Tone mapping image mixed visual feature extraction model establishment and quality evaluation method

A visual feature and tone mapping technology, applied in the field of image processing, can solve the problem of low accuracy of the image quality degradation evaluation model

Active Publication Date: 2021-07-16
NORTHWEST UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide an image quality evaluation method, modeling method and system based on mixed visual features to solve the problem of low accuracy of the evaluation model caused by insufficient consideration of image quality degradation in the prior art

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
  • Tone mapping image mixed visual feature extraction model establishment and quality evaluation method
  • Tone mapping image mixed visual feature extraction model establishment and quality evaluation method
  • Tone mapping image mixed visual feature extraction model establishment and quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] In this example, two data sets, TMID and ESPL-LIVE, are used to verify the performance of this method. The TMID data set contains 120 images, which are divided into 15 groups. Each group includes an HDR image and corresponding 8 TMIs generated from different TMOs. , the quality score of each distorted image in the TMID dataset ranges from 1-8. The ESPL-LIVE dataset contains 1811 HDR processed images generated by three processing algorithms (including TM, multi-exposure fusion and post-processing), of which 747 TMIs were used in the experiment, the quality of each distorted image in the ESPL-LIVE dataset Scores range from 1-100. This embodiment provides an image quality evaluation method, and the following technical features are disclosed on the basis of the above embodiments:

[0066] Specifically, in step 1, each image is divided into multiple non-overlapping image blocks of the same size, and each image block is resized to 224×224 to be sent to the multi-scale featur...

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 an image quality evaluation method, modeling method and system based on mixed visual features. The modeling method comprises the steps of dividing a distorted image into a plurality of non-overlapping image blocks, sending the image blocks into a multi-scale feature fusion network to extract multi-scale content features of the image, calculating a gradient map corresponding to the distorted image, obtaining mixed visual perception features, and mapping the obtained features to human subjective scores by using support vector regression. According to the method provided by the invention, a new multi-scale feature fusion network for expressing image quality hierarchical degradation is designed by combining a hierarchical perception mechanism in a human vision system, and the network can express image distortion more comprehensively; meanwhile, a double-branch feature extraction model comprising an image flow and a gradient flow is constructed in combination with primary perception characteristics of human vision. The improved tone mapping image quality evaluation model can extract richer image quality perception features, and has good accuracy and universality.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for establishing a mixed visual feature extraction model of a tone mapping image and evaluating its quality. Background technique [0002] With the development of digital imaging technology, high dynamic range (High Dynamic Range, HDR) images emerge as the times require. Because HDR images have a wide dynamic range and rich details of real scene images, they have great application value in the fields of video production, virtual reality, remote sensing detection, medical treatment and military affairs. However, HDR displays have not been popular so far. The existing image processing systems mainly use conventional 8-bit display devices, and HDR is far beyond the range that it can handle. Therefore, visualization of HDR images on conventional displays inevitably leads to loss of image information and degradation of perceived quality. To visualize HD...

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): G06K9/46G06K9/62G06N3/04G06T5/20G06T7/00
CPCG06T5/20G06T7/0002G06T2207/30168G06V10/56G06N3/045G06F18/214Y02P90/30
Inventor 张敏许筱敏张汝雪石小妹冯筠
Owner NORTHWEST 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