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

Image super-resolution reconstruction method and system

A technology for super-resolution reconstruction and low-resolution images, which is applied in image data processing, graphics and image conversion, neural learning methods, etc., can solve the problem of low efficiency of MSRN multi-scale feature extraction, and achieve good single-frame image super-resolution Reconstruction performance, fast speed, effect with few parameters

Active Publication Date: 2021-11-19
SUZHOU UNIV
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] For this reason, the technical problem to be solved by the present invention is to overcome the low technical problem of MSRN multi-scale feature extraction efficiency in the prior art

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 super-resolution reconstruction method and system
  • Image super-resolution reconstruction method and system
  • Image super-resolution reconstruction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the examples given are not intended to limit the present invention.

[0065] refer to Figure 1-Figure 7 As shown, the present invention discloses a method for image super-resolution reconstruction, comprising the following steps:

[0066] Step 1, the input low-resolution image, and extract basic image features from the low-resolution image.

[0067] Step 2: Taking basic image features as initial input, using multiple sequentially executed AMB modules to sequentially extract higher-level features to obtain multiple high-level feature outputs.

[0068] Wherein, the AMB module includes a first convolutional layer, a second convolutional layer, a third convolutional layer, a fourth convolutional layer and a fifth convolutional layer. The first and th...

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 relates to an image super-resolution reconstruction method and system. The method comprises the following steps: for an input low-resolution image, extracting basic image features from the low-resolution image; taking the basic image features as initial input, sequentially extracting higher-level features by using a plurality of AMB modules which are executed in sequence, and obtaining a plurality of high-level feature outputs; fusing the basic image features and the plurality of high-level feature outputs to obtain fused features; and reconstructing an image through the fused features to obtain reconstructed high-resolution image output. According to the invention, single-frame image super-resolution reconstruction performance similar to that of an existing MSRN can be obtained with higher efficiency, the number of used parameters is small, and the operation speed is high; and the number of the AMB modules can be increased to achieve operation complexity similar to that of the existing MSRN, while the better single-frame image super-resolution reconstruction performance can be obtained.

Description

technical field [0001] The present invention relates to the technical field of digital image processing, in particular to a method and system for image super-resolution reconstruction. Background technique [0002] Single image super-resolution (SISR) is a basic image processing technology, its purpose is to enlarge a low-resolution (LR) image into a high-resolution High-resolution (HR) images, this technology has been widely used in a variety of image-based applications. In recent years, research on this problem has mainly focused on deep learning-based methods. Among them, some methods adopt multi-scale strategies. By using receptive fields of different scales to simulate human eyes observing images from different scales, it is conducive to better image feature extraction; therefore, these methods that adopt multi-scale strategies are usually able to Achieve super-resolution reconstruction performance comparable to deeper models requiring a large number of parameters wit...

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): G06T3/40G06N3/04G06N3/08
CPCG06T3/4053G06T3/4038G06T3/4046G06N3/04G06N3/08
Inventor 季家欢钟宝江
Owner SUZHOU UNIV