Image quality evaluation method and device for mixed degraded images

A technology for image quality evaluation and image degradation. It is applied in image enhancement, image analysis, image data processing, etc. It can solve the problem of inaccurate image degradation measurement results, optimize estimation, simplify degradation description, and solve evaluation results. Inaccurate effect

Active Publication Date: 2019-05-10
重庆瑞景信息科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide an image quality evaluation method and device for mixed degraded images, which are used to solve the problem that the existing image degraded measurement results are not accurate enough

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
  • Image quality evaluation method and device for mixed degraded images
  • Image quality evaluation method and device for mixed degraded images
  • Image quality evaluation method and device for mixed degraded images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] This embodiment provides an image quality evaluation method for mixed degraded images, and the image quality evaluation method specifically includes the following steps:

[0024] Step 1) extracting image features, the image features include the image features of the mixed degraded image to be detected, the image features of the passivation image and the image features of the noise image, and the passivation image is preserved by the mixed degraded image Obtained by edge filtering, the noise image is obtained by calculating the mixed degraded image and the passivation image;

[0025] Step 2) calculating the image features of the ideal image quality image corresponding to the mixed degraded image, the image features of the ideal image quality image are calculated by inputting the image features of the passivation image into a pre-built image feature degradation model;

[0026] Step 3) Construct the quality features of the mixed degraded image according to the image featur...

Embodiment 2

[0145] In addition, this embodiment also provides an image quality evaluation device for mixing degraded images. The image quality evaluation device is a product solution corresponding to the technical solution in Embodiment 1. Therefore, the two have the same technical principle and solve the same problem. Technical issues and solutions with the same technical effect are embodied differently, so the specific content will not be repeated.

[0146] Specifically, see Figure 5 , a schematic diagram of the principle of an image quality evaluation device for mixed degraded images is given in the present invention. As shown in the figure, the image quality evaluation device 200 includes: a feature extraction module 210 for extracting image features, and the image features Including the image features of the mixed degraded image to be detected, the image features of the passivation image, and the image features of the noise image, the passivation image is obtained by edge-preserving...

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 present invention provides a method and a device for image quality assessment of a mixing and degradation image. The influence of degradation factors of different properties is described by two degradation principal elements consisting of noise and passivation so as to simplify the degradation description, have visual attributes for the degradation description and better reflect the influenceof the degradation on vision. The method and the device for image quality assessment of a mixing and degradation image are achieved based on the noise degradation features, the passivation degradationfeatures and the mixing degradation features to optimize the design of the degradation features, and the extracted visual features are consistent to the human eye visual features on a certain degreeso as to solve the problem that a current image quality assessment result is not accurate.

Description

technical field [0001] The invention relates to the technical field of measurement of image degradation, in particular to an image quality evaluation method and device for mixed degraded images. Background technique [0002] The degradation introduced in the process of image acquisition, compression and storage makes the degraded image obtained by the user and the image of ideal quality visually very different. The causes of these degradations are different, the characteristics of the performance are different, and the impact on the vision is also different, so they need to be treated differently. For example, when doing image evaluation, divide the degradation types into passivation degradation and noise degradation, and quantify them separately, and then weight the passivation component and noise component separately, so that more accurate quality evaluation results can be obtained; The sharpening strength is determined according to the degree of bluntness, and the streng...

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): G06T5/00
CPCG06T5/002G06T2207/20081G06T2207/30168
Inventor 孙斌
Owner 重庆瑞景信息科技有限公司
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