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

A Reconstruction Method for Infinitely Scaling Super-Resolution Images

A technology for super-resolution reconstruction and low-resolution images, applied in the field of image reconstruction, can solve the problem that high-resolution images cannot meet the scale requirements, and achieve the effects of improving image reconstruction efficiency, reducing running time, and improving applicability

Active Publication Date: 2019-10-22
XIDIAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in some specific cases, the high-resolution images obtained by this method do not meet the required scale requirements

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 Reconstruction Method for Infinitely Scaling Super-Resolution Images
  • A Reconstruction Method for Infinitely Scaling Super-Resolution Images
  • A Reconstruction Method for Infinitely Scaling Super-Resolution Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] See figure 1 , figure 2 with image 3 , figure 1 Is a schematic flowchart of a method for continuously zooming super-resolution image reconstruction according to an embodiment of the present invention; figure 2 Is a schematic diagram of a dictionary training principle provided by an embodiment of the present invention; image 3 This is a schematic diagram of the principle of a method for continuously zooming super-resolution image reconstruction provided by an embodiment of the present invention. The method for reconstructing a super-resolution image with stepless scaling includes the following steps:

[0057] Step 1. Perform blur processing and N times downsampling on the high-resolution sample image according to the degradation model to obtain a low-resolution sample image;

[0058] Step 2. Using the K-SVD method, use the low-resolution sample images for dictionary training to obtain a high-resolution dictionary and a low-resolution dictionary;

[0059] Among them, step 1 ...

Embodiment 2

[0105] On the basis of the first embodiment, this embodiment provides another stepless zoom super-resolution image reconstruction method, which includes three processing steps: a dictionary training process, an image reconstruction process, and a scale change process. It includes the following steps:

[0106] S1: Dictionary reconstruction process.

[0107] S11: Using a large number of high-resolution sample images, the high-resolution images are blurred and down-sampled by N times according to the modified degradation model to obtain corresponding low-resolution sample images.

[0108] S12: Extract the image features of the low-resolution sample image obtained in step 1 through the feature extraction method, and obtain the high- and low-resolution feature information of the spatial target, namely X s And Y s .

[0109] S13: Use the K-SVD method to perform joint training on high and low resolution feature information to obtain a high and low resolution dictionary.

[0110] S13a: Trainin...

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 a reconstruction method for a stepless zooming super-resolution image. The method comprises the following three processing steps of a dictionary training process, an image reconstruction process and a scale change process. The invention put forward a method for establishing an image library to train a dictionary, an image set is subjected to the off-line training of a dictionary database to obtain a mapping relationship between a high-resolution image and a low-resolution image, and an image reconstruction step is optimized, method operation time is effectively shortened, and the method exhibits adaption and efficiency. In the method, a threshold value is subjected to optimization fixing on the basis of a great quantity of contrast tests, and no changes need to be carried out in the process; and nder a situation that an image reconstruction effect is not affected, image reconstruction efficiency is effectively improved. The super-resolution reconstruction image obtained by the method can be subjected to any-size scale transformation. In engineering application, requirements under different situations can be met, and the method has good applicability.

Description

Technical field [0001] The invention belongs to the technical field of image reconstruction, and specifically relates to a method for reconstructing a super-resolution image with stepless scaling. Background technique [0002] Currently, the image resolution is affected by factors such as the imaging system and the shooting environment, and the resulting image resolution often cannot meet people's needs. However, the current optical imaging system and its detectors are limited by technical level and processing complexity, and cannot improve the imaging quality of the system from a hardware perspective. Therefore, the emergence of image super-resolution reconstruction technology has broken the limitation of image resolution. A high-resolution image is calculated from one or more degraded low-resolution images through software processing to obtain richer detailed information. At present, the super-resolution reconstruction technology is widely used in the fields of image processi...

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 Patents(China)
IPC IPC(8): G06T3/40
Inventor 赵小明向健勇李轩樊星宇温少华
Owner XIDIAN UNIV