Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Non-uniform image motion blur removing method based on deep neural network

A deep neural network and motion blur technology, applied in the field of image processing, can solve problems such as image non-uniform blur, uniform blur image blur removal, etc.

Active Publication Date: 2015-06-03
XI AN JIAOTONG UNIV
View PDF4 Cites 48 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method mainly focuses on removing non-uniform blur of images caused by camera motion, object motion, etc.; at the same time, as a general method, it can also solve the problem of blur removal of uniform blur images

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
  • Non-uniform image motion blur removing method based on deep neural network
  • Non-uniform image motion blur removing method based on deep neural network
  • Non-uniform image motion blur removing method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to make the purpose, technical solutions 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 restrictive of the invention.

[0054] like figure 1 As shown, a method for removing image non-uniform motion blur based on a deep neural network of the present invention comprises the following steps:

[0055] 1. Construct the training data set

[0056] Describe the motion blur kernel as a motion vector. The motion vector space is quantized into N different motion vectors, and each motion vector determines a motion blur kernel, thereby forming a motion blur kernel set G. A large number of images are collected, and motion blur kernels corresponding to different motion vectors are applied to the images to obtain blurred images. A blurred image block of M×M size is intercepted from the above-ment...

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 non-uniform image motion blur removing method based on a deep neural network. The non-uniform image motion blur removing method comprises two main steps of training deep neural network parameters, and estimating and removing motion blur by applying a deep network to an image. The deep network structure consists of a convolution network layer and a forward network layer; the network model training process comprises the following steps: generating a blur image block and a blur kernel pair by using a natural image, and training the deep neural network model parameters by using the data; providing a motion blur image, decomposing the image into an image block set with overlapped areas, inputting each image block into motion blur probability distribution corresponding to deep neural network output image blocks, and further acquiring different motion blur kernels per pixel points of the image by optimizing a Markov random field model; finally, acquiring a blur removed image by using a deconvolution algorithm based on the estimated motion blur kernels. Due to good learning capability of the deep neural network, non-uniform motion blur of the image can be precisely estimated, and clear images can be further obtained.

Description

Technical field: [0001] The invention belongs to the field of image processing, and in particular relates to a method for removing non-uniform motion blur in images based on a deep neural network, which is used for automatically estimating and removing non-uniform motion blur in images. Background technique: [0002] Image deblurring is an important problem in the field of image processing. Existing methods mostly focus on removing globally consistent blur. In addition, there is non-uniform motion blur, that is, the motion blur kernel is spatially inconsistent. This type of blur mostly occurs when objects move during image capture, or when shooting external scenes in a moving car. This problem is very challenging. Existing approaches to address image blur and non-uniform blur estimation and removal are presented below. [0003] 1. Image Uniform Blur Estimation and Removal Method [0004] The current uniform blur kernel estimation algorithm is usually implemented by opti...

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
Inventor 孙剑曹文飞徐宗本
Owner XI AN JIAOTONG UNIV
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
Eureka Blog
Learn More
PatSnap group products