Image matting method and device

A technology in images and images, applied in the field of image processing, can solve problems such as unsatisfactory effects, mistakes, inaccurate manual division, etc., and achieve the effect of solving poor matting effects and improving quality and effect.

Inactive Publication Date: 2016-07-27
LEADCORE TECH
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, manually dividing the foreground, background and unknown regions of the image often makes mistakes, and the manual division is inaccurate. Therefore, the effect of using the Bayes method is not ideal.

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 matting method and device
  • Image matting method and device
  • Image matting method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] see figure 1 , an image matting method provided in this embodiment specifically includes: operation 11 and operation 12.

[0022] In operation 11, the image to be processed is divided by clustering to obtain a foreground area, a background area and an unknown area.

[0023] For example, you can draw a line in the foreground and background in the image for clustering. Specifically, it may include:

[0024] receiving a drawing operation command performed on the first area and the second area of ​​the image to be processed;

[0025] drawing a first line in the first area of ​​the image to be processed according to the drawing operation command, and drawing a second line in the second area;

[0026] clustering the pixels in the image to be processed by using the first line and the second line as initial clustering centers;

[0027] The image to be processed is divided according to the clustering result, which improves the precision of division.

[0028] The image is di...

Embodiment 2

[0056] On the basis of the foregoing embodiments, this embodiment provides a method for dividing an image to be processed through clustering.

[0057] see figure 2 The method for dividing the image to be processed by clustering provided in Embodiment 2 specifically includes: operation 21-operation 25.

[0058] In operation 21, two lines are drawn on the input image.

[0059] Here, the input image is the image to be processed, that is, the image to be matted. These two lines represent the foreground and background of the image, respectively. Since the user can see the foreground area and the background area of ​​the image, the user can draw a line in the foreground area and a line in the background area through terminal operations.

[0060] In operation 22, the pixel point sets F and B are divided.

[0061] Specifically, according to these two lines, the GraphCut algorithm is used to divide the foreground pixel point set F, the background pixel point set B and the unknown pi...

Embodiment 3

[0079] This embodiment provides another image matting method on the basis of the foregoing embodiments.

[0080] see image 3 , the image matting method provided in this embodiment specifically includes: operation 31-operation 34.

[0081] In operation 31, the image area is divided.

[0082] Specifically, the whole picture can be divided into foreground area, background area and need to calculate Unknown range of values. in, The value refers to the proportion of the foreground color, or indicates the degree of opacity. In a composite image, C, F and B denote the synthetic image, foreground image and background image respectively, correspondingly, C(x, y), F(x, y) and B(x, y) denote the synthetic color, foreground color and background color.

[0083] In this operation, the method of combining the GraphCut algorithm and clustering can be used to divide the image. For details, please refer to the description in the above-mentioned embodiments, which will not be repeated...

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 matting method and device. The image matting method comprises the following steps: images to be processed are divided via clustering operation into foreground areas, background areas and unknown areas; the images to be processes are matted based on the foreground areas, the background areas and the unknown areas; a problem that poor image matting effects are caused due to manual dividing operation faults and inaccuracy via use of technologies of the prior art is solved, and image matting quality and effects are improved.

Description

technical field [0001] Embodiments of the present invention relate to image processing technologies, and in particular to an image matting method and device. Background technique [0002] Digital matting technology is an image processing technology that separates a part of an image from other parts, referred to as matting. Cutouts include blue screen cutouts with known backgrounds and natural image cutouts with unknown backgrounds. [0003] Among them, the methods used in natural image matting include Knockout method, Poisson method, matting based on perceptual color space and Bayesian (Bayes) method, etc. [0004] In the prior art, when the Bayes method is used for image matting, the foreground, background and unknown regions of the image are first manually divided, and then the image is segmented based on the divided foreground region, background region and unknown region to achieve matting. [0005] However, manual division of the foreground, background and unknown regi...

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): G06T7/00
Inventor 方圆圆
Owner LEADCORE TECH
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