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

Method of using natural image prior-knowledge for multi-image super-resolution reconstruction

A technology of multi-frame images and prior knowledge, applied in the field of image processing, can solve the problem of not being able to capture the statistical characteristics of natural images well, and achieve the effect of reducing time complexity, high computational efficiency and improving quality

Active Publication Date: 2018-10-16
ZHEJIANG UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Natural images obey the heavy-tailed distribution, and the commonly used L1 norm and full variation prior knowledge cannot capture the statistical characteristics of natural images well.

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
  • Method of using natural image prior-knowledge for multi-image super-resolution reconstruction
  • Method of using natural image prior-knowledge for multi-image super-resolution reconstruction
  • Method of using natural image prior-knowledge for multi-image super-resolution reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described below in conjunction with accompanying drawing.

[0045] In the process of multi-frame image super-resolution reconstruction, the present invention aims at the statistical characteristics of natural images obeying the heavy-tailed distribution. The present invention uses the expert field model obtained through training to simulate the prior distribution of natural images, and improves the accuracy of multi-frame super-resolution reconstruction images. quality. The optimization process of the present invention is relatively simple, avoids excessive calculation amount, and reduces time complexity. The flow chart of the present invention is as figure 1 As shown, it mainly includes several processes of learning prior knowledge of natural images, inputting a series of low-resolution images, initialization, and super-resolution reconstruction.

[0046] Step 1. Training to get the expert field model

[0047] 1-1 Use the studen...

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 provides a method of using natural image prior-knowledge for multi-image super-resolution reconstruction. According to the method, a fields-of-experts model obtained by learning is introduced to be used as the natural image prior-knowledge in a process of using a series of low-resolution images for super-resolution reconstruction, and quality of multi-image super-resolution reconstruction is improved. Compared with prior knowledge of L1-norm, total variation and the like used by traditional Bayesian multi-image super-resolution methods, the natural image prior-knowledge used in the method is the fields-of-experts model obtained through training of an image database, and can better extract statistical features of natural scenes, and thus obtain better super-resolution reconstruction effects. The method simplifies partial processes of multi-image super-resolution, and shortens calculation time.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a method for super-resolution reconstruction of multi-frame images by using prior knowledge of natural images. Background technique [0002] Image super-resolution (Super Resolution) reconstruction technology is a technology that uses digital image processing algorithms to restore details lost in the imaging process and improve image resolution. At present, image super-resolution reconstruction is mainly divided into two fields: single-frame image super-resolution reconstruction and multi-frame image super-resolution reconstruction. Multi-frame image super-resolution reconstruction uses the complementary information between multiple frames of low-resolution images to reconstruct images. On the premise that multiple frames of images can be obtained, multi-frame image super-resolution can achieve better results. [0003] Among the methods of multi-frame image super-res...

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 冯华君张承志徐之海李奇陈跃庭
Owner ZHEJIANG 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