An image segmentation method, apparatus, device, and computer storage medium

CN115661162BActive Publication Date: 2026-04-03CHINA MOBILEHANGZHOUINFORMATION TECH CO LTD +1
View PDF -1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-07
Publication Date
2026-04-03

AI Technical Summary

Technical Problem

Existing fuzzy C-means classification algorithms are sensitive to initial values ​​and noise, and are prone to getting trapped in local optima, resulting in inaccurate image segmentation results.

Method used

By combining fuzzy clustering and population genetic algorithms, the initial cluster centers and initial membership matrices are determined, and then corrected using spatial coordination parameters to determine the target cluster centers and target membership matrices, thus introducing spatial information to improve segmentation accuracy.

Benefits of technology

It improves the accuracy of image segmentation, solves the local optima problem of the fuzzy C-means classification algorithm, and enhances robustness to noise and illumination changes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115661162B_ABST
    Figure CN115661162B_ABST
Patent Text Reader

Abstract

This application provides an image segmentation method, apparatus, device, and computer storage medium. The method includes: determining initial cluster centers and an initial membership matrix based on the image to be segmented; determining spatial coordination parameters based on a preset spatial algorithm and the initial membership matrix; correcting the initial cluster centers and the initial membership matrix using the spatial coordination parameters to determine target cluster centers and a target membership matrix; and segmenting the image to be segmented based on the target cluster centers and the target membership matrix. By incorporating spatial information into the correction process of the cluster centers and membership matrices using spatial coordination parameters, more accurate target cluster centers and target membership matrices can be obtained, thereby improving the accuracy of image segmentation.
Need to check novelty before this filing date? Find Prior Art