Image scaling method for keeping visual quality of sensitive target

A visual quality and sensitive technology, applied in the field of computer vision, it can solve the problems of target deformation and distortion, unfavorable application, large amount of calculation, etc., and achieve the effect of reducing deformation and improving the zoom effect.

Inactive Publication Date: 2010-10-27
BEIHANG UNIV
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, in practical applications, the original image is scaled by direct linear scaling. There are two types of problems in the image scaling method of direct linear scaling: 1) After direct linear scaling, the size of important objects may be too small, which is not easy to observe
2) If the aspect ratio of the original image differs greatly from the aspect ratio of the mobile terminal screen, it will cause serious deformation and distortion of the target in the image
The technology based on the fusion of multiple methods has a large amount of calculation, which is not conducive to the application on mobile devices with limited processing capabilities.

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 scaling method for keeping visual quality of sensitive target
  • Image scaling method for keeping visual quality of sensitive target
  • Image scaling method for keeping visual quality of sensitive target

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0029] Step 1: Calculation of image sensitivity

[0030] Existing image sensitivity calculation methods can be divided into two categories: use the underlying features of the image to calculate the sensitivity of the image; use pattern recognition to identify sensitive targets in the image. At present, most of the methods that use the bottom-level features of an image focus on using a single bottom-level feature, such as gradient, as the sensitivity of the image. The characteristics of this type of method are simple and fast. The disadvantage is that this type of method is not robust and not accurate enough. The advantage of using pattern recognition to identify sensitive targets in images is: accuracy. The disadvantage is that only certain types of objects can be identified, and the generalization performance is poor. In the present invention, the sensitivity of the image is calculated by using the weighted average method for the four characteristics of the image pixel point ...

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 scaling method for keeping visual quality of a sensitive target, which comprises the following steps of: calculating the sensitivity of a pixel point in an image by using four characteristics comprising color, gradient, brightness and center distance of the pixel point in the image to obtain an image sensitivity graph in accordance with the primary image, then generating a triangle mesh covering the primary image by adopting Delaunay triangulation according to the image sensitivity graph, establishing a visual loss function of the image on the basis, obtaining a target mesh with the same size as a target image by solving the optimization problem of the minimum value of the visual loss function under integrity constraint of the image, and finally generating a final result image in a texture mapping mode.

Description

Technical field [0001] The invention relates to an image scaling method for maintaining the visual quality of a sensitive target, which relates to the sensitivity calculation of pixels in the image and an image deformation method based on a triangular grid. The best visual effect is obtained on the premise that the sensitive target is basically not deformed The high-quality zoomed image belongs to the field of computer vision technology. Background technique [0002] At present, in practical applications, direct linear scaling is used to scale the original image. The image scaling method of direct linear scaling has two types of problems: 1) Direct linear scaling may cause important targets to be too small in size and inconvenient to observe. 2) If the aspect ratio of the original image is significantly different from the aspect ratio of the mobile terminal screen, it will cause serious distortion of the target in the image. The image scaling method that maintains the visual qua...

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): G06T3/40H04N1/393
Inventor 李炜陈志高黄超李小燕李天然
Owner BEIHANG 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