Full-reference image-based objective quality evaluation method

An evaluation method and objective quality technology, applied in image communication, television, electrical components, etc., can solve problems such as difficulty in establishing mathematical models and inconsistent subjective evaluation results

Active Publication Date: 2015-03-04
TONGJI UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage is that at present, it can only imitate the subjective visual system of the human eye to a limited extent in some aspects, and there are often inconsistencies with the subjective evaluation results. Different models make different conditional assumptions according to specific application fields, and it is difficult to establish suitable for any field. mathematical model of

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
  • Full-reference image-based objective quality evaluation method
  • Full-reference image-based objective quality evaluation method
  • Full-reference image-based objective quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0076] Select a distorted image d and its reference image r as the input signal, and use the filter to calculate the corresponding perceptual feature vector l r and l d , the reference image r is selected below for illustration (d is the same as r):

[0077] Two-dimensional filtering is performed on the reference image r by means of cumulative sum, which is equivalent to calculating the mean value of the square sum of all elements in a sliding window with a radius of 7 for each pixel position, denoted as r k ;

[0078] Calculate the square of the mean of all elements in the sliding window, denoted as m k :

[0079] Compute the variance within a sliding window

[0080] Set the penalty factor α to 0.01;

[0081] vector l r The kth element of is computed as follows:

[0082] l r k = r k - m ...

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 a full-reference image-based objective quality evaluation method. The method comprises the following steps: (1) acquiring image signals sr of reference images r in an image library and image signals sd of distorted images of different distortion types corresponding to the image signals s; (2) calculating an Euclidean distance DLLM between each reference image and distorted image extraction vector according to the acquired sr and sd; (3) calculating according to the Euclidean distance DLLM to obtain a primary objective evaluation score MLLM; (4) calculating the primary objective evaluation scores MLLM of a plurality of distorted images of different distortion types in the image library and objective evaluation scores thereof, and drawing a scoring scatter diagram; (5) establishing a reference line in the scoring scatter diagram, and calculating an adjustment value offset (xk) of the image of each distortion type; (6) adjusting to obtain the final objective evaluation score new (x1k) of the to-be-evaluated image. Compared with the prior art, the method has the advantages of high consistency in human eye subjective evaluation score, effectiveness to various distortion types, good fitting curve continuity and the like.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to an objective quality evaluation method based on full reference images. Background technique [0002] The meaning of image quality mainly includes two aspects: image fidelity and image intelligibility. Image quality directly depends on the optical performance of imaging equipment, image contrast, instrument noise and other factors. Through quality evaluation, monitoring methods can be provided for image acquisition and processing. In order to make a reasonable evaluation of each link of image processing, the research of image quality evaluation has become one of the basic technologies of image information engineering. [0003] For many years, people have hoped to find out quantitative measurement methods for image fidelity and intelligibility as a basis for evaluating images and designing image systems. However, people still do not fully understand the characteristics of huma...

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): H04N17/00
Inventor 王瀚漓傅杰
Owner TONGJI 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

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