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

A full-reference screen image quality assessment method combining wavelet and corner features

A technology of screen image and corner point features, applied in the field of image processing, can solve the problems of insufficient consideration of screen image characteristics, time-consuming and labor-intensive, and difficulty in practical application.

Active Publication Date: 2019-08-06
HUAQIAO UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Usually the human eye is the final perceiver of the image, so the subjective quality assessment is the most scientific and accurate, but there is a fatal disadvantage: time-consuming and labor-intensive and difficult for practical application
Since screen images and natural images have different image structures and statistical properties, such as having sharper edges, they do not fully consider the screen image characteristics and cannot evaluate the screen image quality very accurately

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 full-reference screen image quality assessment method combining wavelet and corner features
  • A full-reference screen image quality assessment method combining wavelet and corner features
  • A full-reference screen image quality assessment method combining wavelet and corner features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The present invention will be further described below through specific embodiments.

[0066] refer to figure 1 , a full-reference screen image quality assessment method combining wavelet and corner features, including the following steps:

[0067] 1) Input a reference screen image r and a distorted screen image d, respectively perform grayscale processing on the reference screen image r and the distorted screen image d, and convert the input color image into a grayscale image;

[0068] 2) Extract the corner feature cf of the reference screen image r and the distorted screen image d respectively r (x,y), cf d (x,y). The corner features of the reference screen image r are extracted, and the steps are as follows:

[0069] 2.1a) Calculate the difference graphs in the horizontal direction and vertical direction for the reference screen image r respectively, The calculation steps are as follows:

[0070]

[0071] Wherein, r(x, y) is the pixel of the (x, y) position ...

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 screen image quality assessment method combining wavelet and corner features. The method comprises the steps of firstly extracting corner feature similarity images of a reference screen image and a distorted screen image respectively; weighing visual sensitivity of the reference screen image by an amplitude value of a wavelet transform coefficient; and performing weighted fusion on the corner feature similarity images based on the visual sensitivity, thereby performing calculation to obtain a quality score of the distorted screen image. According to the method, a description capability of the corner feature for a local structure of the image is fully utilized and the situation that visual sensitive degrees of human eye visual perception to different regions in the screen image are different is considered; and the method has relatively good screen image quality assessment performance and is simple in calculation.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a full-reference screen image quality evaluation method combining wavelet and corner features. Background technique [0002] A screen image is a composite image that includes graphics and text directly generated by a computer, as well as natural images captured by a camera. Due to its great application value in the fields of virtual screen sharing, online education and advertising, screen image has become a research hotspot in academia and industry. However, like natural images, screen images will inevitably introduce various distortions in the process of generation, compression, storage, transmission and display, resulting in image quality degradation. Therefore, how to accurately evaluate the image quality of the screen image is helpful to improve the performance of the related screen image processing system, which has important theoretical significance and practical applicatio...

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): G06T7/00G06T7/13
CPCG06T7/0002G06T2207/20164G06T2207/30168
Inventor 曾焕强符颖陈婧朱建清蔡灿辉马凯光
Owner HUAQIAO UNIVERSITY