A super-resolution image reconstruction method of a generative adversarial network based on an attention mechanism

A technology for high-resolution images and low-resolution images, which is applied in the field of super-resolution image reconstruction based on generative confrontation networks, can solve the problems of insufficient edge detail information of reconstructed images, waste of computing resources, and poor image performance, etc., to achieve The image edge and detail information are clear, the reconstruction effect is excellent, and the reconstruction effect is better

Active Publication Date: 2019-05-28
DALIAN MARITIME UNIVERSITY
View PDF2 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main problem is that the edge details of the reconstructed image are insufficient, and the performance of the final image is not...

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
  • A super-resolution image reconstruction method of a generative adversarial network based on an attention mechanism
  • A super-resolution image reconstruction method of a generative adversarial network based on an attention mechanism
  • A super-resolution image reconstruction method of a generative adversarial network based on an attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0036] Such as figure 1 , 2 , 3, an image super-resolution image reconstruction method based on an attention mechanism-based generation confrontation network, including the following steps:

[0037] A. Preprocess the ImageNet data set to make training data sets corresponding to high and low resolution images;

[0038] B. Construct a generative confrontation network model for training, and introduce an attention mechanism into the model;

[0039] C. Input the training data set obtained in step A into the generation confrontation network in turn for model training;

[0040] D. Input the image to be processed into the trained generation network model to obtain a reconstructed high-resolution image.

[0041] Further, the preparation method of the training data set described in step A is:

[0042] A1. Obtain the ImageNet data set, and randomly select some images as the training data set;

[0043] A2. Perform normalization processing on all the images in the obtained training d...

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 super-resolution image reconstruction method of a generative adversarial network based on an attention mechanism, and the method comprises the steps of preprocessing an ImageNet data set, and manufacturing a training data set corresponding to a high-resolution image and a low-resolution image; constructing a generative adversarial network model for training, and introducing an attention mechanism into the model; inputting the obtained training data set into a generative adversarial network in sequence to carry out model training; and inputting the to-be-processed image into the trained generation network model to obtain a reconstructed high-resolution image. According to the invention, the attention mechanism is added into the perception network to extract the salient region of the target; a mode of combining local information and global information is utilized to enable the generated image to be closer to a real high-resolution image, and the perception lossis introduced to improve the generation effect, so that the edge and the detail information of the reconstructed image are clearer, and the reconstruction effect is better.

Description

technical field [0001] The present invention relates to an image reconstruction method, in particular to a super-resolution image reconstruction method based on a generating confrontation network. Background technique [0002] Image super-resolution reconstruction is a technique that uses low-resolution images to produce high-resolution images. The application field of image super-resolution reconstruction is extremely broad, and it has important application prospects in military, medical, public security, computer vision, etc. [0003] At present, super-resolution reconstruction algorithms can be mainly divided into reconstruction-based methods and learning-based methods. Reconstruction-based methods are based on balanced and unbalanced sampling theorem, assuming that the low-resolution input sample signal can well predict the original high-resolution signal. The learning-based method uses a large number of high-resolution images to construct a learning library to generat...

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): G06T3/40G06N3/04
Inventor 王琳杨思琦
Owner DALIAN MARITIME UNIVERSITY
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