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

A method and device for acquiring visual entropy

An acquisition method and visual technology, applied in the computer field, can solve problems such as inaccurate calculation results, inability to truly reflect the complexity of image regions, and failure to measure probability distributions.

Active Publication Date: 2018-01-19
HUAWEI TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing visual entropy calculation method only considers the richness of the pixel values ​​of each pixel in the specified image area, that is, it measures the probability distribution of the texture intensity of each pixel, but does not measure the texture direction of each pixel in the specified image area. Therefore, the visual entropy calculation method has certain limitations, and the calculation results are not accurate, and cannot truly reflect the complexity of the specified image area.

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 method and device for acquiring visual entropy
  • A method and device for acquiring visual entropy
  • A method and device for acquiring visual entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0204] In the first implementation manner, the second determination module 102 is configured to calculate the joint entropy of texture directions and texture intensities corresponding to all target pixel points in the specified image area, and use the joint entropy as the specified image the visual entropy of the region;

[0205]The visual entropy can be the joint entropy of the texture direction and texture intensity corresponding to each target pixel. The specific calculation method can be as follows. Assuming that the number of target pixels is N, the texture direction and texture intensity corresponding to all target pixels are respectively Dn and Sn (n=1,...,N, N>1, N is a positive integer), for the N groups of texture directions and texture strengths, the second determination module 102 calculates the joint entropy of texture directions and texture strengths, as specified The visual entropy E of the image region, namely:

[0206]

[0207] Wherein i and j are positive...

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

An embodiment of the invention discloses a visual entropy acquisition method and device. The method includes: acquiring at least two target pixel points in a designed image area; determining a texture direction and texture intensity corresponding to each target pixel point; and determining entropy of the texture direction and the texture intensity corresponding to each target pixel, and obtaining a visual entropy of the designated image area according all entropy. By adoption of the visual entropy acquisition method, not only is the texture direction of each target pixel point considered, the texture intensity of each target pixel point is also considered, the acquired visual entropy is high in accuracy, and can truly reflect the complexity of the designated image area.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for acquiring visual entropy. Background technique [0002] An image is formed by combining multiple pixels, and the pixels in the image are usually obtained by sampling the shooting scene. In different specified image areas in the image, due to the different pixels that make up the specified image areas, the complexity of different specified image areas is different. When the distorted signals of the same physical strength (such as the same mean square error) appear in different complex Different degrees of visual intensities will appear when over a specified image area. Visual experiments have found that when the specified image area is more complex, the distortion appearing on the specified image area is more difficult to be found. This phenomenon is called entropy masking effect. In practical applications, in order to obtain the entropy masking...

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): G06T7/40
Inventor 赵寅杨海涛周炯
Owner HUAWEI TECH CO LTD