ヤマグチ　カズアキ   Kazuaki Yamaguchi   山口　一章    所属   追手門学院大学  理工学部 情報工学科    職種   教授
言語種別	英語
発行・発表の年月	2006/01
形態種別	外国学会誌（その他）
査読	査読あり
標題	Improvements of TLAESA nearest neighbour search algorithm and extension to approximation search
執筆形態	共著・編著（代表編著を除く）
掲載誌名	Proceedings of the 29th Australasian Computer Science Conference
出版社・発行元	Australian Computer Society
巻・号・頁	pp.77-83,pp.77-83
担当区分	責任著者
著者・共著者	TOKORO Ken,YAMAGUCHI Kazuaki,MASUDA Sumio
概要	Nearest neighbour (NN) searches and κnearest neighbour (κ-NN) searches are widely used in pattern recognition and image retrieval. An NN (κ-NN) search finds the closest object (closest κ objects) to a query object. Although the definition of the distance between objects depends on applications, its computation is generally complicated and time-consuming. It is therefore important to reduce the number of distance computations. TLAESA (Tree Linear Approximating and Eliminating Search Algorithm) is one of the fastest algorithms for NN searches. This method reduces distance computations by using a branch and bound algorithm. In this paper we improve both the data structure and the search algorithm of TLAESA. The proposed method greatly reduces the number of distance computations. Moreover, we extend the improved method to an approximation search algorithm which ensures the quality of solutions. Experimental results show that the proposed method is efficient and finds an approximate solution with a very low error rate. Copyright © 2006, Australian Computer Society, Inc.
ISSN	1445-1336
DBLP ID	conf/acsc/TokoroYM06
PermalinkURL	https://dl.acm.org/citation.cfm?id=1151709
researchmap用URL	https://dblp.uni-trier.de/rec/conf/acsc/2006