Image processing method and training method of image processing model

An image processing and model technology, applied in image data processing, computing models, image enhancement, etc., can solve problems such as limited application of machine learning, and achieve good restoration effect and high restoration efficiency

Pending Publication Date: 2021-11-23
BOE TECH GRP CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the shortcomings of the existing methods, the present application proposes an image processing method and a training method for image processing models to solve the problem that the application of machine learning in the field of old photo processing technology is limited due to the inability to obtain training samples in the prior art technical problem

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 processing method and training method of image processing model
  • Image processing method and training method of image processing model
  • Image processing method and training method of image processing model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present application is described in detail below, and examples of embodiments of the present application are shown in the drawings, wherein the same or similar reference numerals denote the same or similar components or components having the same or similar functions throughout. Also, detailed descriptions of known technologies will be omitted if they are not necessary to illustrate the features of the present application. The embodiments described below by referring to the figures are exemplary only for explaining the present application, and are not construed as limiting the present application.

[0033] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms, such as those defined in commonly used dictionaries, should be ...

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 provides an image processing method and a training method of an image processing model. The image processing method comprises the following steps: acquiring a to-be-processed first original image; and according to the configured down-sampling processing path and Gaussian blur parameters, sequentially carrying out down-sampling processing and Gaussian blur processing on the first original image, and obtaining a first degraded image. According to the method, multiple degradation factors such as blurring and noise can be added to the new photo, the degraded image similar to the effect of the old photo is obtained, the mathematical relationship between the old photo and the new photo is established, and a good training sample is provided for application of machine learning in the old photo repairing technology; and the image processing model used in the old photo restoration technology is trained based on the training sample, the image processing model with relatively strong restoration can be obtained, the image processing model is used for restoring the old photo, the restoration efficiency is relatively high, and the restoration effect is relatively good.

Description

technical field [0001] The present application relates to the technical field of digital image processing, and in particular, the present application relates to an image processing method and a training method of an image processing model. Background technique [0002] Image processing using machine learning has always been an important branch of image processing, and it is also a technology hotspot that has developed very rapidly in recent years. [0003] Image processing based on machine learning methods usually requires paired images as training samples (training set). At present, the training sample collection method is mainly: under the exact same external conditions (scene, time, location, shooting angle, etc.) A set of images (including high-quality and high-resolution images and low-quality low-resolution images, where high and low are relative concepts) is taken with different devices, and then a data set is obtained through a small amount of post-processing (such a...

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): G06T5/00G06N20/00
CPCG06T5/002G06T5/003G06T5/005G06N20/00G06T2207/10004G06T2207/20081
Inventor 刘瀚文王婷婷陈冠男
Owner BOE TECH GRP CO LTD
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