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

Multi-task super-resolution image reconstruction method based on KSVD dictionary learning

A low-resolution image and high-resolution image technology, applied in the field of image super-resolution reconstruction, can solve the problems of inability to share information of multiple tasks, deviation of image reconstruction effect, long image reconstruction time, etc., and achieve details The texture information is good, the number is reduced, and the reconstruction time is shortened.

Active Publication Date: 2011-01-19
XIDIAN UNIV
View PDF4 Cites 49 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Sun et al. have extended this method, mainly by using some original contour prior knowledge to remove the smoothing of boundaries and details, but this method still requires a large number of low-resolution images and high-resolution images block to ensure the sufficiency of prior contour detail information, the amount of calculation is huge, and the image reconstruction time is long, resulting in low efficiency
In addition, the above algorithms are all based on single-task reconstruction algorithms. Compared with multi-task algorithms, information sharing between multiple tasks cannot be performed, resulting in deviations in image reconstruction 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
  • Multi-task super-resolution image reconstruction method based on KSVD dictionary learning
  • Multi-task super-resolution image reconstruction method based on KSVD dictionary learning
  • Multi-task super-resolution image reconstruction method based on KSVD dictionary learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Refer to attached figure 1 , concrete steps of the present invention include:

[0030] Step 1. Preprocess and classify training images

[0031] 1a) Input the training image, filter it to extract features, the filter used is f 1 =[-1,0,1], f 3 =[1,0,-2,0,1], The training images used are as image 3 , Figure 4 , Figure 5 with Image 6 shown;

[0032] 1b) Randomly select about 100,000 pairs of small image blocks, construct a matrix M, use the K-means algorithm to divide the small image blocks in the matrix M into 5 categories, but not limited to 5 categories, and obtain 5 pairs of initial dictionaries H 1 , H 2 , H 3 , H 4 , H 5 and L 1 , L 2 , L 3 , L 4 , L 5 and 5 cluster centers C 1 , C 2 , C 3 , C 4 , C 5 , but not limited to 5 pairs of initial dictionaries and 5 cluster centers.

[0033] Step 2. Use the KSVD algorithm to select the initial dictionary H 1 , H 2 , H 3 , H 4 , H 5 and L 1 , L 2 , L 3 , L 4 , L 5 to train

[0034]Thi...

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 multi-task super-resolution image reconstruction method based on KSVD dictionary learning, which mainly solves the problem of relatively serious quality reduction of the reconstructed image under high amplification factors in the existing method. The method mainly comprises the following steps: firstly, inputting a training image, and filtering the training image to extract features; extracting image blocks to construct a matrix M, and dividing the matrix M into K classes to acquire K pairs of initial dictionaries H1, H2...Hk and L1, L2...Lk; then, training the K pairs of initial dictionaries H1, H2...Hk and L1, L2...Lk into K pairs of new dictionaries Dh1, Dh2...Dhk and Dl1, Dl2...Dlk by utilizing a KSVD method; and finally, carrying out super-resolution reconstruction on the input low-resolution image by utilizing a multi-task algorithm and the dictionaries Dh1, Dh2...Dhk and Dl1, Dl2...Dlk to acquire a final reconstructed image. The invention can reconstruct various natural images containing non-texture images such as animals, plants, people and the like and images with stronger texture features such as buildings and the like, and can effectively improve the quality of the reconstructed image under high amplification factors.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image super-resolution reconstruction method, that is, by learning a relationship model between a low-resolution image and a high-resolution image, it is predicted from a single input low-resolution image The corresponding high-resolution images can be used for super-resolution reconstruction of various natural images. Background technique [0002] Super-resolution image reconstruction can be regarded as an inverse problem of recovering a high-resolution image from one or more low-resolution images. In order to solve this problem, some traditional model-based methods have been proposed: such as MAP (maximum a-posteriori) method, maximum likelihood estimation method, convex set projection method (POCS), etc. However, these traditional methods will produce over-smoothing and jagged effects, and the quality of the reconstructed image will be seriously degraded under the c...

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): G06K9/62G06K9/66
Inventor 杨淑媛焦李成刘志州孙凤华王爽侯彪马文萍缑水平朱君林
Owner XIDIAN 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