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

An omni-focus image reconstruction method based on multi-scale defocus information

An all-focus image and focus image technology, applied in image enhancement, image data processing, instruments, etc., can solve the problems of not giving a full-focus image, not being able to obtain a full-focus image, etc., to achieve rich detail textures and eliminate defocus blur , no artifact effect

Active Publication Date: 2019-10-18
TIANJIN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above methods are able to estimate the defocus map from a single image, none of these methods give the corresponding omni-focus image
[0004] Aiming at the problem that the existing defocus estimation methods cannot obtain fully focused images, this method combines defocus blur estimation with image deblurring, and proposes a deblurring framework for a single image, which can reconstruct the original blurred image. Potential omni-focus image

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
  • An omni-focus image reconstruction method based on multi-scale defocus information
  • An omni-focus image reconstruction method based on multi-scale defocus information
  • An omni-focus image reconstruction method based on multi-scale defocus information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] An embodiment of the present invention provides an all-focus image reconstruction method based on multi-scale defocus information, see figure 1 , the method includes the following steps:

[0029] 101: Construct and solve a multi-parameter regular optimization model by combining the Tychonoff regular term with the Huber function;

[0030] 102: Using a multi-scale selection strategy to reconstruct an all-in-focus image corresponding to the original defocused image;

[0031] In summary, the image restored by the omni-focus image reconstruction method proposed by the embodiment of the present invention contains richer detail textures, less distortion, no artifacts, and is clearer and more natural.

Embodiment 2

[0033] The method in embodiment 1 is verified below in conjunction with specific accompanying drawing, see the following description for details:

[0034] The embodiments of the present invention verify the effectiveness of the algorithm by comparing the subjective experimental results and the evaluation scores of the objective LR criterion. The parameter setting of the multi-scale defocus estimation method proposed by the embodiment of the present invention is: α=22, μ 1 =0.9,μ 2 = 0.1, fuzzy scale {σ 1 ,σ 2 ,...,σ m} starts at 0.4 px and increases to 4.6 px in steps of 0.3 px.

[0035] 1. Subjective experiment

[0036] The method proposed in the embodiment of the present invention is different from the kernel estimation algorithm of motion blur [6] , an image restoration algorithm based on grayscale and gradient prior knowledge [7] For comparison, the experimental results are compared with image 3 shown.

[0037] From image 3 It can be seen that this method can o...

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 multi-scale defocusing information-based full-focus image reconstruction method. The full-focus image reconstruction method comprises the following steps of establishing and solving a multi-parameter regular optimization model by combination of a Tikhonov regular term and a Huber function; and reconstructing a full-focus image corresponding to an original defocusing image based on a multi-scale selection strategy. By adoption of the full-focus image reconstruction method disclosed by the invention, the fuzzy textures of the image can be effectively suppressed, the recovered image has more abundant detailed textures, less distortion is achieved, an image artifact phenomenon is avoided, and the image is more clear and natural.

Description

technical field [0001] The invention relates to the field of image reconstruction, in particular to an image reconstruction method based on multi-scale defocus information. The method proposes a multi-scale defocus model, which can be used to reconstruct an all-focus image. Background technique [0002] Image reconstruction is an important research topic in the field of computer vision. The defocus blur of an image tends to vary across the image plane, and this spatially varying defocus blur can guide the reconstruction of an all-in-focus image. Effectively combining defocus blur estimation with image reconstruction techniques, a latent clear image can be reconstructed from a single blurred image. [0003] For the image defocus blur problem, many image defocus estimation methods have been proposed in recent years. These algorithms can be divided into two categories: methods based on multiple images and methods based on a single image. In practical applications, usually onl...

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 Patents(China)
IPC IPC(8): G06T5/00
CPCG06T5/73
Inventor 周圆王爱华庞勃陈阳吴琼李成浩
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