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

Prospect extraction method based on pixel diffusion

A foreground extraction and pixel technology, applied in image analysis, image data processing, instruments, etc., can solve the problem of reducing the speed of foreground extraction, and achieve the effect of reducing the selection of samples, improving the running speed, and improving the speed.

Inactive Publication Date: 2010-10-06
FUDAN UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] However, the current foreground extraction algorithms such as the robust foreground extraction algorithm use sample selection and define the similarity between pixels in different steps, which greatly reduces the speed of foreground extraction

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
  • Prospect extraction method based on pixel diffusion
  • Prospect extraction method based on pixel diffusion
  • Prospect extraction method based on pixel diffusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045]figure 1 It is a flowchart of the present invention, specifically:

[0046] Step 1 Input the original image and the corresponding trimap

[0047] Step 2 determines the foreground sample points, background sample points and unknown pixels.

[0048] Step 3 select an unknown pixel.

[0049] Step 4 calculates the confidence of each foreground-background sample pair for this pixel.

[0050] Step 5 Select the foreground and background sample pair with the highest confidence to calculate the preliminary α value.

[0051] Step 6: Calculate the final α value of the unknown pixel according to the assumed internal relationship between the unknown pixel and the adjacent pixels whose α values ​​have been calculated.

[0052] In step 7, if there are unknown pixels whose α value has not been calculated, go to step 3, otherwise the algorithm ends.

[0053] figure 2 The flow chart of pre-allocating background sample pixels for the present invention is specifically:

[0054] Step 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 belongs to the technical field of image processing, and relates to a quick prospect extraction method, in particular to a method for solving and inputting an unknown pixel alpha value of the image. The method defines and makes full use of the internal relationship between adjacent pixel alpha values so as to achieve the purpose of prospect extraction, and comprises the following steps that: an original image and a corresponding trimap are input, a prospect sample point, a background sample point and an unknown pixel are determined, the unknown pixel is selected, the confidence of each prospect background sample pair of the unknown pixel is calculated, the prospect background sample pair with the high confidence is selected to calculate and obtain the initial alpha value, and the final alpha value of the unknown pixel is calculated and obtained according to the internal relationship. When being used for prospect extraction, the method can achieve similar effect of previous methods, but the speed can be improved by 25 times on average.

Description

technical field [0001] The invention belongs to the technical field of computer digital image processing, and in particular relates to a fast foreground extraction method. Background technique [0002] With the continuous growth of people's cultural needs, the continuous expansion of imagination space, and the continuous emphasis on visual experience, people's requirements for photo processing, poster production and movie special effects are also continuously improved. Extracted from the image to replace it with a new scene, this process is the foreground extraction operation. Although image editing tools such as Photoshop can also be used to achieve the effect of foreground extraction, on the one hand, when the edge of the object is more complicated, the workload of foreground extraction is too large; such as animal hair. So a certain foreground extraction algorithm is needed to achieve this goal. [0003] When using the foreground extraction algorithm for foreground ext...

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): G06T7/00G06T7/40
Inventor 金城顾抑扬薛向阳
Owner FUDAN UNIV
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