基于高通差异性特征的图像质量评估方法

Translated title of the contribution: High-Pass Difference Features Based Image Quality Assessment

Rui Wang, Ping Li, Bin Sheng, Congbin Qiao, Lizhuang Ma, Enhua Wu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

Current methods of image quality assessment only can assess the quality of images under the same type of image distortion. In order to fix such weaknesses, this paper is designed based on the image features of natural scene statistics and proposes a new metric method using high-pass filter for detecting features. The approach computes locally the normalized luminance; selects features such as the difference of RGB channels via high-pass filter, image gradient, sharpness, contrast, etc.; and analyzes and gathers features in the metric method trained by logistic regression. Experimental results show that the proposed method can work efficiently under multiple distortion types and is significantly better than current no-reference image quality assessment methods under the test sets, which gather multiple distortion types.

Translated title of the contributionHigh-Pass Difference Features Based Image Quality Assessment
Original languageChinese
Pages (from-to)227-237
Number of pages11
JournalXitong Fangzhen Xuebao / Journal of System Simulation
Volume31
Issue number2
DOIs
Publication statusPublished - 8 Feb 2019
Externally publishedYes

Keywords

  • Image quality assessment
  • Logistic regression
  • Natural scene statistics
  • No-reference

ASJC Scopus subject areas

  • Modelling and Simulation
  • Aerospace Engineering
  • Computer Science Applications

Cite this