Image deblurring method based on nonlinear dynamic system

A nonlinear dynamic and deblurring technology, applied in the field of image processing, can solve the problem of relatively high requirements for potential image strong edge conditions

Active Publication Date: 2018-02-23
DALIAN UNIV OF TECH
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The blur kernel estimated by this method is more robust, but the strong edge condition of the potential image is relatively high when estimating p(k|y)

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
  • Image deblurring method based on nonlinear dynamic system
  • Image deblurring method based on nonlinear dynamic system
  • Image deblurring method based on nonlinear dynamic system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific examples. These examples are illustrative only and not limiting of the invention. Such as figure 1 shown.

[0055] Step 100: read in a blurred image, such as figure 2 . The blur kernel k is initialized according to the blurred image, and the blur kernel is set to a size of 45×45 squares in this example.

[0056] Step 200: Based on the maximum a posteriori probability framework, and based on the problem model and the prior of the latent image x, an energy function about x is established:

[0057]

[0058] where weight α=2 is set, f, φ and g are filter, sparse function and guide respectively. The training method is used to learn the filter f, the sparse function φ and the guide g respectively. Specific practices include:

[0059] Step 201: Learn...

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 belongs to the field of image processing, and particularly relates to a learning-based nonlinear dynamic system deblurring method. The method comprises the steps that firstly, for an image to be deblurred, the kernel estimation energy is controlled by a learnable non-linear dynamic system; secondly, after continuous iteration of a latent image and a fuzzy kernel, great fuzzy kernel estimation is acquired; and finally, the problem of blind deblurring is transformed into the problem of non-blind deblurring, and various existing non-blind deblurring methods can be used for solving.The method has the advantages that 1 a new principle for deblurring is provided, and the learnable dynamic system instead of manually set regularization is used to control kernel estimation; 2 a new structure is designed to learn components in the dynamic system, and a suitable and flexible deblurring system is acquired through the structure; and 3 the method involves a residual network proposed recently, which brings new ideas to image processing and deep learning.

Description

technical field [0001] The invention belongs to the field of image processing and relates to image deblurring, in particular to a learning-based nonlinear dynamic system deblurring method. Background technique [0002] Image deblurring is an important research direction in the field of image processing, and it is also an indispensable prerequisite for image feature extraction and image classification in the process of image preprocessing. There are many reasons for image blur, such as inaccurate focus, aberrations of the optical system, relative motion during the imaging process, atmospheric turbulence effects, random noise in the environment, etc. will all lead to blurred images. A model describing this process can be summarized as: Among them, k is the point spread function of the blur kernel, x is the potential clear image, n is the noise, is a two-dimensional convolution operation, and y is the observed blurred image. It can be seen from the model that deblurring ne...

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 Applications(China)
IPC IPC(8): G06T5/00
CPCG06T5/003G06T2207/20081
Inventor 刘日升樊鑫罗钟铉程世超王欢
Owner DALIAN UNIV OF TECH
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