Method for improving image resolution

An image resolution, high-resolution image technology, applied in the field of image optimization, can solve the problem of consuming a lot of time and energy, low efficiency, etc., and achieve the effect of good image reconstruction effect, less parameter quantity, and high image quality.

Pending Publication Date: 2022-05-27
NANJING UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these software require users to have certain professional skills to use them proficiently, and manual P-mapping takes a lot of time and energy, and is often inefficient

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
  • Method for improving image resolution
  • Method for improving image resolution
  • Method for improving image resolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] The invention discloses a method for improving the resolution of an image, and the method is applied to a scene that needs to adopt an automatic means to improve the resolution of a picture to make the visual effect better.

[0082] The present invention provides a method for improving image resolution, comprising the following steps:

[0083] Step 1, use the DIV2K dataset (the DIV2K dataset is an image super-resolution dataset) to train the image super-resolution model (image super-resolution refers to increasing the image resolution), and randomly crop 48 from the pictures in the DIV2K dataset *48 size image blocks as training data;

[0084] Step 2, using a convolutional neural network to perform shallow feature extraction on the image block to obtain a feature map;

[0085] Step 3, using the Transformer block to perform deep feature extraction on the feature map to obtain a new feature map; wherein the Transformer is a deep learning network structure;

[0086] Step...

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 method for improving image resolution. The method comprises the following steps: training an image super-resolution model by using a DIV2K data set; after training is completed and a final image super-resolution model is obtained, an image needing to be tested is cut into 96 * 96 image blocks, and then each image block is input into the image super-resolution model in sequence; the input image block is subjected to convolutional neural network shallow feature extraction, Transform block deep feature extraction and pixel recombination image reconstruction to obtain a high-resolution output image block; and splicing the series of obtained high-resolution output image blocks according to the sequence of the high-resolution output image blocks in the input picture to form a final high-resolution output image. Compared with the prior art, the image super-resolution model provided by the invention contains less parameter quantity, and a better image reconstruction effect can be realized.

Description

technical field [0001] The present invention relates to an image optimization method, in particular to a method for improving image resolution. Background technique [0002] In recent years, with the rapid development of deep learning, computer vision tasks have achieved very good results. At present, a large number of pictures have been generated on the Internet, and there are a large number of pictures in social media, news pages, e-commerce shopping websites and other places. Pictures have become an indispensable role in each of our lives. However, due to various reasons, including the relatively low resolution of the original shooting, the lower quality after multiple transmissions, etc., the resolution of pictures on the Internet is often very low, which not only makes our viewing experience bad, but even may There is some key information that cannot be prepared for judgment. Therefore, it is very important to increase the resolution of the picture. [0003] The trad...

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): G06T3/40G06K9/62G06N3/04G06N3/08G06V10/774G06V10/82
CPCG06T3/4053G06N3/08G06N3/045G06F18/214
Inventor 杨育彬谢佳鑫
Owner NANJING 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