Mixed order l 0 Regularized Blur Kernel Estimation Method

A fuzzy kernel, mixed-order technology, applied in the field of image processing, can solve the problems of single, misjudged as the edge of the image, inaccuracy, etc.

Active Publication Date: 2019-07-05
上海厉鲨科技有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the image contains rich details or a large blur scale, the blur kernel estimated by the current method is generally not ideal, and the image restored from the inaccurate blur kernel will naturally produce different degrees of ringing effect
[0005] Through analysis, when the image details are rich or the blur scale is large, the existing processing techniques are: 1) impose a single first-order regularization constraint on the image, resulting in an accurate estimation of the blur kernel; 2) according to the magnitude of the image edge instead of If the scale is used to estimate the blur kernel, it is easy to misjudge the details of the image as the edge of the image, resulting in inaccurate blur kernel estimation

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
  • Mixed order l  <sub>0</sub> Regularized Blur Kernel Estimation Method
  • Mixed order l  <sub>0</sub> Regularized Blur Kernel Estimation Method
  • Mixed order l  <sub>0</sub> Regularized Blur Kernel Estimation Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention implements estimation of accurate blur kernels on a multi-scale framework. The multi-scale framework is composed of multi-layer image pyramid models with resolutions ranging from low to high. The pyramid model can effectively avoid local optimal solutions and ensure that the final solution converges to the global optimal solution, especially when the degree of blur is serious in the case of.

[0043] For each layer in the image pyramid model, the present invention implements the proposed blur kernel estimation method on the high-frequency components of the image.

[0044] Such as figure 1 As shown, a mixed-order L-based 0 A regularized fuzzy kernel estimation method, comprising the following steps:

[0045] Step 1: Establish the blur kernel estimation model, input the initial blur image, and get the estimated blur kernel.

[0046] Step 2: According to the estimated blur kernel, the initial blurred image is restored to obtain the intermediate cl...

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 provides a regularization fuzzy kernel estimation method based on the mixed order L0. The method is characterized by comprising the steps of subjecting an intermediate clear image in a fuzzy kernel estimation model to the regularization constraint at the mixed order L0, protecting the edge of the image by utilizing the first-order constraint, inhibiting the ringing effect generated by the first-order constraint by utilizing the second-order constraint, restoring a clear intermediate image, adding an improved adaptive adjustment factor in the fuzzy kernel estimation model, and extracting more obvious edge information beneficial to fuzzy kernel estimation from the intermediate clear image. According to the technical scheme of the invention, based on the semi-quadratic variable splitting technology, a proposed fuzzy kernel estimation model can be solved. Meanwhile, the experimental results of artificial blurred images and real blurred images prove that, the fuzzy kernel estimation method provided by the invention is effective and restored images are obviously improved in subjective visual effect and objective evaluation index compared with most representative methods in recent years.

Description

technical field [0001] The present invention relates to an image processing method, in particular to a method based on the mixing order L 0 Regularized Blur Kernel Estimation Method. Background technique [0002] In the process of image acquisition, transmission, and storage, due to the influence of factors such as physical defects of the imaging equipment itself, changes in the external environment, and improper operation of the operator, it is inevitable that the image will be degraded to varying degrees. Not only seriously affect the visual effect of the image, but also greatly reduce the practical application value. As a result, image restoration technology emerged as the times require, and has been widely used in astronomical observation, medical imaging, video multimedia, criminal investigation and other fields. At present, many image restoration methods require more prior information, or have disadvantages such as poor effect and high algorithm complexity. For this...

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
CPCG06T5/003G06T2207/20056
Inventor 李伟红陈扬清龚卫国陈蕊
Owner 上海厉鲨科技有限公司
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
Try Eureka
PatSnap group products