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

Interactive intelligent image segmentation method based on tumor attack

An intelligent image, interactive technology, applied in the field of image processing, can solve the problems of poor segmentation, no use of global information, slow speed, etc.

Inactive Publication Date: 2016-03-09
ZHEJIANG UNIV OF TECH
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the two have common shortcomings: 1. Only the color information of local pixels is used, and global information is not used; 2. If the background is complex or the similarity between the background and the target is large, the segmentation is not very good; 3. slow

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
  • Interactive intelligent image segmentation method based on tumor attack
  • Interactive intelligent image segmentation method based on tumor attack
  • Interactive intelligent image segmentation method based on tumor attack

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with the accompanying drawings.

[0037] refer to Figure 1 to Figure 4 , a kind of interactive intelligent image segmentation method based on tumor attack, described segmentation method comprises the following steps:

[0038]1) For the image to be processed, use a simple linear iterative clustering (SLIC) algorithm to perform over-segmentation (over-segment) to obtain the corresponding superpixel block;

[0039] 2) Extract the color information of each superpixel block, and find the adjacent superpixel blocks of each superpixel block in the spatial position; adopt the RGB color space, and the average RGB color of a superpixel block is used as the feature of the current superpixel value.

[0040] 3) Using the iterative energy minimization segmentation algorithm to obtain the preliminary segmentation results, the process is as follows:

[0041] 3.1) The user gets the initial tripletT(l p ,θ p , T ...

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 interactive intelligent image segmentation method based on tumor attack. The method comprises the following steps that 1) over-segmentation is carried out on an image to be processed in a simple linear iteration cluster algorithm to obtain corresponding super pixel blocks; 2) color information of each super pixel block is extracted, and the spatially adjacent super pixel block of each super pixel block is found; and 3) an initial segmentation result is obtained by utilizing an iteration energy minimizing segmentation algorithm. According to the method, local information is combined with global information, that a pixel point serves as a processing object in two original methods is replaced, instead, the super pixel serves as the processing object, the frequency in the iteration process is reduced, the speed is higher, and the obtained segmentation result is more stable.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a color image target segmentation method. Background technique [0002] In the research and application of images, people are often interested in some parts of the image, and these interested parts generally correspond to specific and special areas in the image (can correspond to a single area or multiple areas), Call it the object or the foreground; while the other part is called the background of the image. In order to identify and analyze the target, it is necessary to isolate the target from an image, which is the problem to be studied in image segmentation. [0003] Image segmentation is a key technology in image processing, and it is also a classic problem. So far, no general method has been found, and no standard for judging the quality of segmentation algorithms has been formulated. The image segmentation methods that have emerged in recent years hav...

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): G06T7/00
CPCG06T2207/30096
Inventor 周小龙产思贤陈胜勇张卓李大宁黄诚斌管秋
Owner ZHEJIANG UNIV OF TECH