A fast encoding algorithm for vector quantization based on haar wavelet transform

Jiann Der Lee*, Yaw Hwang Chiou

*Corresponding author for this work

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

Abstract

For vector quantization (VQ), it is extremely time-consuming to extract the similar codeword with input vector during the encoding process. In this paper, we present an efficient algorithm to extract the features of input vector using Haar Wavelet Transform (HWT) and use these features to early remove impossible codeword in the distortion computations stage. From the experimental results, it is shown that the proposed approach can largely decrease the computation time for achieving VQ coding with the same quality with full search algorithm. More specifically, compared with the DHSS algorithm, the proposed algorithm reduces the computational time by 31% to 61%. Compared with the Pan's algorithm, the proposed algorithm reduces the computational time by 62% to 75%. Compared with the Lai's algorithm, the proposed algorithm reduces the computational time by 48% to 58%. Compared with the HTPDE algorithm, the proposed algorithm reduces the computational time by 27% to 44%. Compared with the WTPDE algorithm, the proposed algorithm reduces the computational time by 21% to 45%.

Original languageEnglish
Title of host publicationProceedings - IEEE INDIN 2008
Subtitle of host publication6th IEEE International Conference on Industrial Informatics
Pages683-687
Number of pages5
DOIs
StatePublished - 2008
EventIEEE INDIN 2008: 6th IEEE International Conference on Industrial Informatics - Daejeon, Korea, Republic of
Duration: 13 07 200816 07 2008

Publication series

NameIEEE International Conference on Industrial Informatics (INDIN)
ISSN (Print)1935-4576

Conference

ConferenceIEEE INDIN 2008: 6th IEEE International Conference on Industrial Informatics
Country/TerritoryKorea, Republic of
CityDaejeon
Period13/07/0816/07/08

Keywords

  • Haar wavelet transform
  • Image coding
  • Vector quantization

Fingerprint

Dive into the research topics of 'A fast encoding algorithm for vector quantization based on haar wavelet transform'. Together they form a unique fingerprint.

Cite this