A full-reference image quality evaluation method based on spatial domain combined with frequency domain analysis

An image quality evaluation and reference image technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problems of low accuracy of evaluation results, single spatial or frequency domain feature information, and ignoring the characteristics of human visual processing information, etc. , to achieve the effects of increasing application versatility, improving robustness, and high consistency

Active Publication Date: 2021-10-26
XIAN UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] At present, most image quality evaluation methods based on feature similarity calculations quantify image quality in the spatial or frequency domain, but these methods only use a single spatial or frequency domain feature information, ignoring the The characteristics of processing information in the spatial and frequency domains, resulting in low accuracy of evaluation results

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 image quality evaluation method based on spatial domain combined with frequency domain analysis
  • A full-reference image quality evaluation method based on spatial domain combined with frequency domain analysis
  • A full-reference image quality evaluation method based on spatial domain combined with frequency domain analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] The present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.

[0095] The present invention is a full-reference image quality evaluation method combining spatial domain and frequency domain analysis, such as figure 1 As shown, it can be divided into two parts, namely: the establishment of RF model and the prediction of image quality.

[0096] In the part of establishing the RF model, the processing objects are reference images and distorted images in the image database, extract four similarity features in the present invention, combine the subjective MOS value in the database, and use random forest RF to establish a regression model.

[0097] In the image quality prediction part, calculate the global maximum structure, texture, spatial frequency, and color similarity of the distorted image and the corresponding reference image, shape these four similarity features into a 9-D feature vector, and input it t...

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 full-reference image quality evaluation method based on spatial domain combined with frequency domain analysis. Firstly, color space conversion is performed on reference and distorted images in the database; secondly, spatial domain gradient and frequency domain phase features of reference images and distorted images are extracted to obtain Calculate the global maximum structural feature similarity; then perform the calculation of the frequency domain texture and spatial frequency feature similarity, the spatial domain color feature similarity, and combine the global maximum structural feature similarity to form a 9-D feature vector; establish according to random Senli RF Regression model to fuse feature vectors and subjective MOS values, and perform training; finally execute to extract the 9-D feature vector of the image to be tested, and input it to the trained regression model to achieve high-precision prediction of image quality, thereby completing the objective image quality Evaluation. The invention realizes high-precision objective evaluation of full-reference image quality, and can maintain high consistency with human visual characteristics.

Description

technical field [0001] The invention belongs to the technical field of image processing and image quality evaluation methods, and relates to a full-reference image quality evaluation method based on spatial domain combined with frequency domain analysis. Background technique [0002] With the rapid development of multimedia, image processing and communication technologies, digital images, as one of the most intuitive and effective information carriers, convey important visual signals. At the same time, the popularity of related image acquisition and processing equipment, such as digital cameras, computers and smart phones, vividly and vividly describe objectively existing things for users. [0003] Users are always eager for high-quality images. However, in the process of image acquisition, storage, compression, transmission, and restoration, various unavoidable factors will cause image distortion and quality degradation, such as : During the shooting process, problems such...

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): G06T7/00G06T7/40G06T7/90
CPCG06T7/0002G06T7/40G06T2207/30168G06T7/90
Inventor 郑元林唐梽森廖开阳王玮于淼淼
Owner XIAN UNIV OF TECH
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