Image restoration method and device, image restoration equipment and storage medium

An image and feature map technology, applied in the field of image processing, can solve the problems of difficult to meet real-time observation, poor quality of restored images, and large amount of calculation.

Active Publication Date: 2021-04-06
HEFEI INNOVATION RES INST BEIHANG UNIV
View PDF17 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing methods usually design various prior knowledge on the basis of the minimum mean square error of the fidelity item, and then use convex optimization t

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 restoration method and device, image restoration equipment and storage medium
  • Image restoration method and device, image restoration equipment and storage medium
  • Image restoration method and device, image restoration equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] figure 1 It is a flow chart of an image restoration method provided by Embodiment 1 of the present invention, and this embodiment is applicable to the case of performing image restoration on a blurred image. Specifically, the image restoration method can be executed by an image restoration device, which can be realized by means of software and / or hardware, and integrated into an image restoration device. Further, image restoration equipment includes, but is not limited to: electronic equipment such as desktop computers, notebook computers, smart phones, and servers.

[0047] The image restoration method of this embodiment can be applied to a microscopic imaging system. For example, when observing the cell culture process, with the change of cell shape and medium level, there will be a slight shift of the focal plane, so that the imaging plane is not on the focal plane, causing the observed image to be blurred. This phenomenon is called Out of focus blur. The farther ...

Embodiment 2

[0063] image 3 It is a flow chart of an image restoration method provided by Embodiment 2 of the present invention. This embodiment is optimized on the basis of the above embodiments, the training process of the blur strength evaluation network and the blur removal main network, and the process of iterative processing Describe in detail. It should be noted that for technical details not exhaustively described in this embodiment, reference may be made to any of the foregoing embodiments.

[0064] Such as image 3 As shown, the method specifically includes the following steps:

[0065] S210. Acquire a sample image, where the sample image includes a blurred image and a clear image.

[0066] Specifically, the sample images are used to train the blur strength evaluation network and the blur removal main network, and the sample images are essentially a large number of pairs of blurred images and clear images. The sample image can be stored locally, downloaded from a server or d...

Embodiment 3

[0102] Figure 8 It is a schematic structural diagram of an image restoration device provided by Embodiment 3 of the present invention. Such as Figure 8 As shown, the image restoration device provided in this embodiment includes:

[0103] An evaluation module 310, configured to evaluate the image to be processed through the fuzzy strength evaluation network to generate a fuzzy strength feature map;

[0104] An input module 320, configured to input the image to be processed and the blur intensity feature map into the main network for blur removal;

[0105] The output module 330 is configured to perform a set number of iterative processing on the image to be processed according to the blur intensity feature map through the blur removal main network, and output a restored image.

[0106] An image restoration device provided by Embodiment 3 of the present invention extracts the blur intensity feature of the image to be processed through the evaluation module, and performs iter...

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 restoration method and device, image restoration equipment and a storage medium. The method comprises the following steps: evaluating a to-be-processed image through a fuzzy intensity evaluation network to generate a fuzzy intensity feature map; inputting the to-be-processed image and the blurring intensity feature map into a blurring elimination main network; and through the blurring elimination main network, according to the blurring intensity feature map, carrying out iterative processing on the to-be-processed image for a set number of times, and outputting a restored image. According to the technical scheme, the blurring intensity evaluation network is adopted to extract the blurring intensity characteristics of the to-be-processed image, the blurring elimination main network is adopted to iterate the to-be-processed image, the blurring intensity evaluation network and the blurring elimination main network are trained networks and have corresponding functions, automatic restoration of the image can be achieved, and the image restoration efficiency and quality are improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, relate to an image restoration method, device, image restoration device, and storage medium. Background technique [0002] For an optical imaging system with a small depth of field, it is necessary to estimate the defocus amount during the imaging focusing process, which not only requires a large amount of calculation, but also needs to change the internal parameters of the optical imaging system, so it is difficult to achieve fast and accurate autofocus. Taking the scene of cultivating cells as an example, with the changes of cell shape and medium liquid level, there will be a slight shift of the focal plane, resulting in unclear images and problems such as defocus blur, which will affect the observation results and embryo culture. quality. Therefore, it is necessary to restore the blurred image. If the degradation kernel function of the image 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
IPC IPC(8): G06T5/00G06N3/04G06N3/08
CPCG06T5/003G06N3/08G06T2207/20081G06T2207/20084G06N3/043G06N3/045
Inventor 张冀聪王海波王华胡静斐曹朝辉武广
Owner HEFEI INNOVATION RES INST BEIHANG 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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap