Learning no-reference quality metric by examples

Hanghang Tong, Mingjing Li, Hong Jiang Zhang, Changshui Zhang, Jingrui He, Wei Ying Ma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

33 Scopus citations

Abstract

In this paper, a novel learning based method is proposed for No-Reference image quality assessment. Instead of examining the exact prior knowledge for the given type of distortion and finding a suitable way to represent it, our method aims to directly get the quality metric by means of learning. At first, some training examples are prepared for both high-quality and low-quality classes; then a binary classifier is built on the training set; finally the quality metric of an un-labeled example is denoted by the extent to which it belongs to these two classes. Different schemes to acquire examples from a given image, to build the binary classifier and to model the quality metric are proposed and investigated. While most existing methods are tailored for some specific distortion type, the proposed method might provide a general solution for No-Reference image quality assessment. Experimental results on JPEG and JPEG2000 compressed images validate the effectiveness of the proposed method.

Original languageEnglish (US)
Title of host publicationProceedings of the 11th International Multimedia Modelling Conference, MMM 2005
Pages247-254
Number of pages8
DOIs
StatePublished - Dec 1 2005
Event11th International Multimedia Modelling Conference, MMM 2005 - Melbourne, VIC, Australia
Duration: Jan 12 2005Jan 14 2005

Publication series

NameProceedings of the 11th International Multimedia Modelling Conference, MMM 2005

Other

Other11th International Multimedia Modelling Conference, MMM 2005
CountryAustralia
CityMelbourne, VIC
Period1/12/051/14/05

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Modeling and Simulation

Fingerprint Dive into the research topics of 'Learning no-reference quality metric by examples'. Together they form a unique fingerprint.

Cite this