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

Image Deblurring Method Based on Combining Image Pixel Prior and Image Gradient Prior

An image pixel and image gradient technology, which is applied in the field of image processing and computer vision, can solve the problems of generalization and weak robustness of fuzzy images, and achieve the effect of improving performance and facilitating recovery

Active Publication Date: 2022-06-17
QINGHAI UNIV FOR NATITIES
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, there are too many network parameters and too large network models in some deep learning-based methods, which undoubtedly put forward higher requirements for network training in terms of hardware configuration; other methods are only suitable for synthetic blurred images, Weak generalization and robustness in real blurred 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
  • Image Deblurring Method Based on Combining Image Pixel Prior and Image Gradient Prior
  • Image Deblurring Method Based on Combining Image Pixel Prior and Image Gradient Prior
  • Image Deblurring Method Based on Combining Image Pixel Prior and Image Gradient Prior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0026] The present invention will be described in detail below with reference to the algorithm flowchart.

[0027] like figure 1 As shown, this embodiment provides an image deblurring method based on combining image pixel prior and image gradient prior, which includes the following steps:

[0028] Step 1: Build the network structure of the generator and discriminator

[0029] like figure 2 and image 3 As shown, the generator is used to learn the process of image sharpening, and the discriminator discriminates and feeds back the generated images learned by the generator;

[0030] Step 1.1: Build the generator G network structure

[0031] The present invention adopts the net...

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 deblurring method based on combining image pixel priors and image gradient priors, comprising the following steps: preparing data; building a generative confrontation network model, including two subnets respectively recorded as DNet and GNet. DNet restores the content of the image from the image pixel domain, and GNet restores the gradient of the image from the image gradient domain; set the target loss function: the target loss function including the constraint DNet subnet includes: image content target loss function L content , Image pixel-level reconstruction target loss function L pixel ; on the other hand, the objective loss function of the GNet subnet is given by L GradientNet pose, L GradientNet The role of is to narrow the gap between the gradient strength map of the label image and the gradient strength map of the generated blurred image; the target loss function L in the discriminator adv , L adv It is used to distinguish the authenticity of the generated image and the label image, and drives the generator to generate an image close to the label image.

Description

technical field [0001] The invention belongs to the technical fields of image processing and computer vision, and in particular relates to an image deblurring method based on combining image pixel prior and image gradient prior. Background technique [0002] As the carrier of external objective world information recording and transmission, images have always been the main source and means for human beings to obtain and identify objective world information. However, image blur caused by camera shake or object motion often occurs during image capture. Since blurred images lose sharp edges and rich texture information, it is difficult for people to obtain clear content and fine information from them. Therefore, how to clarify motion blurred images so that they can be better applied to advanced image processing (image detection, image recognition) and other fields has become a research hotspot. [0003] For the problem of image deblurring, the existing technical methods can be...

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
CPCG06T5/003G06T2207/20081G06T2207/20084
Inventor 祁清
Owner QINGHAI UNIV FOR NATITIES