Unlock instant, AI-driven research and patent intelligence for your innovation.

SVR parameter optimization method in blind image quality evaluation algorithm

A technology of image quality evaluation and optimization method, which is applied in image data processing, kernel method, image analysis and other directions to achieve the effect of enhancing generalization ability and improving prediction accuracy

Active Publication Date: 2019-11-26
NANCHANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the problem that the selection of penalty parameter C and kernel function parameter σ has been ignored for a long time in the field of blind image quality evaluation SVR, a method based on the improved ABC algorithm to optimize SVR parameters is provided, and it is introduced into the blind image quality evaluation algorithm for the first time. Enhance SVR generalization ability in blind image quality assessment and improve SVR prediction accuracy

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
  • SVR parameter optimization method in blind image quality evaluation algorithm
  • SVR parameter optimization method in blind image quality evaluation algorithm
  • SVR parameter optimization method in blind image quality evaluation algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0034] Such as figure 1 As shown, step 1: collect data on the LIVE database, including image features and corresponding image human subjective scores. Image features are normalized to map the human subjective score to a suitable interval (recommended interval is [0,100]). Perform 5-fold cross-validation on the data, and use the penalty parameter C in SVR and the radial basis kernel function parameter σ as the parameters to be optimized.

[0035] Step 2: Use the parameter to be optimized (C, σ) selected in step 1 as the corresponding dimension value of the particle at the current position. Use 5-fold cross-validation to get 5 Root Mean Squared Errors (Root Mean Squared Error, RMSE), and use the median of the 5 RMSEs as the fitness value of the particle at the current position.

[0036] Step 3: Initialize the relevant parameters of the improved ABC algo...

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 SVR parameter optimization method in a blind image quality evaluation algorithm, and the method comprises the following steps: 1, collecting data, carrying out the five-foldcross verification of the data, and selecting a parameter affecting the prediction performance in SVR as a to-be-optimized parameter; 2, taking the selected parameter to be optimized as a corresponding dimension value of the particle at the current position, obtaining five root-mean-square errors by using five-fold cross validation, and taking a median of the five RMSEs as a fitness value of theparticle at the current position; 3, initializing related parameters of the improved ABC algorithm; 4, evaluating the particles, and calculating fitness values corresponding to the current positions of the particles; 5, if the stop condition is met, ending the parameter optimization process, and outputting the optimal combination of the to-be-optimized parameters; otherwise, returning to the step4 to continue to execute the optimization process until the stop condition is met.

Description

technical field [0001] The invention belongs to the technical field of image processing and image quality evaluation, and relates to an SVR parameter optimization method, in particular to an SVR parameter optimization method for blind image quality evaluation based on an improved artificial bee colony algorithm, which can be used for various natural images, medical images, and HDR images and the screen image field. Background technique [0002] With the continuous development and popularization of digital imaging technology and mobile smart devices, it is very easy to capture and acquire digital images. With the increasing number of digital images and the advent of the 5G era, digital images involve more and more industries. In practical applications, high-quality images are the key to ensuring a good experience for end users. However, in the stages of image acquisition, storage, compression, transmission and reproduction, images often suffer from a series of distortions. ...

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 Applications(China)
IPC IPC(8): G06T7/00G06N3/00G06N20/10
CPCG06T7/0002G06N3/006G06N20/10G06T2207/30168G06T2207/20081
Inventor 李春泉肖典罗族
Owner NANCHANG UNIV