.1, β=1, and the control parameters of the length item are respectively selected as μ=0.001*255 2 , μ=0.003*255 2 and μ=0.01*255 2 , variance σ 1 = 3, σ 2 =5,σ 3 =2.

[0099] from image 3 and Figure 4 It can be seen that the superiority of the algorithm of the present invention can be seen through the final level set function graph and curve evolution results, wherein, Figure 4 columns of image 3 Corresponds to each column in . The invention can adapt to different initial contours of images, an...

Embodiment 3

[0101] In this embodiment, the present invention is compared with the CV model, the LBF model and the GLP model respectively, and the effects of the four methods on image segmentation are considered.

[0102] The specific parameters are set as follows: the first and second images α=0.25, β=0.75, μ=0.001*255 2 , σ=4, the third image α=0.1, β=0.9, μ=0.002*255 2 , σ=2.

[0103] Such as Figure 5 As shown, the first column is the image curve initialization position, the second column is the CV model segmentation result, the third column is the LBF model segmentation result, the fourth column is the GLP model segmentation result, and the fifth column is the segmentation result of the present invention. Table 1 shows the number of iterations and processing time of different algorithms in the comparative experiment, and Table 2 shows the comparison results of JS coefficients and DC coefficients of different algorithms.

[0104]

[0105]

[0106] Table 1

[0107]

[0108]...

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 segmentation method of a local energy functional and a non-convex regular term combined with local entropy, comprising the following steps: (1) reading an image I (x,y); (2) initializing the parameters of the local energy functional and the non-convex regular term based on the local entropy in the image segmentation model; (3) calculating the local entropy hx of image I (x, y); (4) segmenting the image I (x, y) on the basis of the initialization parameters in the step (2), segmenting the image I (x, y) using a local energy functional based on the local entropyand an image segmentation model of a non-convex regular term, and updating the level set function phi in the segmentation process; 5) carry out evolution on that level set function phi according to the equation, jud whether the level set function phi converges or not, if so, stopping the evolution of the level set function phi, and outputting a segmented image; Otherwise, the process returns to step (4) to continue. The invention can efficiently and accurately segment gray-level non-uniform images.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to an image segmentation method. Background technique [0002] As a key technology in the fields of pattern recognition, computer vision, and artificial intelligence, image segmentation mainly aims to separate specific foreground objects from the background. However, since both the gray scale of the interest area and the background area in the image may have gray scale inhomogeneity, it brings certain difficulties to the accurate segmentation of the image. Among many image segmentation techniques, the variational level set model has the characteristics of free topological transformation and can effectively extract complex object boundaries, and has received more and more attention and applications. [0003] The level set method includes two methods based on region and edge. Among them, the CV model is a typical level set method based on region statistics. Fitting, which d...

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): G06T7/10
CPCG06T7/10
Inventor 韩明王敬涛孟军英
Owner SHIJIAZHUANG UNIVERSITY
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