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

Image quality blind evaluation method for complementary color wavelet domain

A technology for image quality evaluation and image quality, applied in image enhancement, image analysis, image data processing, etc.

Active Publication Date: 2017-09-22
FUDAN UNIV
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a complementary color wavelet domain image quality blind evaluation method to overcome the deficiencies of the existing color image quality blind evaluation method

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 quality blind evaluation method for complementary color wavelet domain
  • Image quality blind evaluation method for complementary color wavelet domain
  • Image quality blind evaluation method for complementary color wavelet domain

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] 1. Decompose the image by two-dimensional complementary color wavelet

[0056] In order to effectively apply the complementary color wavelet, for the complementary color wavelet of the complementary color wavelet level j direction n and vector of coefficients obtained by decomposing an image and Using two-dimensional complementary color transformation / operator

[0057]

[0058] To obtain the black-white, red-cyan, green-magenta, blue-yellow four sets of complementary color complementary color wavelet characteristic subbands [20] . The number of decomposition levels j is 1 to 5, and the direction n is 1 to 8, that is, each complementary color operator has 5 levels, each level has 8 directions, and a total of 40 subbands.

[0059] 2. Statistical feature modeling of natural scenes in complementary color wavelet domain

[0060] After decomposing the sub-bands of each level direction of the complementary color wavelet, the generalized Gaussian distribution model...

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 technical field of color image signal processing and specifically relates to a color image quality evaluation method for a complementary color wavelet domain. The method establishes image complementary color natural scene statistics, multiscale and directional energy distribution models based on a complementary color theory in visual physiology. Analysis shows that the models not only cover information which can be described by the conventional method but effectively represent the relation between channels of a color image through the complementary color, so that one group of efficient characteristics for representing the image quality are given. An application result shows that distortion statistical characteristics of the image can be effectively extracted through the image quality blind (no reference) evaluation method for the complementary color wavelet domain which are provided based on the characteristics, so that the image quality blind evaluation result obtained through the characteristics can be highly consistent with an eye subjective evaluation result and is remarkably better than the blind evolution result of the existing method, and an evaluation result which can be comparable to non-blind (full reference) is obtained.

Description

technical field [0001] The invention belongs to the technical field of color image signal processing, and in particular relates to a color image quality blind evaluation method. Background technique [0002] With the rise of computer, mobile communication and Internet technologies, the generation and transmission of images have shown explosive growth. There is a profound contradiction between the rapid growth of image quantity and quality and the slow growth of communication bandwidth and storage capacity, so that in the process of image transmission and storage, people have to intentionally (such as compress images) and / or unintentionally ( Such as transmission data packet loss) reduce the quality of the image. How to evaluate the quality of an image with objective criteria, and to transmit and store the image with the best quality with the smallest resources, and / or let the machine and network intelligently adjust the allocation of these resources has become a very meanin...

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): G06T7/00G06K9/62
CPCG06T7/0002G06T2207/30168G06T2207/20076G06T2207/20064G06F18/2411
Inventor 陈扬张建秋
Owner FUDAN UNIV