Presentation 2011-02-18
Performance comparison of the hashing retrieval method for the large-scale video data
Noboru MURABAYASHI, Kenichi YOSHIDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the previous researchs, we proposed the Tiny LSH method as a high-speed retrieval technique for the large-scale video data. The Tiny LSH method is the retrieval method that combines bit shift processing with Direct-mapped cache data structure, and similar data can be retrieved at high speed as well as conventional LSH method. In this paper, the retrieval performances with Tiny LSH method, chain method, and conventional LSH methods were compared using video data. Experimental result shows that Tiny LSH method is superior to the conventional hashing method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) video retrieval / image feature / Locality-sensitive hashing / Direct-Mapped Cache / pointer
Paper # PRMU2010-226
Date of Issue

Conference Information
Committee PRMU
Conference Date 2011/2/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Performance comparison of the hashing retrieval method for the large-scale video data
Sub Title (in English)
Keyword(1) video retrieval
Keyword(2) image feature
Keyword(3) Locality-sensitive hashing
Keyword(4) Direct-Mapped Cache
Keyword(5) pointer
1st Author's Name Noboru MURABAYASHI
1st Author's Affiliation Graduate School of Business Sciences, University of Tsukuba()
2nd Author's Name Kenichi YOSHIDA
2nd Author's Affiliation Graduate School of Business Sciences, University of Tsukuba
Date 2011-02-18
Paper # PRMU2010-226
Volume (vol) vol.110
Number (no) 414
Page pp.pp.-
#Pages 6
Date of Issue