Fast radix-3/6 algorithms for the realization of the dciscrete cosine transform

Yuk Hee Chan, Wan Chi Siu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

5 Citations (Scopus)

Abstract

This paper presents two new fast discrete cosine transform computation algorithms: radix-3 and radix-6 algorithm. They are superior to the conventional radix-2 algorithm as they require less computational complexity. Besides, they provide a wider choice of the sequence length for which the DCT can be realized and support the prime-factor-decomposed computation algorithm to realize the 2m3n-point DCT. Furthermore, a mixed-radix algorithm is proposed such that an optimal performance can be achieved by applying the proposed radix-3 and radix-6 and the well-developed radix-2 decomposition techniques in a proper sequence. This mixed-radix algorithm not only possesses the advantages mentioned above. Compared with the prime-factor-decomposed algorithm, this mixed-radix algorithm i) requires less computational effort and ii) saves complicated data routing and mapping procedures.

Original languageEnglish
Title of host publication1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages153-156
Number of pages4
ISBN (Electronic)0780305930
DOIs
Publication statusPublished - 10 May 1992
Event1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 - San Diego, United States
Duration: 10 May 199213 May 1992

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume1
ISSN (Print)0271-4310

Conference

Conference1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992
Country/TerritoryUnited States
CitySan Diego
Period10/05/9213/05/92

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Fast radix-3/6 algorithms for the realization of the dciscrete cosine transform'. Together they form a unique fingerprint.

Cite this