GrabCut texture image segmentation method based on Gabor transform

A texture image and image technology, applied in the field of GrabCut texture image segmentation based on Gabor transform, can solve the problem that it is difficult to obtain the global joint distribution

Inactive Publication Date: 2017-05-31
BEIJING UNION UNIVERSITY
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In 1979, Yokoyama et al. proposed the Markov random field (MRF) model, which regards texture as a random two-dimensional image field, and assumes that the value of a certain point is related to the value of surrounding pixels, and this assumption is passed through local features. distribution is difficult to obtain a global joint distribution

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
  • GrabCut texture image segmentation method based on Gabor transform
  • GrabCut texture image segmentation method based on Gabor transform
  • GrabCut texture image segmentation method based on Gabor transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] The present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.

[0079] Such as figure 1 As shown, step 100 is executed. In order to calculate the multi-scale and multi-directional texture features of a discrete two-dimensional image, the image I needs to be transformed into a frequency-domain spatial representation. Suppose G(x, y) is a two-dimensional differentiable smooth function, for the Gabor function, its definition is as follows:

[0080]

[0081] where: σ x , σ y They are the scaling coefficients corresponding to the Gabor function along the x-direction and y-direction, and G(x, y) is used as the parent function of the Gabor wavelet transform. Through appropriate rotation and scaling, a group of filters with similar shapes and differences in direction and scale can be obtained group, and obtain a multi-scale and multi-directional Gabor filter group by scaling and rotating the image space, nam...

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 provides a GrabCut texture image segmentation method based on Gabor transform. The method comprises the following steps that: transforming a two-dimensional image into frequency domain space representation through Gabor wavelet transform, calculating the parametric transform of a frequency spectrum space two-dimensional Gabor filter group to obtain multi-scale multi-direction texture features, constructing a multi-scale texture energy generic function, calculating the GMM (Gaussian Mixture Model) probability distribution model of the texture features, and introducing the GMM of the texture features into GrabCut for image segmentation. The GrabCut texture image segmentation method based on the Gabor transform has the characteristics of being simple in artificial interaction, high in processing speed, good in image segmentation effect and the like.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a Gabor transform-based GrabCut texture image segmentation method. Background technique [0002] Texture images occupy a large proportion in natural images, and the diversity and complexity of the real world lead to the randomness and diversity of texture images. The traditional color-based feature description method lacks the ability to describe scales and directions, making texture objects of different scales and directions in the same image useless to use color features to describe them. [0003] The patent document whose publication number is CN101493932A discloses a watershed texture image segmentation method based on morphological Haar wavelet texture gradient extraction. TG; (2) Rotate the source image 90 degrees clockwise and use the morphological Haar wavelet to extract its texture gradient map RTG; (3) Rotate and weight the texture gradient map RTG and...

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): G06T7/11
CPCG06T2207/20064
Inventor 袁家政刘宏哲谭智勇
Owner BEIJING UNION UNIVERSITY
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