Image segmentation method based on a secondary confinement region growth method

A technology for limiting areas and image segmentation, applied in image analysis, image data processing, instruments, etc., can solve problems such as being easily affected by noise, and achieve good results, easy control, and more complete areas

Active Publication Date: 2019-05-24
西安波普索尔网络科技有限公司
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies in the above-mentioned prior art, the present invention proposes a simple, accurate, and easy-to-implement image segmentation method, aiming to solve the problem of seed point distribution and coverage for region growth, pixel spatial relationship utilization, and segmentation effect in Hidden Markov Problems in Models Susceptible to Noise

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 a secondary confinement region growth method
  • Image segmentation method based on a secondary confinement region growth method
  • Image segmentation method based on a secondary confinement region growth method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0117] Fig. 4 is a comparison diagram of common image segmentation effects, wherein Fig. 4(a) is the original image, and Fig. 4(b) is the result processed by the method of the present invention. In this embodiment, using the algorithm of the present invention, the number of seed points is set to 200 in step 2, the threshold is set to 30, the number of initial regions is 8 in step 5, the number of iterations is 30, and the predetermined value of energy change is 0. Fig. 4 (a) original picture is processed according to the method of the present invention, obtains the result image of Fig. 4 (b); As a comparison result, Fig. 4 (c) is the effect of the image segmentation algorithm based on the pixel point application hidden Markov model , the results are all obtained under the same clustering number, iteration times and energy change predetermined value settings, it can be seen that the pixel-based hidden Markov model divides objects of different categories such as planks and fruits...

Embodiment 2

[0119] In order to illustrate the segmentation effect of the method of the present invention when the image texture and details are relatively rich, the image in Figure 5(a) is used as the processing object for processing, which is implemented as this embodiment, and Figure 5(a) is without The original figure of processing, Fig. 5 (b) is the result figure after the process of the inventive method, in the application of the inventive method, in the step 2, the number of seed points is set to 200, and the threshold is set to 40, and in the step 5, the number of initial regions is 5, the number of iterations is 30, and the predetermined value of energy change is 0. Input figure (a) to get the result of figure (b). As a comparison result, Figure (c) is the effect of the image segmentation algorithm based on the application of the hidden Markov model based on the pixels of the original image. The results are all obtained under the same cluster number, iteration number and energy ch...

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 belongs to the technical field of image segmentation, and particularly relates to an image segmentation method based on a secondary confinement region growth method, which comprises thefollowing steps: step 1, converting an image from an RGB space into a Lab space; step 2, setting the number of seed points and a threshold value, throwing the seed points, and marking the image by using a limited area growth method and the threshold value; step 3, traversing the whole image according to a grating scanning sequence to carry out secondary limited region growth, and marking each unmarked point; step 4, calculating a mean value of wave bands of the superpixel blocks divided in the last two steps; And step 5, setting a predicted classification number, and combining the superpixel results obtained in the step 3 by using a simulated annealing algorithm based on a hidden Markov model, an Isinuous model and a Gaussian function to obtain a final segmentation result. According to theimage segmentation method disclosed by the invention, a region growth limiting method is used, so that each seed point performs region growth in an image range of the step size multiplied by the stepsize, the calculation workload is reduced, and the operation speed is increased.

Description

technical field [0001] The invention belongs to the technical field of image segmentation, and relates to digital image segmentation, in particular to an image segmentation method based on a quadratic limited region growing method. Background technique [0002] The purpose of image segmentation is to classify all pixels in an image into meaningful categories. Accurate image segmentation results are the premise and basis for technologies such as object recognition and automatic driving. Image segmentation can be divided into two categories: traditional machine vision-based segmentation and neural network-based segmentation. [0003] Traditional machine vision segmentation algorithms include region growing method, SLIC segmentation algorithm, Markov random field algorithm and so on. The region growing method is a relatively common and widely used image segmentation method. Its algorithm is simple, but it does not consider the local relationship between image pixels and objec...

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): G06T7/11G06T7/187G06T7/143
Inventor 朱娟娟刘硕珣郭彦宗朱倩蓓
Owner 西安波普索尔网络科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap