Fast codebook design for vector quantization on partitioned space

Shintaro Momose, Kentaro Sano, Tadao Nakamura

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Vector quantization(VQ) is an attractive technique for lossy data compression, which has been a key technology for data storage and/or transfer. So far, various competitive learning (CL) algorithms have been proposed to design optimal code-books presenting quantization with minimized errors. However, their practical use has been limited for large scale problems, due to the computational complexity of competitive learning. This paper presents a fast codebook design algorithm reducing the computational complexity. The algorithm partitions input-vector space into some subspaces, and designs a subcodebook for each subspace independently. Experimental results indicate a speedup of this algorithm without serious increase of quantization errors, and promising potential of its parallelization.

本文言語English
ホスト出版物のタイトルProceedings of the Second International Conference on Information Technology and Applications (ICITA 2004)
ページ58-63
ページ数6
出版ステータスPublished - 2004
外部発表はい
イベントProceedings of the Second International Conference on Information Technology and Applications (ICITA 2004) - Harbin, China
継続期間: 2004 1月 92004 1月 11

出版物シリーズ

名前Proceedings of the Second International Conference on Information Technology and Applications (ICITA 2004)

Other

OtherProceedings of the Second International Conference on Information Technology and Applications (ICITA 2004)
国/地域China
CityHarbin
Period04/1/904/1/11

ASJC Scopus subject areas

  • 工学(全般)

フィンガープリント

「Fast codebook design for vector quantization on partitioned space」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル