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

Image super-resolution restoration method based on sparse coding coefficient matching

A sparse coefficient, super-resolution technology, applied in image enhancement, image data processing, instrumentation, etc., can solve problems such as affecting image effects and unreliable assumptions

Inactive Publication Date: 2015-04-29
BEIJING UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the current super-resolution restoration method based on sparse representation assumes that the sparsely encoded coefficients (wl) obtained from the LR image represented by the low-resolution sparse dictionary (Dl) are different from the HR images represented by the high-resolution sparse dictionary (Dh). The sparse coding coefficients (wh) obtained by the image are equal, and the image is reconstructed on the premise of this assumption
However, after research, this assumption is not reliable in practical situations
Even though this method constrains wl and wh to be equal when training Dh and Dl, it turns out that the sparse coding coefficients wl and wh obtained by Dl and Dh in real situations are very different, which directly affects the recovery of this method. image effects

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 super-resolution restoration method based on sparse coding coefficient matching
  • Image super-resolution restoration method based on sparse coding coefficient matching
  • Image super-resolution restoration method based on sparse coding coefficient matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Below in conjunction with accompanying drawing of description, the embodiment of the present invention is described in detail:

[0044] The algorithm of the present invention is divided into a sample library building step and an image reconstruction step; the sample library building step includes training the sparse dictionary and building a sparse coefficient sample library; the image reconstruction step includes image classification, sparse representation, sparse coefficient search and matching, and sparse reconstruction Integrate four steps; the image reconstruction step first divides the input LR image into a flat area and a non-flat area, and at the same time interpolates and enlarges the LR image for backup, selects the non-flat area of ​​the image for sparse representation to obtain the sparse coefficient wl, and obtains The sparse coefficients in the sparse representation low-resolution image coefficient sample library are matched to search for the closest sparse...

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 super-resolution restoration method based on sparse coding coefficient matching and belongs to the field of image information processing technology. A sparse coefficient sample pair of high resolution images and low resolution images is established in a classification mode, a classification matching method is adopted, sparse coding coefficients wh, corresponding to sparse coding coefficients wl of the low resolution images, of the high resolution images are searched for, and therefore the sparse coding coefficients, closer to reality, of the high resolution images are obtained for image reconstruction, and a better super-resolution restoration effect is achieved.

Description

technical field [0001] The invention belongs to the technical field of image information processing, and relates to an image super-resolution algorithm, in particular to an image super-resolution restoration algorithm based on sparse coding coefficient matching. Background technique [0002] With the rapid development of computer and multimedia technology, images are used in all aspects of multimedia technology as the main source of information for human beings. High-quality images / videos can provide richer information and more realistic visual experience. Foundation. Spatial resolution refers to the amount of information stored in an image, and is an important indicator to measure the expressiveness of image details. High resolution means a high density of pixels in an image, providing more detail that is essential in many practical applications. The real-world scene itself has rich information, but affected by various factors such as imaging equipment, imaging environmen...

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): G06T5/00G06K9/62
Inventor 李晓光赵寒卓力郭立磊
Owner BEIJING UNIV OF TECH