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

Blind removal of image motion blur based on gradient domain and depth learning

A motion blur and deep learning technology, applied in the field of image processing, can solve the problems of obvious image ringing effect, loss of texture details, and long time consumption.

Inactive Publication Date: 2019-02-15
NANJING UNIV OF INFORMATION SCI & TECH
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Deep learning networks are mainly used in image restoration. At present, image deblurring methods based on deep learning networks mostly ignore the high-frequency information of images, so that the texture details of images are lost in the process of deblurring, which not only takes a long time, but also Will cause the ringing effect of the image to be more obvious

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
  • Blind removal of image motion blur based on gradient domain and depth learning
  • Blind removal of image motion blur based on gradient domain and depth learning
  • Blind removal of image motion blur based on gradient domain and depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solutions and beneficial effects of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0033] Such as figure 1 As shown, the present invention provides a method for blind removal of image motion blur based on gradient domain and deep learning, comprising the following steps:

[0034] Step 1, construct the training data set. Using the guided filtered gradient domain image as the base image, the influence of noise and redundant details can be reduced by guiding the filtered image. will y i Guide filtered gradient domain images and corresponding clear images as samples. guided filtering and L 0 Filtering works on clear images. The original clear image is randomly convolved with different blur kernels, and 1% Gaussian white noise is added to generate a motion blur image.

[0035] The specific image preprocessing process is as follows: figure 2 As shown, it contains the following content:

[0036] (...

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 an image motion blur blind removing method based on gradient domain and depth learning, A guide filter gradient domain image is used as a basic image, A L0 filt gradient domainimage and a corresponding clear image are taken as samples, that clear image is randomly convolution with different blur kernel, and 1% Gaussian white noise is added to generate a motion blur image.The gradient domain image after the guide filter, the gradient domain image after the L0 filter and the motion blur image constitute a training data set; The depth convolution neural network is constructed, and the weight data of the depth convolution neural network is learned from the training data set, and the depth convolution neural network used for motion fuzzy kernel estimation is learned. Extracting the weight data of the network training, obtaining the motion blur kernel, optimizing the deconvolution function of the image prior constraint, and obtaining the motion blur image by using the total variational term. This method can effectively suppress the image ringing effect and reduce the image noise, and the effect of motion blur removal is better.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a method for blindly removing image motion blur based on gradient domain and deep learning. Background technique [0002] In the process of image acquisition, transmission, recording, etc., the actual image may be degraded to varying degrees due to factors such as harsh actual environment, imperfect imaging equipment, and relative movement between the equipment and the target, such as noise, blur, and geometric distortion. These will have a great impact on digital images. Image blur can be caused by certain reasons, such as Gaussian blur caused by atmospheric turbulence, motion blur caused by relative motion during the exposure of the camera, and defocus blur caused by the subject being outside the focal length of the camera when shooting, etc. Therefore, it is very important to remove the blur and get a clear image. [0003] There are two main categories of existing i...

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): G06T5/00G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06T5/73
Inventor 郭业才郑慧颖施钰鲲
Owner NANJING UNIV OF INFORMATION SCI & TECH
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