• DocumentCode
    2751224
  • Title

    Parallel Huffman decoder with an optimized look up table option on FPGA

  • Author

    Aspar, By Zulfakar ; Yusof, Zulkalnain Mohd ; Suleiman, Ishak

  • Author_Institution
    Fac. of Electr. Eng., Univ. Teknologi Malaysia, Malaysia
  • Volume
    1
  • fYear
    2000
  • fDate
    2000
  • Firstpage
    73
  • Abstract
    Compression is very important for systems with limited channel bandwidth and/or limited storage size. One of the main components in image/video compression is variable length coding (VLC). This paper discusses one of the most popular VLC technique known as Huffman coding. A real time hardware parallel Huffman decoder has been successfully designed and implemented using 50,000 gate FPGA (FLEX10K20 from Altera). The parallelism is exploited in the design to achieve the high frame rate such as in JPEG and MPEG implementation. Using a parallel technique, a codeword is guaranteed to be processed within a single clock cycle. The codeword to be processed is matched with the one stored in a look up table (LUT). A LUT is needed during the coding and decoding process. In order to save memory cost, an optimized LUT is suggested. This paper does not intend to complete an optimized operating speed design, but instead only concentrates on producing a workable real-time decoder design
  • Keywords
    Huffman codes; data compression; decoding; digital signal processing chips; field programmable gate arrays; image coding; parallel architectures; table lookup; variable length codes; video coding; Altera FLEX10K20; FPGA; Huffman coding; codeword processing; high frame rate; image compression; optimized look up table option; parallel Huffman decoder; real-time decoder design; variable length coding; video compression; Bandwidth; Clocks; Cost function; Decoding; Field programmable gate arrays; Hardware; Huffman coding; Image coding; Table lookup; Video compression;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    TENCON 2000. Proceedings
  • Conference_Location
    Kuala Lumpur
  • Print_ISBN
    0-7803-6355-8
  • Type

    conf

  • DOI
    10.1109/TENCON.2000.893543
  • Filename
    893543