Super-resolution image reconstruction method based on characteristic channel adaptive weighting

A super-resolution image and self-adaptive weighting technology, which is applied in image data processing, graphics and image conversion, neural learning methods, etc., can solve problems affecting image quality and achieve high image peak signal-to-noise ratio

Active Publication Date: 2019-08-09
HARBIN ENG UNIV
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These network models treat each feature channel equally, which affects the reconstructed image quality

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
  • Super-resolution image reconstruction method based on characteristic channel adaptive weighting
  • Super-resolution image reconstruction method based on characteristic channel adaptive weighting
  • Super-resolution image reconstruction method based on characteristic channel adaptive weighting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0026] The specific implementation steps of the super-resolution image reconstruction technology proposed by the present invention are as follows:

[0027] Step 1, improving the existing SE structure to obtain the ISE module.

[0028] Such as figure 1 As shown, on the basis of the original SE network, the input layer and the output layer are residually connected using the following formula to realize adaptive learning of network channel weights.

[0029] E(y)=(σ(W 2 δ(W 1 y))×0.8+σ(y)×0.2)×2

[0030] Among them, y is the input vector of the SE network, E(y) is the channel weight of the network, σ and δ represent the Sigmoid function and the ReLU function respectively, W 1 and W 2 is the weight of the single hidden layer neural network and C is the number of channels.

[0031] Step 2, Simplify the EDSR network.

[0032] The simplified EDSR network mo...

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 belongs to the field of image reconstruction, and particularly relates to a super-resolution image reconstruction method based on characteristic channel adaptive weighting. A super-resolution image reconstruction method based on characteristic channel adaptive weighting comprises the following steps: (1) improving an excitation function of a compressed excitation network SE to obtainan ISE module; (2) simplifying the existing EDSR network; (3) embedding the ISE model into the simplified EDSR network to obtain an ISE-EDSR model; (4) training ISE-EDSR model by using the training sample. The method has the advantages that the training difficulty is low; adaptively learning feature channel weights; the problem that the output value of the network intermediate layer is too low isavoided; and the peak signal-to-noise ratio of the image after super-resolution reconstruction is high.

Description

technical field [0001] The invention belongs to the field of image reconstruction, in particular to a super-resolution image reconstruction method based on feature channel adaptive weighting. Background technique [0002] Super-resolution image reconstruction refers to the technology of converting low-resolution images into high-resolution images using signal processing or image processing algorithms. More specifically, it is a technology to restore single or multiple confused and degraded low-resolution images to high-resolution images. According to the number of low-resolution images used, super-resolution image reconstruction techniques can be divided into single-image-based and multiple-image-based reconstruction methods. Among them, the super-resolution reconstruction technology of a single image is widely used in computer vision fields such as medical image processing, video surveillance, criminal investigation analysis, image printing, and satellite imaging. [0003...

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
CPCG06T3/4053G06N3/08G06N3/045
Inventor 郑丽颖张文武邴鑫阳张晏博
Owner HARBIN ENG 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