High-precision fast image interpolation method based on texture edge self-adaptive data fusion

A technology of data fusion and interpolation method, which is applied in image data processing, graphics and image conversion, instruments, etc. It can solve problems such as poor consideration of the estimated value formula, the final effect of interpolation needs to be improved, and insufficient consideration of the fusion method.

Active Publication Date: 2016-12-07
NORTHWESTERN POLYTECHNICAL UNIV
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the estimated value formula of this method in all directions in the neighborhood is not considered well, and there is still room for improvement
In summary, although some current interpolation methods based on fusion ideas have made breakthroughs in interpolation speed and accuracy, they are not fully considered in the design of fusion methods, and the final effect of interpolation needs to be improved.

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
  • High-precision fast image interpolation method based on texture edge self-adaptive data fusion
  • High-precision fast image interpolation method based on texture edge self-adaptive data fusion
  • High-precision fast image interpolation method based on texture edge self-adaptive data fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0131]The original Lena image is a grayscale image with a size of 256×256 pixels, and the grayscale value range is [0, 255]. Sampling and compression is performed on it to reduce its width and height to 50% of the original, that is, the size of the compressed image is 128×128 pixels, and the gray scale remains unchanged. Use bilinear interpolation method, bicubic interpolation method, Sun Yumin interpolation method, Deng Cai interpolation method and the image interpolation method proposed by the present invention to interpolate the compressed image, and enlarge it to the same size as the original Lena image, i.e. 256×256 pixels. Wherein, in the method proposed by the present invention, the threshold T=7500, λ=0.4. Count the running time of each method and the peak signal-to-noise ratio of the interpolation result image. The higher the peak signal-to-noise ratio, the better the interpolation effect. The results are shown in Table 1:

[0132] Table 1 Comparison of interpolati...

Embodiment 2

[0136] The original flower image is a grayscale image with a size of 256×256 pixels, and the grayscale value range is [0, 255]. Sampling and compression is performed on it to reduce its width and height to 70% of the original, that is, the size of the compressed image is 179×179 pixels, and the gray scale remains unchanged. Respectively adopt bilinear interpolation method, bicubic interpolation method, Sun Yumin interpolation method, Deng Cai interpolation method and the image interpolation method proposed by the present invention to interpolate the compressed image, and expand it to the same size as the original flower image, i.e. 256×256 pixels. Wherein, in the method proposed by the present invention, the threshold T=5000, λ=0.1. Count the running time of each method and the peak signal-to-noise ratio of the interpolation result image. The higher the peak signal-to-noise ratio, the better the interpolation effect. The results are shown in Table 2:

[0137] Table 2 Compar...

Embodiment 3

[0141] A solder paste image containing a circular pad is selected as the original image, which is a grayscale image with a size of 1292×964 pixels, and the grayscale value range is [0, 255]. The image is sampled and compressed to reduce its width and height to 30% of the original, that is, the size of the compressed image is 388×289 pixels, and the gray scale remains unchanged. Respectively adopt bilinear interpolation method, bicubic interpolation method, Sun Yumin interpolation method, Deng Cai interpolation method and the image interpolation method proposed by the present invention to interpolate the compressed image, so that it is expanded to include the circular pad as the original image The solder paste image is the same size, i.e. 1292 x 964 pixels. Wherein, in the method proposed by the present invention, the threshold T=4000, λ=0.5. Count the running time of each method and the peak signal-to-noise ratio of the interpolation result image. The higher the peak signal-t...

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 provides a high-precision fast image interpolation method based on texture edge self-adaptive data fusion. The high-precision fast image interpolation method comprises the steps of first, obtaining the pixel gray-level variance of a point to be interpolated in the2*2 neighborhood of a corresponding point in a source image, comparing the pixel gray-level variance with a set threshold, and determining the type of the region where the corresponding point is positioned; interpolating a gray-level flat region using a simple and fast bilinear interpolation algorithm; and in an edge texture region, calculating estimated values of the closest 12 pixel points of the point to be interpolated in four directions of horizontal, vertical and diagonal directions in the 4*4 neighborhood of the corresponding point in the source image along the four directions, and then conducting data fusion by combining two weight factors of the direction gray-level gradient and vertical interpolation distance, to obtain the final interpolation. The invention can meet the requirement of high-precision and fast image interpolation.

Description

technical field [0001] The invention relates to an image interpolation method, in particular to a high-precision and fast grayscale image interpolation method. Background technique [0002] As an important technology in digital image processing, image interpolation plays an important role in the field of image processing. It is widely used in various fields such as network video transmission, image restoration, image recognition, and medical aided diagnosis. [0003] Existing image interpolation methods are roughly divided into two categories: traditional linear interpolation methods and edge-adaptive nonlinear interpolation methods. Among the traditional linear interpolation methods, there are more classic ones such as nearest neighbor interpolation, bilinear interpolation and bicubic interpolation. Among them, the nearest neighbor interpolation method is the most simple and convenient to operate, and runs fast, but the interpolation effect is poor and the application ran...

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): G06T3/40G06T3/00
CPCG06T3/0056G06T3/4007G06T3/4023
Inventor 齐敏程恭杜乾敏魏效昱朱柏飞
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap