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

Image Segmentation Method Based on Non-Gaussian hmt Model

An image segmentation and image technology, applied in the field of image segmentation based on non-Gaussian HMT model, can solve the problems of not considering spatial features, poor robustness, poor image segmentation effect, etc., achieve high data redundancy and improve accuracy Effect

Active Publication Date: 2021-11-19
LIAONING NORMAL UNIVERSITY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above methods have their own advantages, they all have disadvantages, such as not suitable for images with inconspicuous peaks and uneven illumination, poor image segmentation effect for complex scenes, poor robustness, and no consideration of spatial features, etc.

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 Non-Gaussian hmt Model
  • Image Segmentation Method Based on Non-Gaussian hmt Model
  • Image Segmentation Method Based on Non-Gaussian hmt Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The method of the present invention is as image 3 There are five stages shown: image UDTCWT transform high-frequency sub-band acquisition, coefficient relative phase Vonn modeling, initial segmentation with maximum likelihood, pixel-level segmentation results using Cauchy spatial modeling method, and context-based multi-scale The fusion method performs image fusion.

[0030] Convention: I represents the image to be segmented; UDTCWT refers to the non-subsampled dual-tree complex wavelet transform; LL refers to the low-frequency sub-band obtained through the UDTCWT filter, HH represents the high-frequency sub-band, J represents the UDTCWT decomposition series; y(j,k ) represents the complex subband coefficient; a is the real subband of y(j,k), b is the imaginary subband; i is the imaginary unit; ∏ is the parameter of the UDTCWT-HMT model estimated by EM; p(S i =m,∏) is the joint probability of the state obtained by ∏; θ is the relative phase; S i is the hidden state o...

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 a non-Gaussian HMT model. Firstly, the texture image is transformed by UDTCWT, and the real part and the imaginary part of the high-frequency sub-band obtained by the transformation are respectively subjected to relative phase calculation; secondly, the Vonn distribution function is applied to the The relative phase is statistically modeled and the maximum likelihood calculation method is used for initial segmentation; then, the pixel-level segmentation method based on the Cauchy mixture model is applied to obtain the pixel-level segmentation results of the image; finally, the context-based multi-scale fusion method is used for fusion to obtain The final image segmentation result.

Description

technical field [0001] The invention belongs to the technical field of digital image segmentation, and relates to an image segmentation method based on relative phase modeling, in particular to an image segmentation method based on a non-Gaussian HMT model. Background technique [0002] In multimedia information processing, image segmentation is often essential, and its purpose is to distinguish the object and background in the image, so that people can study the object area. Image segmentation can also be used in many fields such as medicine, military, industry, etc. Although there are various image segmentation methods, due to the complexity of images, there is no standard segmentation method suitable for all different types of images. Therefore, image segmentation technology is still one of the hotspots of current research. [0003] Due to the different types of image objects and backgrounds, how to effectively extract objects from different backgrounds has become a comp...

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): G06T7/10G06T7/40
CPCG06T7/40G06T2207/20064G06T2207/20076G06T7/10
Inventor 王向阳王倩牛盼盼
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