Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Manifold-learning-based sectional drawing method

A technique of manifold learning and image matting, which is applied in the fields of computer vision and image processing, and can solve problems such as spatial information redundancy

Inactive Publication Date: 2017-06-09
XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problem of spatial information redundancy in the existing matting methods, the present invention provides a matting method based on manifold learning

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
  • Manifold-learning-based sectional drawing method
  • Manifold-learning-based sectional drawing method
  • Manifold-learning-based sectional drawing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] refer to figure 1 , the key steps that the present invention realizes are as follows:

[0049] Step 1, PAMM local modeling

[0050] For the problem of matting, the first thing to consider is the spatial structure relationship between pixels, so it is necessary to define a local small window of the image. Other pixels in the small window centered on pixel i are the neighbors of the spatial relationship. These pixel points is very close to pixel i. The RGB color information of pixel i is defined as I i ,I i The nearest neighbors are defined as and i j Represented in the local small window w i ={i 1 ,...,i p} The jth nearest neighbor point in}, usually defines a 3×3 small window, i is the center point of the small window, defined as formula (1)

[0051]

[0052] where p is the pixel index number within the local small window.

[0053]In order to achieve the purpose of matting, a basic assumption is: the RGB three color channels of natural images have their c...

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 present invention relates to the field of computer vision and image processing, and more particularly to a manifold-learning-based sectional drawing method. According to the manifold-learning-based idea, a relationship between image color subspace and alpha subspace is dug deeply, so that a local data redundancy problem of sectional drawing can be solved. On the basis of qualitative and quantitative experiment comparison, the manifold-learning-based sectional drawing method has characteristics of high precision and universal adaptability and thus has the great practical application value.

Description

technical field [0001] The invention belongs to the technical field of computer vision and image processing, in particular to a method for matting based on manifold learning. Background technique [0002] Foreground extraction refers to a task of identifying and extracting objects of interest from real images. It is a branch of image segmentation and one of the key problems in the fields of computer vision and pattern recognition. Image segmentation plays an important role in image analysis and image processing research, and is an important link in image processing. Image segmentation can not only test the effect of image preprocessing, but also lay a solid foundation for subsequent image analysis and processing. Since its inception, image segmentation has been widely used in many fields, which has made a significant contribution to the improvement of image processing level in people's life, and also played a great role in promoting the improvement of human productivity an...

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): G06T7/11G06T7/194
CPCG06T2207/10024
Inventor 李学龙刘康董永生
Owner XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
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
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