An improved simulated annealing algorithm for vector quantizer design

Mengyu Zhu*, Yuliang Yang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

An improved Simulated Annealing algorithm in conjunction with GLA algorithm has been proposed in this paper. Using SA algorithm and new distortion measure, our new algorithm can avoid the GLA algorithm's defect in that is sensitive to the original codebook and is easy to fall into the locally optimal solution during the searching. The experiment results indicate that the improved algorithm can efficiently eliminate the sensibility to the original codebook, and improve performance for searching ability and subjective quality of decoding image.

Original languageEnglish
Title of host publication2009 World Summit on Genetic and Evolutionary Computation, 2009 GEC Summit - Proceedings of the 1st ACM/SIGEVO Summit on Genetic and Evolutionary Computation, GEC'09
Pages1077-1080
Number of pages4
DOIs
Publication statusPublished - 2009
Event2009 World Summit on Genetic and Evolutionary Computation, 2009 GEC Summit - 1st ACM/SIGEVO Summit on Genetic and Evolutionary Computation, GEC'09 - Shanghai, China
Duration: 12 Jun 200914 Jun 2009

Publication series

Name2009 World Summit on Genetic and Evolutionary Computation, 2009 GEC Summit - Proceedings of the 1st ACM/SIGEVO Summit on Genetic and Evolutionary Computation, GEC'09

Conference

Conference2009 World Summit on Genetic and Evolutionary Computation, 2009 GEC Summit - 1st ACM/SIGEVO Summit on Genetic and Evolutionary Computation, GEC'09
Country/TerritoryChina
CityShanghai
Period12/06/0914/06/09

Keywords

  • GLA
  • Image
  • Metrics iteration
  • Simulated annealing
  • Subjective quality
  • VQ

Fingerprint

Dive into the research topics of 'An improved simulated annealing algorithm for vector quantizer design'. Together they form a unique fingerprint.

Cite this