Unlock instant, AI-driven research and patent intelligence for your innovation.

Blur Kernel Computation Method for Motion Blurred Image Restoration

A motion blurred image and calculation method technology, applied in the field of blur kernel calculation, can solve the problems of long time consumption, unsatisfactory deblurring effect, slow calculation and operation of blurring kernel parameters, etc., and achieve short time consumption, fast calculation speed and deblurring effect Good results

Active Publication Date: 2019-11-12
SOUTHEAST UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: The purpose of the present invention is to provide a blur kernel calculation method for motion blurred image restoration, to solve the problem of unsatisfactory deblurring effect, slow calculation of blur kernel parameters, and long time-consuming problems

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
  • Blur Kernel Computation Method for Motion Blurred Image Restoration
  • Blur Kernel Computation Method for Motion Blurred Image Restoration
  • Blur Kernel Computation Method for Motion Blurred Image Restoration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings.

[0020] Such as Figure 1-2 As shown, a blur kernel parameter estimation method for motion blur image restoration, including the following steps:

[0021] (1) Establish an image degradation model. The key to image deblurring is to establish an image degradation model. For digital images, the formation of motion blurred images can usually be described as the convolution process of the original clear image I(x,y) and the blur kernel h(x,y). If the noise exists, the influence of noise should be considered, generally assuming that the noise is additive noise, the process can be expressed as:

[0022] g(x,y)=h(x,y)*I(x,y)+n(x,y) (Formula 1)

[0023] Among them, * indicates convolution operation, n(x,y) indicates additive noise, g(x,y) indicates blurred image, I(x,y) indicates clear image, and h(x,y) indicates blurred image The blur kernel determined by the two parameters...

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 fuzzy kernel calculation method for motion blurred image restoration. The invention is a fuzzy kernel parameter estimation algorithm based on sparse characteristics, super Laplacian prior and integrated BP neural network. First, in the image gray gradient Under the constraints of the super Laplace distribution, the blur angle of the blur image is determined by analyzing the sparse representation coefficients of the blur image; then, the sum of the Fourier coefficient amplitudes obtained after the Fourier transformation of the blur image is used as input, and The integrated BP neural network model based on the bagging method is trained to complete the estimation of the blur length; finally, the deblurred image is obtained through a one-step deblurring algorithm with a known blur kernel. The present invention estimates blur kernel parameters accurately, has fast calculation speed, short time consumption, and good deblurring effect. By restoring the motion blurred image through the present invention, the edges of the restored image can be made clearer and the ringing effect is less.

Description

technical field [0001] The invention relates to image signal processing, in particular to a blur kernel calculation method for motion blur image restoration. Background technique [0002] Blurred images are usually caused by relative camera or object motion, atmospheric turbulence, camera out of focus, and data loss during data transmission. Deblurring of motion blurred images is one of the important topics in image restoration. According to whether the blur kernel is known, image deblurring can be divided into non-blind and blind deblurring. When the blur kernel is known, it is called non-blind deblurring. From a mathematical point of view, the main purpose of non-blind image deblurring is to implement a deconvolution and add appropriate constraints in the solution process. At present, non-blind image deblurring technology is quite mature and has been successfully applied in many scientific research fields. On the other hand, blind image deblurring techniques need to au...

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): G06T5/00G06N3/08
CPCG06N3/084G06T2207/20084G06T2207/20081G06T5/73
Inventor 陈熙源柳笛方文辉刘晓
Owner SOUTHEAST UNIV