Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Super-resolution reconstruction method of image

A super-resolution reconstruction, high-resolution image technology, applied in image data processing, graphic image conversion, instruments, etc., can solve problems such as low processing efficiency, complex calculation, and time-consuming, to reduce computational complexity, improve Rebuild performance, save processing time

Active Publication Date: 2017-06-23
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV +1
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method of dictionary training involves the processing of a large number of image sets, the calculation is complex, the training phase consumes a lot of time, and the processing efficiency is low

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 of image
  • Super-resolution reconstruction method of image
  • Super-resolution reconstruction method of image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The present invention will be described in further detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0012] The idea of ​​the present invention is to perform super-resolution processing of a single frame image in combination with a graph theory method. In the previous super-resolution algorithms, the structure of the image was not considered. In the present invention, the structural features of the image are utilized, and when the image block is a non-smooth image block, the high-resolution image block is calculated in combination with graph theory.

[0013] like figure 1 As shown, the super-resolution reconstruction method of the image in this specific embodiment comprises the following steps:

[0014] A1, calculate the high-resolution image corresponding to the low-resolution image to be processed, as the initial high-resolution image, divide the obtained initial high-resolution image into blocks, the size of ea...

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 of an image. The method comprises the following steps that A1) a high-resolution image corresponding to a low-resolution image to be process is calculated, the obtained initial high-resolution image is divided into blocks, and a structure tensor Sw(p) corresponding to a position vector p of a central pixel point of each image block is calculated; A2) a characteristic value of the structure tensor Sw(p) of each image block is calculated, and whether the image block is a smooth image block is determined; A3) when the image block is the smooth image block, an initial high-resolution image block serves as a final high-resolution image block of the image block; A4) when the image block is not the smooth image block, reconstruction calculation is carried out by combining a graph theory; and A5) after that all image blocks obtain the final high-resolution image blocks, a final reconstructed high-resolution image is obtained. During construction, an average value of two high-resolution pixel values corresponding to a pixel point is used for a pixel point in an overlapped area. The super-resolution reconstruction method can be used to reduce the computing complexity and reduce processing time.

Description

【Technical field】 [0001] The invention relates to the fields of computer vision technology and image processing, in particular to an image super-resolution reconstruction method. 【Background technique】 [0002] Image super-resolution technology does not need to change the existing physical equipment, as long as appropriate digital signal processing technology can be used to obtain high-resolution images that meet the needs, it has great advantages in technology and cost, so it is being increasingly used It is used in high-definition digital TV, military remote sensing monitoring, public safety and medical imaging and other fields. Compared with the multi-frame reconstruction technology, the single-frame image super-resolution technology only needs one low-resolution image in the actual scene to estimate the high-resolution image in the same scene during reconstruction, which is more suitable for some applications. Application requirements. Meanwhile, depth images play an i...

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): G06T3/40
CPCG06T3/4053
Inventor 张永兵冯义晖王兴政王好谦戴琼海张云
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com