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

Image Quality Evaluation Method Based on Visual Perception

A technology for quality evaluation and image capture, which is applied in the field of image processing, can solve problems such as the inability to apply image capture, and achieve the effects of excellent performance, simple training process, and simple calculation

Active Publication Date: 2018-09-11
XIDIAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, starting from the distortion nature of captured images, combined with human visual characteristics, to propose a method for evaluating the quality of captured images based on visual perception, so as to solve the problem of manual processing in traditional image quality assessment. Distortion types that cannot be applied to the defects of actual captured images, and it is easier to achieve effective and accurate evaluation of captured image quality

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 Based on Visual Perception
  • Image Quality Evaluation Method Based on Visual Perception
  • Image Quality Evaluation Method Based on Visual Perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] The present invention is a method for evaluating the quality of photographed images based on visual perception, including feature extraction of standard images and test images, see figure 1 , the image quality evaluation process includes:

[0026](1) Convert a standard image from the RGB color space to the HSI color space, obtain the hue component, saturation component and brightness component of the standard image respectively, and use the hue component to describe the main color component, which can be distinguished according to the characteristics of human visual perception The difference between color and achromatic color with the same brightness; the saturation component is used to measure the purity of color, that is, the degree to which a pure color is diluted by white light. According to the characteristics of human visual perception, when the saturation value is small, the described color fades faster. Severe; describes the brightness of a color with a luminanc...

Embodiment 2

[0034] The method for evaluating the quality of photographed images based on visual perception is the same as in Embodiment 1, and the framework of the quality evaluation model for photographed images based on visual perception proposed by the present invention is as follows: figure 2 shown.

[0035] A standard image in the step (1) is converted from the RGB color space to the HSI color space, and the hue component H, the saturation component S and the brightness component I of the standard image are obtained respectively, wherein the calculation of the hue component H is shown in the following formula:

[0036]

[0037] In the formula, δ is an angular vector, which is used to express the hue component H. When the blue component B of the standard image is not greater than the green component G, the hue component H is equal to δ; when the blue component B of the standard image is smaller than the green component G , the hue component H is equal to 2π-δ. The expression of δ...

Embodiment 3

[0046] The shooting image quality evaluation method based on visual perception is the same as embodiment 1-2,

[0047] Ask the gradient coefficient of standard image described in the step (2), be to the hue component of standard image, saturation component, brightness component and grayscale image ask gradient coefficient, concrete calculation process is as follows:

[0048]

[0049] In the above formula, P(m,n) represents the gradient matrix obtained after the gradient operation. The gradient matrix represents the gradient coefficient, where m represents the abscissa of the image, and n represents the ordinate of the image; G(m, n) represent hue component H, saturation component S, brightness component I and grayscale image matrix respectively; Indicates linear convolution, g x , g y Represents the Gaussian partial derivative functions in the horizontal and vertical directions. The expression of the Gaussian partial derivative function is as follows:

[0050]

[00...

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 method for evaluating the quality of photographed images based on visual perception, which mainly solves the problem of poor performance of traditional image quality evaluation methods for evaluating the quality of photographed images. Implementation process: convert the standard image to the HIS color space; find the gradient coefficient of the standard image, calculate the gradient coefficient of the hue component, saturation component, brightness component and grayscale image of the standard image, and normalize each gradient coefficient respectively ; use estimated parameters to characterize the image quality; model training, calculate the quality features of all standard images in the training set; obtain the quality score of the test image by comparing the difference between the test image and the standard image quality features. The invention is simple in calculation, and the experimental results show that the invention has high consistency with the subjective quality evaluation, the evaluation performance is better than the existing image quality evaluation method, and has strong practical value.

Description

technical field [0001] The invention belongs to the technical field of image processing, and mainly relates to a method for evaluating the quality of photographed images, in particular to a method for evaluating the quality of photographed images based on visual perception, which can be used in application processes such as automatic compression, storage, and enhancement of photographed images. Background technique [0002] With the advent of the information age, multimedia information analysis, big data processing technology, cloud computing and Internet of Things platforms are developing rapidly as the main ways for people to obtain information. As the main carrier of information transmission, images play an important role in the process of information interaction, which enables people to obtain information and recognize things intuitively, vividly and vividly. However, due to the incompleteness of various image acquisition devices, the complexity of the storage and proces...

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): G06T7/90G06K9/62
CPCG06F18/214
Inventor 路文任玉玲贾长城许天骄何立火邓成王颖王斌王秀美牛振兴
Owner XIDIAN 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