Image Segmentation Method Based on Superpixel and Immune Sparse Spectral Clustering

An image segmentation and super-pixel technology, applied in the field of image processing, can solve the problems of low computational complexity and low segmentation accuracy, and achieve the effect of improving segmentation accuracy and accuracy

Active Publication Date: 2022-03-04
XIDIAN UNIV
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method does not require prior knowledge and has low computational complexity, it still has the disadvantage of low segmentation accuracy.

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
  • Image Segmentation Method Based on Superpixel and Immune Sparse Spectral Clustering
  • Image Segmentation Method Based on Superpixel and Immune Sparse Spectral Clustering
  • Image Segmentation Method Based on Superpixel and Immune Sparse Spectral Clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0025] Step 1, input the image to be segmented.

[0026] Select a texture image whose size is A=256*256 from the database as the input image to be segmented.

[0027] Step 2, the image to be segmented is divided into superpixels.

[0028] Existing methods for dividing superpixels include methods based on graph theory, methods based on entropy rate, method Meanshift based on gradient descent, simple linear iterative clustering method SLIC and level set method Turbopixels based on geometric flow, etc. In this example, the simple linear iterative clustering method SLIC is used to divide the image to be segmented into n superpixels. The implementation steps are as follows:

[0029] (2a) Evenly select n pixels in the image to be segmented as initial seed points, assign a label to each initial seed point, each seed point contains A / n pixel points, and the distanc...

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 an image segmentation method based on superpixels and immune sparse spectrum clustering, which mainly solves the problems of low segmentation accuracy and poor robustness of the existing image segmentation methods. The steps of the method are as follows: first, divide the texture image into superpixels, extract its texture features, and use it as a feature data set; then, in the process of spectral clustering, combine the immune cloning algorithm and sparse representation to find the best similarity of the feature data set matrix; finally, the original image is marked according to the clustering label combined with superpixels to realize the segmentation of the texture image. The invention extracts the superpixel block of the image as a feature data set, and uses the image segmentation method based on immune sparse spectrum clustering to divide the feature data set, and obtains more accurate segmentation results.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image segmentation technology, which can be used for target recognition. Background technique [0002] Commonly used methods for image segmentation include threshold-based segmentation methods, edge-based segmentation methods, and region-based segmentation methods. With the development of pattern recognition and artificial intelligence theory, segmentation methods combined with specific theories have also been widely used. For example, based on Clustering segmentation technology, segmentation technology based on artificial neural network, segmentation technology based on genetic algorithm, etc. Among the existing clustering methods, spectral clustering is a clustering method with good characteristics of simple implementation, dimension-independent and global optimization. Applying spectral clustering to image segmentation is a hot research direction in th...

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 Patents(China)
IPC IPC(8): G06T7/10G06V10/762G06K9/62G06N3/00
CPCG06N3/006G06T7/10G06T2207/10004G06F18/23
Inventor 尚荣华刘爽焦李成刘芳尚凡华王蓉芳侯彪王爽马文萍
Owner XIDIAN 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