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

Image super-resolution method

A super-resolution and image technology, applied in the field of image super-resolution, can solve problems such as slow processing speed

Active Publication Date: 2015-09-09
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such methods usually need to solve optimization problems based on norms or norms, and their processing speed is very slow

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 method
  • Image super-resolution method
  • Image super-resolution method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Embodiments of the present invention will be described in detail below. It should be emphasized that the following description is only exemplary and not intended to limit the scope of the invention and its application.

[0040] refer to figure 1 , in an embodiment of the present invention, for a single low-resolution image, an image super-resolution method based on non-correlated dictionary learning and neighbor regression is proposed. According to this method, a training sample set is extracted from existing high-quality images, and a low-resolution dictionary is trained on the training samples. From the basis of the low-resolution dictionary and the high-resolution and low-resolution samples, the high-resolution and low-resolution neighbor sets corresponding to each dictionary basis are obtained, and then the mapping matrix from low-resolution features to high-resolution features is calculated, which is Training phase: For the input low-resolution image, extract the...

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 present invention discloses an image super-resolution method. The method comprises: training a low-resolution dictionary DL; calculating high and low resolution neighbor sets {NH} and {NL}; calculating a mapping matrix set {Fi} from low resolution features to high resolution features; extracting a low-resolution image block set {PL} and a low-resolution feature set {yL} for input low-resolution image IL; selecting the most approximate dictionary-based dk from the low-resolution dictionary DL for each low-resolution feature yL, and utilizing a corresponding mapping matrix set Fk to recover matching high resolution features yH; adding all reconstructed high resolution features {yH} to the matching low-resolution image blocks {PL} to obtain the corresponding high-resolution image blocks {PH}, and fusing all the high-resolution image blocks into one high-resolution image IH. According to the method provided by the invention, the processing speed is high, and high-resolution images of high quality can be obtained.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, in particular to an image super-resolution method. Background technique [0002] Image super-resolution belongs to the field of computer vision and image processing. It is a classic image processing problem and has important academic and industrial research value. The goal of image super-resolution is to reconstruct its corresponding high-resolution image from a given low-resolution image, so that the visual effect is as good as possible while the reconstruction error is as small as possible. The current mainstream image super-resolution methods can be divided into three categories: methods based on interpolation; methods based on reconstruction; methods based on learning. [0003] Interpolation-based methods are a basic class of super-resolution methods, and their processing usually uses local covariance coefficients, fixed-function kernels or adaptive structure kernels, whi...

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
IPC IPC(8): G06T3/40
CPCG06T3/4053
Inventor 张永兵张宇伦王兴政王好谦戴琼海
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