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

Multi-target picture segmentation based on level set

A level set, multi-objective technology, applied in the field of image analysis, can solve the problems of not considering the deviation item, inaccurate results, and unable to correct the image deviation

Inactive Publication Date: 2013-05-08
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method still has some disadvantages: (1) it does not consider the prior probability of region division; (2) it is sometimes sensitive to initialization; (3) this method only considers the two-order situation, and cannot divide the region containing multiple different targets. image; (4) The deviation neighborhood of the image cannot be obtained, so the obtained image cannot be further corrected
But there are still some problems: (1) In Gaussian estimation, it is assumed that all divisions are equal, that is, the prior probability is not considered, which sometimes leads to inaccurate results
(2) Sometimes it is sensitive to the initialization of the contour; (3) This method only considers the two-order situation, and cannot segment images containing multiple different targets; (4) It does not consider the bias term, and finally cannot get the bias domain of the image. Therefore, it is not possible to correct the deviation 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
  • Multi-target picture segmentation based on level set
  • Multi-target picture segmentation based on level set
  • Multi-target picture segmentation based on level set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0100] In order to verify the robustness of the method proposed in the present invention to the initialization of active contours, for a synthetic gray scale uneven noise map, such as figure 1 As shown in (a), consider the experimental results of three initialization positions, which are: 1. figure 1 (b) The initial outline is a square, which contains the entire target; 2. figure 1 The initial contour in (c) is a square, which straddles the boundary of two objects; 3. figure 1 The initial contour in (d) is a regular triangle, which is completely inside a target. Experimental results show that the segmentation method for MRI images with inhomogeneous gray levels proposed by the present invention has good robustness to active contour initialization.

Embodiment 2

[0102] In order to verify the accuracy of the region-based active contour model for segmenting medical images with uneven gray levels, the method proposed by the present invention and the model based on local Gaussian fitting items were used to conduct comparative experiments on the same liver CT image. The results are as follows figure 1 shown. in, figure 2 (a) is a liver CT image; figure 2 The rectangle in (b) is the location of initialization; figure 2 (c) is the segmentation result of the LBF model; figure 2 (d) is the segmentation result of the method proposed by the present invention. figure 2 The shapes and positions of the initialization contours in (b), 2(c), and 2(d) are exactly the same. Experimental results show that the segmentation method proposed by the present invention has a better segmentation effect.

[0103] Accurate extraction of gray matter, white matter, and cerebrospinal fluid in brain images is of great significance in medical image analysis ...

Embodiment 3

[0105] The brain images used in the experiment were as follows: image 3 As shown in (a), image 3 The two rectangles in (b) are the initialization contours of gray matter and white matter respectively; image 3 (c) is the segmentation result that the method proposed in the present invention is extended to multistage; image 3 (d) is the deviation field obtained by the method proposed by the present invention. Experimental results show that the method proposed by the present invention can also achieve ideal segmentation results in multi-level situations.

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 a multi-target picture segmentation based on a level set, and the multi-target picture segmentation based on the level set is applied in the technical field of the image analysis. The method includes the following steps: firstly, drawing one closed curve or more than one closed curves on to-be-segmented images as an initial outline; secondly, utilizing an initiative outline model based on a region, carrying out an iteration revolution on the initiative outline, and obtaining a profile curve of a target. The initiative outline model based on the region fully takes partial gray level information of the image into account. Therefore, the multi-target picture segmentation based on the level set is capable of segmenting images with uneven gray levels, extending the model into multiple orders, and segmenting over the multi-target images. Compared with the prior art, the multi-target picture segmentation based on the level set has the advantages of being insensitive in initialization, quick in calculation speed, strong in anti-noise ability and accurate in segmentation results. Meanwhile, the multi-target picture segmentation based on the level set is capable of segmenting medical images provided with a plurality of different targets.

Description

technical field [0001] The invention relates to a multi-target image segmentation method based on a level set, which can segment images containing multiple different targets and can be widely used in the technical field of image analysis. Background technique [0002] Image segmentation is an important issue in the field of image processing. It is of great significance to image understanding, image analysis, pattern recognition, computer vision, etc. It is widely used in many research fields and has received more and more attention. attention. However, due to its own complexity, although many researchers have made a lot of efforts, so far there is no general segmentation method, and there is no objective standard for judging whether the segmentation is successful. Therefore, image segmentation is an important aspect of computer vision. a bottleneck in . [0003] In the field of medical applications, the medical image segmentation problem faces more difficulties than the ge...

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): G06T7/00G06T7/11
Inventor 刘利雄陈孟娟
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