No-reference image quality assessment through interactive neuroevolution

Yury R. Tsoy, Vladimir G. Spitsyn, Alexander V. Chernyavsky

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

6 Citations (Scopus)

Abstract

Image quality assessment is a complex problem due to subjective nature of human visual perception. One of possible ways to take into consideration user's subjectivism is to develop interactive system which could learn the properties of user's visual perception. In this paper we present a novel way to do this via interactive neuroevolution approach. The key feature of this approach is training of artificial neural network to evaluate image quality on the base of interaction with user. Obtained solutions can then be used for image quality assessment for various automated image and video processing techniques.

Original languageEnglish
Title of host publicationGraphiCon 2007 - International Conference on Computer Graphics and Vision, Proceedings
Publication statusPublished - 2007
Event17th International Conference on Computer Graphics and Vision, GraphiCon 2007 - Moscow, Russian Federation
Duration: 23 Jun 200727 Jun 2007

Other

Other17th International Conference on Computer Graphics and Vision, GraphiCon 2007
CountryRussian Federation
CityMoscow
Period23.6.0727.6.07

Keywords

  • Image quality assessment
  • Interactive evolution
  • Neuroevolution

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'No-reference image quality assessment through interactive neuroevolution'. Together they form a unique fingerprint.

Cite this