Fuzzy clustering image segmentation method with plane as clustering center and anti-noise ability

An image segmentation and fuzzy clustering technology, applied in the field of image processing, can solve problems such as noise sensitivity, no consideration of pixel space information, and no segmentation results, to achieve the effect of improving accuracy, balancing weight relationships, and reducing influence

Active Publication Date: 2019-02-26
SHANDONG UNIV
View PDF6 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] However, the standard FCM method has the following obvious disadvantages in image segmentation: (1) The clustering center has a great influence on the results of image segmentation, and only using the gray value of image pixels as the basis for segmentation cannot be well Covering the image features, the ideal segmentation results cannot be obtained; (2) The spatial information of the pixels is not considered, which makes the method more sensitive to noise. When dealing with noisy images, satisfactory segmentation results cannot be obtained

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
  • Fuzzy clustering image segmentation method with plane as clustering center and anti-noise ability
  • Fuzzy clustering image segmentation method with plane as clustering center and anti-noise ability
  • Fuzzy clustering image segmentation method with plane as clustering center and anti-noise ability

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0027] like figure 1 shown, including the following steps:

[0028] 1. Given the number of cluster centers C, the maximum number of iterations L, the fuzzy weighting index m, and the algorithm termination threshold thres, randomly initialize the membership matrix;

[0029] set u ki is the membership degree of the i-th pixel to the k-th clustering plane, where i∈[1, N], k∈[1, C], the membership degree requirements satisfy:

[0030]

[0031] 2. Using the polynomial function as the clustering center, define the objective function;

[0032] This method replaces the clustering center in the FCM algorithm with a polynomial function. The clustering process of image data points is the surface fitting process. The polynomial function set as the clustering plane is:

[0033] f(x,y)=ax+by+c (4)

[0034] The cluster center is replaced by a polynomial functi...

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 fuzzy clustering image segmentation method with plane as clustering center and anti-noise ability. The method comprises the following steps: firstly, defining an objective function, initializing various coefficients and thresholds in the objective function, and randomly initializing a membership matrix; minimizing the objective function to calculate and update the coefficients and fuzzy membership matrices of the clustering plane. calculating the value of the objective function based on the updated fuzzy membership matrix, when the absolute value of the difference between the objective function values of the two successive iterations is less than the termination condition or the method exceeds the maximum iteration number limit, the iteration ends, otherwise, theiteration continues to perform the updating, and each pixel point is classified and marked according to the criterion of the maximum membership, so as to complete the initial classification; The edgeof the image is extracted from the classification result, and the local window is selected to divide the membership degree again with the edge point as the center pixel. According to the fuzzy membership matrix of clustering output, the membership degree of data points belonging to a certain class is obtained, and each data point is classified and marked according to the maximum probability principle, and the image segmentation is completed. The method of the invention uses a clustering plane instead of a clustering center for image segmentation, can simultaneously consider the gray value information and the position information of pixels, obtains an ideal image segmentation effect, eliminates the influence of noise well, and improves the quality of image segmentation and the stability ofthe segmentation effect.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a fuzzy clustering image segmentation method with anti-noise performance using a plane as a clustering center. Background technique [0002] Image is an important source for human beings to obtain information from the objective world and an important medium for transmitting information. With the development of technologies such as computers and the Internet, digital image processing technology is playing an increasingly important role in industries such as industry, medical care, military affairs, and transportation. [0003] In order to effectively extract and utilize the information contained in the digital image, it is necessary to segment the image. Image segmentation is to divide an image into a group of disjoint sub-regions, which have the same or similar characteristics inside the same region, where the characteristics can be grayscale, color, texture, etc. Image...

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): G06T7/11G06K9/62
CPCG06T7/11G06T2207/10004G06F18/23213
Inventor 张彩明张希静
Owner SHANDONG UNIV
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