Presentation 2005-02-25
Nearest Neighbor Search and Classification Techniques and Their Applications to Image Understanding Problems
Toshikazu WADA, Koji TAKEMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Nearest neighbor search is one of the most fundamental technique, which is applied to wide varieties of problems, such as, nearest neighbor classification, Iterative Closest Point (ICP) algorithms, database retrieval, and so on. The exhaustive nearest neighbor search consumes considerable computation time for large data set. For solving this problem, many acceleration methods have been proposed, such as, k-d tree, (M) VP tree, (L) AESA, and so on. Since the performances of these methods depend on the tasks, e.g. 1-NN, K-NN, range search, and conditions, e.g. number of data and dimensionality, we cannot compare them in a straight forward manner. In this report, we first classify them into some classes, and some applications to Image Understanding problems are shown. Next, we focus on the nearest neighbor classification, and discuss its acceleration techniques and applications.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Nearest Neighbor Search / Nearest Neighbor Classification / Acceleration / Partitioning / Schwarz' inequality
Paper # NLC2004-128,PRMU2004-210
Date of Issue

Conference Information
Committee NLC
Conference Date 2005/2/18(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Nearest Neighbor Search and Classification Techniques and Their Applications to Image Understanding Problems
Sub Title (in English)
Keyword(1) Nearest Neighbor Search
Keyword(2) Nearest Neighbor Classification
Keyword(3) Acceleration
Keyword(4) Partitioning
Keyword(5) Schwarz' inequality
1st Author's Name Toshikazu WADA
1st Author's Affiliation Faculty of Systems Engineering, Wakayama University()
2nd Author's Name Koji TAKEMOTO
2nd Author's Affiliation Faculty of Systems Engineering, Wakayama University
Date 2005-02-25
Paper # NLC2004-128,PRMU2004-210
Volume (vol) vol.104
Number (no) 668
Page pp.pp.-
#Pages 6
Date of Issue