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

A single-frame image super-resolution reconstruction method

A super-resolution reconstruction, frame image technology, applied in image data processing, graphic image conversion, instruments, etc., can solve the problems of super-resolution image detail information loss, edge blur, poor image quality, etc.

Active Publication Date: 2017-04-26
深圳市安软科技股份有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods usually directly obtain the interpolation result of the super-resolution image according to the interpolation formula, often ignoring the influence of the correlation of each pixel in the source image on the interpolation result, resulting in the loss of super-resolution image detail information, blurred edges, and poor image quality. poor

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
  • A single-frame image super-resolution reconstruction method
  • A single-frame image super-resolution reconstruction method
  • A single-frame image super-resolution reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] Uniformly subsample a given high-resolution image to generate a low-resolution image. The method of the present invention is used to perform super-resolution interpolation reconstruction on the generated low-resolution image, and perform performance comparison on the basis of the original high-resolution image.

[0047] figure 2 The reconstruction result of the classic picture LENA often used in image processing is given, where. figure 2 (a) The picture is the source image, figure 2 (b) The picture is a low-resolution image, figure 2 (c) The picture shows the super-resolution image obtained by bilinear interpolation method. figure 2 (d) The picture shows the super-resolution image obtained by Newton interpolation method. figure 2 (e) The picture shows the super-resolution image obtained by using the edge-based adaptive Newton interpolation method, figure 2 (f) is a super-resolution image obtained by the method of the present invention.

[0048] It can be se...

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 belongs to the field of signal and image processing, and in particular relates to a method for reconstructing the super resolution of a single-frame image. The method comprises the steps of calculating the relevance of pixel points in a source image in the directions by using a second-order difference method, selecting a weighting coefficient according to the relevance, carrying out interpolation calculation on the directions by using a Newton interpolation method, and weighting and summing the interpolation result to obtain a final super-resolution image. The method is applicable to the field of image restoration.

Description

technical field [0001] The invention belongs to the field of signal and image processing, and relates to a single-frame image super-resolution reconstruction method, in particular to a single-frame image super-resolution reconstruction method that utilizes relevant information of source images and performs Newton interpolation from multiple directions at the same time. method of construction. Background technique [0002] With the help of signal estimation theory, super-resolution reconstruction overcomes the limitation of the inherent resolution of the imaging system and achieves the purpose of improving image quality. It has a wide application space in the fields of machine vision, image understanding, and image restoration. In 1984, Tsai and Huang first proposed the idea of ​​using low-resolution, under-sampled image sequences to generate high-resolution images, and gave a frequency-domain approximation method. Although the single-frame image super-resolution reconstruct...

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): G06T3/40
Inventor 修春波
Owner 深圳市安软科技股份有限公司