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

Image Super-resolution Reconstruction Method Based on Multilayer Support Vector Regression Machine Model

A support vector regression and model technology, applied in the field of image processing, can solve problems such as super-resolution reconstruction of difficult images, and achieve the effect of rich texture and clear edges

Inactive Publication Date: 2016-10-26
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the performance of this method depends entirely on the training sample library. If the sample selection is not good, it is difficult to achieve better image super-resolution reconstruction.

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 Reconstruction Method Based on Multilayer Support Vector Regression Machine Model
  • Image Super-resolution Reconstruction Method Based on Multilayer Support Vector Regression Machine Model
  • Image Super-resolution Reconstruction Method Based on Multilayer Support Vector Regression Machine Model

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0041] refer to figure 1 , the specific embodiment of the present invention is as follows:

[0042] Step 1, create a training sample library of high-resolution brightness images and low-resolution brightness images.

[0043] (1a) Randomly download a color high-resolution natural image from the Internet;

[0044] (1b) Use the function rgb2ycbcr in matlab to map the high-resolution color image from the RGB space to the YCbCr space, then obtain the luminance signal from the YCbCr space, and use the black-and-white grayscale image composed of the luminance signal as a high-resolution luminance image. Brightness training image creates a high-resolution brightness image training sample library;

[0045] (1c) Take pixels from the high-resolution brightness image at intervals to obtain a low-resolution brightness training image downsampled by 2 times, and use the low-resolution brightness training image to create a low-resolution brightness image training sample library.

[0046] S...

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 reconstruction method based on multi-layer supporting vectors and mainly aims at solving the problems that high-frequency information is lost and a ring effect is generated in an existing super-resolution method. The realizing steps of the method are as follows: (1) respectively establishing a training sample base and a testing sample base, (2) establishing first-layer support vector regression machine models of testing samples, (3) predicating high-resolution luminance initial images and initial training images, (4) calculating differential value training images of the initial training images, (5) establishing second-layer supporting vector regression machine models of the differential value training images, (6) calculating high-resolution luminance differential value images, (7) adding the high-resolution luminance initial images and the high-resolution luminance differential value images to obtain high-resolution luminance images, The images reconstructed through the method have the advantages of being clear in edge, rich in texture and closer to real images. The method can be used for video monitoring and high-definition television (HDTV) imaging.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an image super-resolution reconstruction method, which can be used for video monitoring and HDTV imaging. Background technique [0002] Image resolution is an important performance index to measure image quality. With the invention of CCD and CMOS image sensor, the image obtained by people is clearer, but in the process of image acquisition and processing, it is easily affected by weather conditions, physical conditions, human factors and other factors, which will degrade the image quality. Improving the hardware conditions of image imaging equipment can improve image quality, but high-density image sensors are expensive and it is almost difficult to improve the performance of sensor arrays from a technical level. In order to meet people's demand for low cost while significantly improving image resolution, super-resolution image reconstruction technology has been ...

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 Patents(China)
IPC IPC(8): G06T5/50
Inventor 邓成许洁杨延华谢芳李洁高新波
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

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