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

Color image segmenting method based on pixel probability density classification

A probability density and color image technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as inability to achieve effects, susceptible to noise, and failure to consider image spatial characteristics

Inactive Publication Date: 2017-06-09
LIAONING NORMAL UNIVERSITY
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The threshold segmentation method is simple and effective, but this method still has the following shortcomings: first, it is easily affected by noise, and cannot achieve satisfactory results under strong noise interference; second, when traversing pixels in the gray range The efficiency is very low, and the amount of calculation is large; third, the spatial characteristics of the image are not considered, that is, the segmentation of adjacent regions cannot be guaranteed

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
  • Color image segmenting method based on pixel probability density classification
  • Color image segmenting method based on pixel probability density classification
  • Color image segmenting method based on pixel probability density classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The method of the present invention includes four stages: original color image superpixel segmentation, superpixel feature calculation, superpixel image two-dimensional Initial division and utilization of entropy The model performs pixel classification.

[0047] agreement: means the original color image; means a superpixel image; refer to The total number of superpixels in ; refer to The probability density gradient of ; Refers to the entropy rate superpixel generation method; means based on of energy in means based on of The entropy value in; refer to the gray value of; refer to The average gray value of ; Refers to the image classifier;

[0048] a. Initial setup

[0049] Get the original color image and initialize the settings;

[0050] b. Superpixel segmentation of original color image

[0051] use RAW color image Segmentation, generating superpixel images ;

[0052] c. Superpixel feature calculation

[0053] c.1 Calcula...

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 color image segmenting method based on pixel probability density classification; the method comprises the following steps: firstly using an entropy rate super pixel forming method to segment an original color image, thus obtaining a super pixel image; secondarily calculating a super pixel energy feature and an entropy value feature based on pixel probability density gradient; then using two dimensional entropy to primarily segment the formed super pixel image; finally using a classifier to segment the image. Test results show that the super pixel is introduced, so the color component correlation is considered when calculating the super pixel features, and the classifier with high performance is employed for segmentation, thus greatly improving image segmentation precision and speed.

Description

technical field [0001] The invention relates to an image segmentation method based on threshold segmentation, in particular to a color image segmentation method based on pixel probability density classification, and belongs to the technical field of digital image segmentation. Background technique [0002] With the development of science and technology, people's demand for information is increasing day by day, how to effectively select useful information from massive information is the key issue of information processing. Image processing, as the most common form of information processing, is also developing continuously, and image segmentation, as the central link of image processing, has received extensive attention. Generally speaking, people are only interested in a specific part of an image, which is called the object, and the rest is called the background. In multimedia information processing, image segmentation is often essential, and its purpose is to distinguish 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 Applications(China)
IPC IPC(8): G06T7/11G06T7/136
CPCG06T2207/10024
Inventor 王向阳王倩杨红颖牛盼盼
Owner LIAONING NORMAL UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com