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

Intrinsic image decomposition method based on multi-scale L0 sparse constraint

A sparse constraint, intrinsic image technology, applied in the field of image processing, can solve the problem of unreliable chrominance values, and achieve the effect of improving accuracy

Inactive Publication Date: 2015-04-01
TIANJIN UNIV
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods all rely on chroma values, which are sometimes unreliable

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
  • Intrinsic image decomposition method based on multi-scale L0 sparse constraint
  • Intrinsic image decomposition method based on multi-scale L0 sparse constraint
  • Intrinsic image decomposition method based on multi-scale L0 sparse constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the implementation manners of the present invention will be further described in detail below.

[0027] The invention proposes a layered iterative method for eigendecomposition of a single image. First, use the chromaticity of the image as the initial reflectance component, and then use the zero paradigm sparse constraint to solve the similarity measure of the reflectance component of this layer, and then obtain the reflectance component and illumination component of this layer by optimizing an energy function, and bring it into For the next iteration or output result, the specific technical solution includes the following content: Let M be the number of layers, obtain an image pyramid through up-sampling and down-sampling, and iterate the following steps M times.

[0028] 101: Initialize reflectivity component

[0029] That is, let the input image be I, the ratio of adj...

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 intrinsic image decomposition method based on multi-scale L0 sparse constraint. The method includes the following steps that reflectivity components (please see the symbol in the specification) are initialized, and a non-local zero paradigm sparse constraint model is used for obtaining a similarity measure WR of the reflectivity components among pixels; a similarity measure WS of the illumination components among the pixels is calculated; the reflectivity component R and the illumination component S of the layer are obtained by solving an optimization problem. Experimental results show that non-local zero paradigm sparse constraint can ensure global consistency of intrinsic image decomposition, by using the hierarchical iteration method, the efficiency problem of non-local zero paradigm sparse constraint expression is solved, and dependency on the chromaticity characteristics is reduced. According to standard data and tests, the accuracy of the results of the method is improved substantially, so that the intrinsic image decomposition method is beneficial for improving the results of intrinsic image decomposition.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an intrinsic image decomposition method based on multi-scale L0 sparse constraints. Background technique [0002] The goal of intrinsic image decomposition is to decompose the image into material-dependent parts and lighting-dependent parts, namely reflectance components and lighting components. Barrow and Tenenbaum [1] Firstly, the decomposition method of this kind of picture is proposed, and the reflectance component and illumination component are called the essential characteristics of the image. Because each part of the decomposition represents a different physical element, intrinsic image decomposition has applications in many problems in computer vision and computer graphics, such as: recoloring [2] , image segmentation and object recognition [3] Wait. [0003] But this problem is still a challenging problem because of its serious ill-posed characteristics, that is, give...

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): G06T7/00G06T5/00
CPCG06T7/49
Inventor 冯伟万亮聂学成戴海鹏
Owner TIANJIN 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