A noise image segmentation method based on improved energy functional model

An energy functional and image segmentation technology, applied in the field of image processing, to achieve the effect of improving segmentation speed and segmentation accuracy, reducing staircase phenomenon, and maintaining integrity

Inactive Publication Date: 2019-03-26
SHIJIAZHUANG UNIVERSITY
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to address the shortcomings of the prior art in the segmentation of noise images, and propose a noise image segmentation method based on an improved energy functional model to reduce the occurrence of "staircase phenomenon" and improve noise while denoising. Good to keep the edge information 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
  • A noise image segmentation method based on improved energy functional model
  • A noise image segmentation method based on improved energy functional model
  • A noise image segmentation method based on improved energy functional model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Such as figure 1 As shown, this embodiment relates to a noise image segmentation method based on an improved energy functional model, which specifically includes the following steps:

[0067] (1) Input the original image I(x, y);

[0068] (2) Using an energy functional model based on a non-convex functional to denoise the original image I (x, y) input in step (1), to obtain a smooth image u after denoising, the energy functional model as follows:

[0069]

[0070] Among them: 00 is the adjustment parameter, is the gradient operator;

[0071] (3) An initialization curve C is given to the smooth image u in step (2), and the initial parameters of the initialization curve C are set as follows:

[0072] The interval of the discrete grid is h=1, the time step is Δt=0.1, the regularization parameter ε=1, the weight of the length penalty item L(C) μ=O*255 2 , where O∈[0,1];

[0073] (4) According to the variational method and the Euler-Lagrange equation, the evolution...

Embodiment 2

[0093] This embodiment verifies the image noise processing capability of the present invention.

[0094] Such as figure 2 Shown in (a), it is three images with high-intensity noise, using the method of the present invention to carry out noise processing and segmentation, by figure 2 (b) It can be seen that the method of the present invention achieves better results in target segmentation under high-intensity noise.

[0095] In order to realize the qualitative evaluation of the method of the present invention, three measures of True Positive Rate (True Positive Rate, TPR), False Positive Rate (False Positive Rate, FPR) and Similarity Index (Similarity Index, SI) are used for evaluation. The definitions of the three metrics are as follows:

[0096]

[0097] Among them, S T Indicates the real foreground pixel set of the image to be segmented in the image, S A Indicates the pixel set of the foreground area obtained by the model segmentation algorithm. Ideally, SI and TPR ...

Embodiment 3

[0102] In this embodiment, the method of the present invention is compared with the image segmentation results of the NLIRCV algorithm. For details of the NLIRCV algorithm, please refer to the literature PIOTR S B, PAPIEZ J A, SCHNABEL C M.A level-set approach to joint image segmentation and registration with application to CT lung imaging [J]. Computerized Medical Imaging and Graphics, 2018, 65: 58-68, this The NLIRCV algorithm referred to in the invention is the abbreviation of Chan-Vese segmentation algorithm with a non-linear intensity-based registration algorithm in the above literature.

[0103] Such as image 3 As shown in (a), it is the original image and the image after adding different degrees of noise to the original image, and the latter two images are images with the standard deviation of 0.01 and 0.02 Gaussian noise added respectively. In the experiment, μ=0.06*255 of the two algorithms 2 .

[0104] Adopt the method of the present invention and NLIRCV algorith...

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 a noise image segmentation method based on an improved energy functional model, comprising the following steps: (1) inputting an original image; (2) inputting the original image in the step (1) denoised by using an energy functional model based on a non-convex functional, and the denoised smooth image is obtained; 3) initializing that smooth image in the step (2); (4) According to variational method and Euler-Lagrange equation, the level set function of evolution is obtained. (5) extracting a zero level set according to the level set function obtained in the step (4); (6), solving that minimum value of the energy functional, judging whet the evolution stops or not, if the evolution stops, the evolution curve is the best edge position of the target, give the segmentation result, otherwise, the algorithm goes to the step 4 to continue. Compared with the prior art, the invention improves the energy functional model, realizes a noise image segmentation method basedon the improved energy functional model, reduces the occurrence of ladder phenomenon, and improves the segmentation speed and the segmentation precision of the model while removing noise of the image.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a noise image segmentation method. Background technique [0002] Image segmentation technology is an important image analysis technology in the field of computer vision. The quality of image segmentation technology directly affects the subsequent image processing effect. However, image segmentation becomes more and more complicated due to noise, low contrast between foreground and background, blurred boundary features, and uneven gray scale. Therefore, how to suppress noise and improve segmentation accuracy in image segmentation has become the main research content. . In order to overcome the impact of image grayscale inhomogeneity and noise on image segmentation, scholars at home and abroad have proposed many solutions, and to a certain extent, achieved noise suppression and the impact of grayscale inhomogeneity, but these methods The noise immunity is poor. [0003]...

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): G06T7/11G06T7/12G06T7/194G06T5/00
CPCG06T5/002G06T2207/10132G06T2207/20192G06T2207/30096G06T7/11G06T7/12G06T7/194
Inventor 韩明董倩张培王敬涛
Owner SHIJIAZHUANG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap