Image blind super-resolution method and system

A technology for super-resolution and low-resolution images, applied in the field of image blind super-resolution methods and systems, can solve problems such as long running time, poor estimation accuracy, and complex calculations, and reduce difficulty and running time, convolution Ease of operation and improved estimation accuracy

Active Publication Date: 2021-07-20
XIAMEN UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional machine learning methods usually require a large number of optimization iterations, complex calculations, long running time, and poor estimation accuracy
In the method based on deep learning, the classic fuzzy kernel estimation method KernelGAN also has the problem of complex operation and long running time.

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] see figure 1 , the present embodiment provides a blind image super-resolution method, the method comprising the following steps:

[0044] Step 1: Obtain the trained blur kernel generative network and the spectrogram of the low-resolution image.

[0045] Step 2: Input the spectrogram into the trained blur kernel generation network to obtain the blur kernel corresponding to the low-resolution image.

[0046] Step 3: Determine the degradation feature map corresponding to the low-resolution image according to the blur kernel corresponding to the low-resolution image.

[0047] Step 4: Splicing the low-resolution image and its corresponding degraded feature map to obtain a spliced ​​image.

[0048] Step 5: Input the mosaic image into a trained convolutional neural network to obtain a high-resolution image.

[0049] In one example, before step 1, a step of determining the frequency domain map of the low-resolution image may also be included, specifically Fourier transform m...

Embodiment 2

[0086] see Figure 5 , the present embodiment provides an image blind super-resolution system, the system comprising:

[0087] Obtaining module 501, used to obtain the spectrogram of the trained fuzzy kernel generation network and the low-resolution image;

[0088] A fuzzy kernel determination module 502, configured to input the spectrogram into the trained fuzzy kernel generation network to obtain the corresponding fuzzy kernel of the low-resolution image;

[0089] Degradation feature map determination module 503, configured to determine the degradation feature map corresponding to the low-resolution image according to the blur kernel corresponding to the low-resolution image;

[0090] An image splicing module 504, configured to splice the low-resolution image and its corresponding degraded feature map to obtain a spliced ​​image;

[0091] A high-resolution image determination module 505, configured to input the mosaic image into a trained dense convolutional neural network...

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 an image blind super-resolution method and system. The method comprises the following steps: acquiring a trained blurring kernel generation network and a spectrogram of a low-resolution image; inputting the spectrogram into the trained blurring kernel generation network to obtain a blurring kernel corresponding to the low-resolution image; determining a degradation feature map corresponding to the low-resolution image according to the fuzzy kernel corresponding to the low-resolution image; splicing the low-resolution image and the corresponding degradation feature graph to obtain a spliced graph; and inputting the spliced image into a trained convolutional neural network to obtain a high-resolution image. The method has the advantages of simple and rapid operation and high accuracy.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image blind super-resolution method and system. Background technique [0002] Image super-resolution (Super-Resolution, SR) technology refers to given one or more low-resolution (Low-Resolution, LR) images, using a specific algorithm to reconstruct them into an accurate high-resolution (High-resolution) image. -Resolution, HR) image technology. Image super-resolution technology is widely used in many fields such as surveillance imaging, remote sensing imaging, and medical imaging, and is also used as a preprocessing algorithm for various computer vision tasks. Most image super-resolution methods assume that the HR image is obtained from the LR image through a fixed degradation method (such as bicubic interpolation and downsampling). These methods are essentially the inverse process of learning a predefined single degradation method, which cannot be flexibly To deal with multi...

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
CPCG06T3/4038G06T3/4053G06N3/08G06T2200/32G06N3/045
Inventor 邱明吴国丽许全星黄世雄
Owner XIAMEN 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