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

Image quality evaluation method based on local average characteristic values

A technology for image quality evaluation and local averaging, applied in the field of image processing

Active Publication Date: 2020-10-30
TIANJIN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these algorithms have good performance, there is still a lot of room for development in non-parametric quality evaluation. According to the current research, there are few studies on using eigenvalues ​​for image quality evaluation. Therefore, the present invention proposes a method based on An Efficient Non-parametric Quality Evaluation Method for Eigenvalues

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 evaluation method based on local average characteristic values
  • Image quality evaluation method based on local average characteristic values
  • Image quality evaluation method based on local average characteristic values

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0020] The present invention first calculates its local mean eigenvalues ​​(LMEs) from the image matrix after normalization, analyzes its correlation with image perception quality, and then calculates the magnitude, variance, entropy and contrast (NSS feature) of the image matrix , and then use LMEs and the calculated multiple features to perform simple dictionary learning, and calculate the predicted quality score, and then make a more comprehensive and accurate objective evaluation of the image. The implementation is as follows:

[0021] 1. The image quality evaluation method based on local mean characteristic value, comprises the following steps:

[0022] Step 1: Normalize the pixel values ​​of the image to obtain the normalized image matrix A, and calculate its local mean eigenvalues ​​(LMEs). The calculation process of LMEs is as follows: divide the image matrix into N small square matrices of S*S size, calculate S eigenvalues ​​of each small square matrix, and then calc...

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 relates to an image quality evaluation method based on a local average characteristic value, and the method comprises the following steps: carrying out the normalization of the pixel values of an image, obtaining a normalized image matrix A, and calculating the local average characteristic value LME of the image matrix A; calculating the amplitude, variance, entropy and contrast, i.e., NSS features, of the normalized image matrix A, , and applying each obtained feature to sparse dictionary learning in combination with the local average feature value of the image matrix A obtainedin the step 1; searching feature representations closest to and sparsest than the test picture, wherein the learned sparse representation coefficient is used for calculating the quality Q of the testpicture.

Description

technical field [0001] The invention belongs to the field of image processing and relates to an image quality evaluation method. Background technique [0002] With the rapid development of the Internet and the improvement of science and technology, many image information technologies are widely used. However, in the process of acquisition, processing, transmission and reception of images that people come into contact with in daily life, due to imperfect imaging systems, processing methods, transmission media and recording equipment, coupled with object movement and noise pollution, etc. It will inevitably bring some image distortion and degradation, which will affect human perception of images. Therefore, it is very important to evaluate the image quality, and it is necessary to understand the degree of image distortion. For example, it is necessary to evaluate the image quality of the distorted image after encoding and compression, so as to adjust the corresponding strateg...

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
IPC IPC(8): G06T7/00G06K9/62
CPCG06T7/0002G06T2207/10024G06T2207/20081G06T2207/30168G06F18/28G06F18/214
Inventor 杨嘉琛武建鹏
Owner TIANJIN UNIV