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

Motion blurred image blind restoration method based on multi-scale self-similarity

A motion blurred image, blurred image technology, applied in image enhancement, image data processing, instruments, etc., can solve the problem of poor image effect

Active Publication Date: 2013-10-02
NORTHWESTERN POLYTECHNICAL UNIV
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of the existing image blind restoration methods with poor image restoration effects, the present invention provides a blind restoration method for motion blurred images based on multi-scale self-similarity

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
  • Motion blurred image blind restoration method based on multi-scale self-similarity
  • Motion blurred image blind restoration method based on multi-scale self-similarity
  • Motion blurred image blind restoration method based on multi-scale self-similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The specific steps of the method for blind restoration of motion blurred images based on multi-scale self-similarity of the present invention are as follows:

[0039] 1. Perform multi-scale down-sampling on blurred image B, respectively B o , B 1 ,...B s ,..., B S , Where S is the number of downsampling, B 0 = B, B s =DB s-1 , D is the downsampling operator. The smaller the s, the larger the image scale, when s=0, it is the original blurred image. In this example, S=3, D is 0.5 times downsampling, such as B s-1 The image size is 256×256, then after B s =DB s-1 After B s The image size is B s-1 0.5 times of that is 128×128.

[0040] 2. The fuzzy image with scale s from 3 to 0 is optimized and solved according to the following optimization function:

[0041] { K s , L s } = arg min K s , L s { α | | B s - K s ⊗ L s | | 2 2 + λ | | L s - L s ′ | | 2 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 discloses a motion blurred image blind restoration method based on multi-scale self-similarity, which is used for solving the technical problem that the available image blind restoration method is poor in image restoration effect. The method adopts the technical scheme that the multi-scale self-similarity characteristic of an image serves as prior information to be introduced into the image restoration problem; a clear image estimated by the previous scale serves as prior restriction of a next scale to conduct image restoration; a ring effect of the restoration image on a strong edge is reduced; and a clearer image can be obtained. The method improves the image restoration effect.

Description

Technical field [0001] The invention relates to an image blind restoration method, in particular to a motion blur image blind restoration method based on multi-scale self-similarity. Background technique [0002] The document "Robust Blind Restoration of Motion Blurred Images Based on Edge Information, Optoelectronic Laser, 2011, Vol22(10), p1982-1989" proposes a robust method to obtain blur kernels from a single blurred image and deblur the image Image blind restoration method. This method first estimates the edge information of the unblurred image through the bilateral filter and the shock filter, and then calculates the blur kernel according to the edge relationship between the blurred image and the unblurred image, and finally, sets up the sub-algorithms in a multi-scale framework. Determine the adaptive parameters and construct a robust blind image restoration method. This method has a good restoration effect on blurred degraded images. It not only effectively removes moti...

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): G06T5/00
Inventor 张艳宁李海森张海超孙瑾秋
Owner NORTHWESTERN POLYTECHNICAL 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