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.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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