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

Image foreground extracting method based on Gaussian variation model

A foreground extraction and image technology, applied in the field of image processing, can solve the problems of recognition accuracy and precision need to be improved

Inactive Publication Date: 2015-04-01
EAST CHINA UNIV OF SCI & TECH
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above methods have achieved good results, the accuracy and precision of recognition need to be improved

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 foreground extracting method based on Gaussian variation model
  • Image foreground extracting method based on Gaussian variation model
  • Image foreground extracting method based on Gaussian variation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Step 1, use the Ncut technology to perform region segmentation on the target image, and obtain the region segmentation map of the target image.

[0025] Step 2: Perform sharpening processing on the original target image to obtain a sharpened image, perform Gaussian variation model foreground extraction on the sharpened image in RGB space, and obtain Gaussian variation points.

[0026] We perform Gaussian convolution on each pixel in the image, as shown in the following formula (1), G is the Gaussian function, I is the pixel in the image, and we let the pixels in the image be convolved with the Gaussian function. L is the matrix obtained after convolution. σ is the scale of the Gaussian function, and our value for σ is 1.6.

[0027] L(x,y,σ)=G(x,y,σ)*I(x,y) (1)

[0028] In formula (2), we get the Gaussian variation D, which represents the difference between the Gaussian convolution of the original image at different scales.

[0029] D(x,y,σ)=L(x,y,kσ)-L(x,y,σ) (2)

...

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 novel method for automatic foreground extraction. Under the general conditions, the foreground extraction is interactive, and a foreground region needs an interactive labeling process. According to the method, an image is subjected to Gaussian variation processing to obtain a Gaussian variation point, then, the Gaussian variation point is subjected to marginalization processing by combining a Ncut technology, and marginal information of the image is obtained; finally, the center focus of the image is selected by a certain method, in addition, a key point is subjected to weighted growth in a direction towards the center focus, and a final foreground positioning point is obtained. The foreground region of a target image can be determined according to the proportion of the foreground positioning point in different regions. The whole process is fully automatic, and any manual interaction is not needed. Lots of experiments prove that the method is very effective, and in addition, more precise experiment results can be obtained.

Description

technical field [0001] The invention mainly relates to image processing technology, in particular to a foreground extraction method based on Gaussian variation. Background technique [0002] In the research of computer image processing, the task of foreground extraction is to separate the object of interest from the background from a single image or a sequence of images for subsequent processing. This is an enduring classic research topic and one of the most basic research topics in computer image processing. Targets of interest generally refer to moving objects in the field of view, which need to be obtained by analyzing sequence images; or specific types of objects, such as faces, vehicles, etc., can be extracted by analyzing single or sequence images. The effective extraction of the foreground area is very important for medium and high-level tasks such as target classification, identity recognition, and behavior understanding, because the subsequent processing usually on...

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
IPC IPC(8): G06K9/46G06K9/54
CPCG06T7/11G06T2207/10004G06T2207/20172
Inventor 袁玉波刘赟戴光辉陈志华张静应方立
Owner EAST CHINA UNIV OF SCI & TECH
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