• DocumentCode
    1616157
  • Title

    Real time architecture for vector quantization in residue number system

  • Author

    Goel, B.D. ; Jamali, M.M. ; Kwatra, S.C.

  • Author_Institution
    Fonar Corp., Melville, NY, USA
  • fYear
    1989
  • Firstpage
    204
  • Abstract
    A fast and simplified systolic array architecture for real-time implementation of vector quantization is proposed. The proposed architecture uses the residue number system (RNS) for arithmetic operations. The arithmetic operations can be precomputed and stored in the lookup tables, and the computation time of the arithmetic operations is the access time of the lookup table. The proposed architecture is capable of generating a codevector index each clock cycle with exhaustive search of codebook. A memory-intensive RNS implementation of the systolic array architecture is proposed
  • Keywords
    cellular arrays; digital arithmetic; parallel architectures; real-time systems; table lookup; access time; arithmetic operations; clock cycle; codebook exhaustive search; codevector index; computation time; fast systolic array architecture; lookup tables; memory-intensive RNS implementation; real-time implementation; residue number system; simplified systolic array architecture; vector quantization; Arithmetic; Clocks; Computer architecture; Distortion measurement; Image coding; Real time systems; Signal to noise ratio; Systolic arrays; Table lookup; Vector quantization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Circuits and Systems, 1989., IEEE International Symposium on
  • Conference_Location
    Portland, OR
  • Type

    conf

  • DOI
    10.1109/ISCAS.1989.100327
  • Filename
    100327