Content-insensitive fuzzy image quality evaluation method based on Weibull statistical characteristics

A fuzzy image and quality evaluation technology, applied in the field of image processing, can solve the problems of inaccurate evaluation of fuzzy images, and achieve the effects of accurate model evaluation results, good learning effect, and good practicability.

Active Publication Date: 2017-06-20
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In view of this, the present invention provides a content-insensitive fuzzy image quality evaluation method based on Weibull statistical features, which can well solve the problem of inaccurate evaluation of blurred images with the same blur degree but different content by existing algorithms

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
  • Content-insensitive fuzzy image quality evaluation method based on Weibull statistical characteristics
  • Content-insensitive fuzzy image quality evaluation method based on Weibull statistical characteristics
  • Content-insensitive fuzzy image quality evaluation method based on Weibull statistical characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0037] The invention provides a content-insensitive fuzzy image quality evaluation method based on Weibull statistical features. First, the edge gradient magnitude matrix of the image to be evaluated is extracted, and the edge gradient magnitude matrix is ​​modeled and fitted using Weibull distribution to obtain The Weibull distribution shape and scale parameters of the gradient, and calculate the skewness value of the Weibull distribution shape at the same time; then separate and normalize the Weibull distribution shape, scale and skewness of images with the same content to reduce parameters and image content The relationship between the images is insensitive to the content of the image; finally, the normalized Weibull distribution shape, scale and skewness are used as eigenvalues ​​to evaluate the quality of the image to be evaluated.

[0038] The specif...

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 a content-insensitive fuzzy image quality evaluation method based on Weibull statistical characteristics. Through the method, the problem that the existing algorithm fails to accurately evaluate fuzzy images of the same fuzzy degree but with different contents can be well solved. The method comprises the following steps: first, acquiring an edge gradient amplitude matrix of a to-be-evaluated image, modeling and fitting the edge gradient amplitude matrix by means of Weibull distribution to get gradient Weibull distribution shape and scale parameters, and calculating the skewness value of the Weibull distribution shape, wherein the shape, scale and skewness parameters extracted can well distinguish between images of different fuzzy degrees in gradient amplitude distribution; then, carrying out divisive normalization on the Weibull distribution shapes, scales and skewness of images with the same content in order to reduce the relationship between parameters and image content and achieve insensitivity to image content; and finally, evaluating the quality of the to-be-evaluated image with the Weibull distribution shape, scale and skewness after normalization as characteristic values.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a content-insensitive fuzzy image quality evaluation method based on Weibull statistical features. Background technique [0002] With the rapid development of digital multimedia technology and Internet technology, multimedia content can become the main content of modern people's daily entertainment and communication, such as high-definition television (High Definition Television, HDTV), streaming Internet Protocol TV (Streaming Internet Protocol TV, IPTV) ), iQiyi, Youku, Youtube, Flickr and other video sites. Such a large amount of data and huge demand make human beings have higher and higher requirements for viewing quality of multimedia images, and at the same time trigger vigorous research on technologies such as multimedia signal acquisition, compression, transmission, enhancement and reconstruction. In the process of multimedia acquisition and processing, the sign...

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): G06T7/00G06T7/44
CPCG06T7/0002G06T2207/30168
Inventor 邓宸伟王水根周士超李震赵保军
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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