Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An image quality assessment method for screen content based on edge and structural features

An image quality assessment and structural feature technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as gradient direction insensitivity, achieve strong representation ability and improve performance.

Active Publication Date: 2022-07-08
FUZHOU UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Ni et al. proposed a quality assessment method for SCI based on the gradient direction. The experimental results show that the method is simple and effective, but it ignores the effects of certain types of distortion, such as brightness changes and contrast changes, and the gradient direction is not sensitive to these

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
  • An image quality assessment method for screen content based on edge and structural features
  • An image quality assessment method for screen content based on edge and structural features
  • An image quality assessment method for screen content based on edge and structural features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0051] Compared with natural images, SCI has obvious differences in feature statistics, SCI is composed of text, graphics and pictures, has a large amount of edge information, and the human visual system (HVS) is highly sensitive to edges. Inspired by these facts, this embodiment uses the imaginary part of the Gabor filter to extract image edge features. At the same time, it is observed that each SCI has a certain characteristic layout, and the structural changes are also highly correlated with the image quality, so the Scharr filter and the local binary pattern (LBP) operator are combined to extract the structural features of the image. Finally, through random forest training, a quality evaluation model that is highly consistent with human subjective evaluation can be obtained. This embodiment is applicable to images of various distortion types, and the q...

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 method for evaluating the image quality of screen content based on edge and structural features, comprising the following steps: Step S1: converting an input image from RGB color space to LMN color space, and then applying the imaginary part of the Gabor filter to L In terms of components, the edge features of the image are extracted; Step S2: Convert the input image into a grayscale image, use the Scharr filter to calculate the gradient image on the grayscale image, and then use the local binary pattern (LBP) operator on the gradient image. Calculate the LBP map, and then calculate the structural features of the image on the gradient map according to the LBP map; Step S3: According to the two features in steps S1 and S2, use random forest to train the image evaluation model, and use the trained model to predict all tests. The quality score of the image. By considering the characteristics of the human visual system and combining the edge and structural features of the image to evaluate the image quality, the invention can significantly improve the quality evaluation performance of the non-referenced image.

Description

technical field [0001] The invention relates to the fields of image and video processing and computer vision, in particular to a method for evaluating the image quality of screen content based on edge and structural features. Background technique [0002] With the rapid development of the Internet, Screen Content Image (SCI) is widely used in modern multimedia, such as wireless display, distance education, screen sharing, real-time communication, etc. However, due to the defects of technology and equipment, distortion often occurs in the process of image acquisition, compression and transmission. In order to better apply screen content images, image quality evaluation becomes particularly important. Many quality assessment methods for this type of images have been proposed. For example, Yang proposed a quality assessment method based on uncertainty weighting by considering the different effects of text regions and image regions on SCI visual quality. Later, Yang et al. pr...

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): G06T7/00G06T7/73
CPCG06T7/0002G06T7/73G06T2207/10016G06T2207/10024G06T2207/20024G06T2207/30121G06T2207/30172
Inventor 牛玉贞魏乐松吴志山
Owner FUZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com