Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Super-resolution reconstruction method based on dense neural network and two-parameter loss function

A technology of super-resolution reconstruction and loss function, which is applied in the field of image processing, can solve the problem of not being able to reconstruct high-frequency information images, etc., achieve good generalization ability, save pre-processing and post-processing, and increase the effect of reuse

Inactive Publication Date: 2018-11-06
TIANJIN UNIV
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the L2 norm makes the reconstructed image too smooth due to the square term
Compared with the L2 norm, although the L1 norm can make the values ​​tend to be sparse during the training process, it still cannot reconstruct images with sufficient high-frequency information.

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 reconstruction method based on dense neural network and two-parameter loss function
  • Super-resolution reconstruction method based on dense neural network and two-parameter loss function
  • Super-resolution reconstruction method based on dense neural network and two-parameter loss function

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] 1. Data preparation:

[0059] (a) Divide the dataset. The public dataset DIV2K is used, which contains 800 training images, 100 verification images and 100 test images. Since the high-resolution images of the test images are not publicly available, 100 validation images are used to test the reconstruction effect. Among them, the 800 training images used for training and the 100 verification images used for testing are composed of high-resolution images and their corresponding low-resolution images. generated by the degraded model.

[0060] (b) Divide 800 training images without overlapping into 96×96 image blocks as network input.

[0061] 2. Network structure construction:

[0062] The network structure of the present invention is mainly composed of N multi-connection structural blocks, an amplification module and a jump layer. The following will combine figure 1 , and describe in detail the network structure built by the present invention. figure 1 "C" in the m...

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 reconstruction method based on a dense neural network and a two-parameter loss function. The method comprises a data preparation stage, a network structure construction stage, a model training stage, and an image reconstruction stage. The idea of a dense convolutional neural network structure is applied to the super-resolution reconstruction of a single-frame image, shallow features such as texture and contour in the network structure are fully utilized, and local features and global features of the image are combined to perform super-resolution reconstruction. On the above basis, the two-parameter loss function is adopted to perform more accurate optimization training on the network structure, and the algorithm effect is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and more specifically relates to a super-resolution reconstruction method based on a dense neural network and a double-parameter loss function. Background technique [0002] The super-resolution reconstruction of the image is to use various reconstruction techniques to map the low-resolution image into a high-resolution image, recover more high-frequency information, and make the texture and texture of the image clearer. Since multiple different high-resolution images may produce the same low-resolution image through the same downsampling, which is a typical one-to-many problem, the image super-resolution reconstruction problem is essentially an ill-posed problem. )question. According to the different principles of the algorithm, image super-resolution reconstruction methods can be roughly divided into three categories: interpolation-based methods, reconstruction-based methods, and lear...

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): G06T3/40G06T7/13G06T7/40G06N3/08
CPCG06N3/08G06T3/4053G06T7/40G06T7/13
Inventor 褚晶辉张佳祺吕卫
Owner TIANJIN 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
Eureka Blog
Learn More
PatSnap group products