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

Full-reference high-dynamic image quality evaluation method based on multi-feature fusion

A high dynamic image, multi-feature fusion technology, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as poor prediction accuracy and inability to effectively apply high dynamic range images.

Active Publication Date: 2020-10-13
SHANGHAI UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1. The current algorithm only considers some single features and does not start from multiple features, so the prediction accuracy is poor;
[0005] 2. The current algorithm cannot be effectively applied to high dynamic range images of different formats

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 high-dynamic image quality evaluation method based on multi-feature fusion
  • Full-reference high-dynamic image quality evaluation method based on multi-feature fusion
  • Full-reference high-dynamic image quality evaluation method based on multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] see Figure 1-Figure 2 , a full-reference high dynamic image quality evaluation method based on multi-feature fusion, the operation steps are as follows:

[0083] (1) Calculation of color features:

[0084] By converting the distorted high dynamic image to the YIQ color domain and extracting the I and Q channel images separately, combining the I channel and Q channel images extracted from the original image, using the method of calculating similarity to calculate the original image and the distortion The similarity of the image on the I channel and the similarity on the Q channel are used as color features;

[0085] (2) Visual contrast difference feature calculation:

[0086] Using the visual difference prediction method to simulate the visual characteristics of the human eye for high-dynamic images, first simulate the scattering process of light inside the human eye, and then simulate the selection process of the human eye for different spatial frequencies and direct...

Embodiment 2

[0092] This full-reference high dynamic image quality evaluation method based on multi-feature fusion includes the following steps:

[0093] Color direction eigenvalue calculation: By converting the distorted high dynamic image into the YIQ color domain and extracting the I and Q channel images separately, combining the I channel and Q channel images extracted from the original image, using the method of calculating similarity Calculate the similarity between the original image and the distorted image on the I channel and the similarity on the Q channel as the eigenvalue of the color direction;

[0094] Visual contrast difference eigenvalue calculation: The visual difference prediction method HDR-VDP-2 is used to extract visual contrast difference features, firstly simulate the scattering process of light inside the human eye, and then simulate the human eye's response to light in the visual cortex through multi-scale decomposition The selection process of different spatial fr...

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 provides a full-reference high-dynamic image quality evaluation method based on multi-feature fusion. The full-reference high-dynamic image quality evaluation method is mainly divided into a feature extraction stage and a training regression stage. In the feature extraction stage, features of the image are extracted in three directions, and two color similarity features of the imageare extracted in the color direction by using a color similarity method extraction method; visual contrast difference features are extracted by adopting a visual difference prediction method in a visual contrast difference direction; a log-Gabor filter is used for extracting multi-scale features in different frequency scales and directions according to the multi-scale comprehensive feature direction; and the quality of the high-dynamic image is predicted by using a machine learning method in a training regression stage. The algorithm provided by the invention can accurately and effectively predict the quality of the high-dynamic image.

Description

technical field [0001] The present invention relates to the technical field of high dynamic image quality evaluation, and relates to a high dynamic image quality evaluation method based on multiple feature extraction, in particular to a full-reference high dynamic image quality evaluation method based on multi-feature fusion. Background technique [0002] High Dynamic Range (HDR) images can accurately show brightness differences from dark backgrounds to bright sunlight (10 -3 cd / m 2 to 10 5 cd / m 2 ), which can bring viewers a more realistic and rich visual experience. However, the existing image quality evaluation algorithms are mainly aimed at the traditional 8-bit low dynamic range (Low Dynamic Range, LDR) image. Due to the expansion of the dynamic range, the color vividness and brightness of the image have increased significantly, resulting in the traditional image Quality evaluation methods are no longer highly effective. In order to conform to the development trend ...

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
IPC IPC(8): G06T7/00G06T7/90G06T5/50G06N3/08
CPCG06T7/0002G06T7/90G06T5/50G06N3/08G06T2207/30168G06T2207/20221G06T2207/20081G06T2207/20084G06T2207/10024Y02P90/30
Inventor 沈礼权卞辉姜明星
Owner SHANGHAI 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